Sample records for satellite image classification

  1. Biogeography based Satellite Image Classification


    Harish Kundra; Parminder Singh; Navdeep Kaur; V.K. Panchal


    Biogeography is the study of the geographical distribution of biological organisms. The mindset of the engineer is that we can learn from nature. Biogeography Based Optimization is a burgeoning nature inspired technique to find the optimal solution of the problem. Satellite image classification is an important task because it is the only way we can know about the land cover map of inaccessible areas. Though satellite images have been classified in past by using various techniques, the researc...


    Directory of Open Access Journals (Sweden)

    P. Kupidura


    Full Text Available In this paper, we present a proposition of a fully automatic classification of VHR satellite images. Unlike the most widespread approaches: supervised classification, which requires prior defining of class signatures, or unsupervised classification, which must be followed by an interpretation of its results, the proposed method requires no human intervention except for the setting of the initial parameters. The presented approach bases on both spectral and textural analysis of the image and consists of 3 steps. The first step, the analysis of spectral data, relies on NDVI values. Its purpose is to distinguish between basic classes, such as water, vegetation and non-vegetation, which all differ significantly spectrally, thus they can be easily extracted basing on spectral analysis. The second step relies on granulometric maps. These are the product of local granulometric analysis of an image and present information on the texture of each pixel neighbourhood, depending on the texture grain. The purpose of texture analysis is to distinguish between different classes, spectrally similar, but yet of different texture, e.g. bare soil from a built-up area, or low vegetation from a wooded area. Due to the use of granulometric analysis, based on mathematical morphology opening and closing, the results are resistant to the border effect (qualifying borders of objects in an image as spaces of high texture, which affect other methods of texture analysis like GLCM statistics or fractal analysis. Therefore, the effectiveness of the analysis is relatively high. Several indices based on values of different granulometric maps have been developed to simplify the extraction of classes of different texture. The third and final step of the process relies on a vegetation index, based on near infrared and blue bands. Its purpose is to correct partially misclassified pixels. All the indices used in the classification model developed relate to reflectance values, so the

  3. Classification of Pansharpened Urban Satellite Images

    DEFF Research Database (Denmark)

    Palsson, Frosti; Sveinsson, Johannes R.; Benediktsson, Jon Atli


    The classification of high resolution urban remote sensing imagery is addressed with the focus on classification of imagery that has been pansharpened by a number of different pansharpening methods. The pansharpening process introduces some spectral and spatial distortions in the resulting fused...... information from the panchromatic data. Random Forests (RF) and Support Vector Machines (SVM) will be used as classifiers. Experiments are done for three different datasets that have been obtained by two different imaging sensors, IKONOS and QuickBird. These sensors deliver multispectral images that have four...

  4. Panchromatic Satellite Image Classification for Flood Hazard Assessment

    Directory of Open Access Journals (Sweden)

    Ahmed Shaker


    Full Text Available The study aims to investigate the use of panchromatic (PAN satellite image data for flood hazard assessment with anaid of various digital image processing techniques. Two SPOT PAN satellite images covering part of the Nile River inEgypt were used to delineate the flood extent during the years 1997 and 1998 (before and after a high flood. Threeclassification techniques, including the contextual classifier, maximum likelihood classifier and minimum distanceclassifier, were applied to the following: 1 the original PAN image data, 2 the original PAN image data and grey-levelco-occurrence matrix texture created from the PAN data, and 3 the enhanced PAN image data using an edgesharpeningfilter. The classification results were assessed with reference to the results derived from manualdigitization and random checkpoints. Generally, the results showed improvement of the calculation of flood area whenan edge-sharpening filter was used. In addition, the maximum likelihood classifier yielded the best classificationaccuracy (up to 97% compared to the other two classifiers. The research demonstrates the benefits of using PANsatellite imagery as a potential data source for flood hazard assessment.

  5. Satellite Image Classification and Segmentation by Using JSEG Segmentation Algorithm


    Khamael Abbas; Mustafa Rydh


    In this paper, a adopted approach to fully automatic satellite image segmentation, called JSEG, "JPEG image segmentation" is presented. First colors in the image are quantized to represent differentiate regions in the image. Then image pixel colors are replaced by their corresponding color class labels, thus forming a class-map of the image. A criterion for “good” segmentation using this class-map is proposed. Applying the criterion to local windows in the class-map results in the “J-image”...

  6. Classification-based vehicle detection in high-resolution satellite images (United States)

    Eikvil, Line; Aurdal, Lars; Koren, Hans

    In this study, we have looked into the problem of vehicle detection in high-resolution satellite images. Based on the input from the local road authorities, we have focused not only on highways, but also on inner city roads, where more clutter is expected. The study site is the city of Oslo, Norway. To do vehicle detection in these areas, we propose an automatic approach, consisting of a segmentation step, followed by two stages of object classification. In the process, we utilize multispectral images, panchromatic images and a road network. The approach has been tested on Quickbird images, and the results that are obtained have been compared with manual counts and classifications.

  7. Satellite image classification by narrowband Gabor filters and artificial neural networks (United States)

    Nezamoddini-Kachouie, Nezamoddin; Alirezaie, Javad


    Satellite image segmentation is an important task to generate classification maps. Land areas are classified and clustered into groups of similar land cover or land use by segmentation of satellite images. It may be broad classification such as urban, forested, open fields and water or may be more specific such as differentiating corn, soybean, beet and wheat fields. One of the most important among them is partitioning the urban area to different regions. On the other hand Multi-Channel filtering is used widely for texture segmentation by many researchers. This paper describes a texture segmentation algorithm to segment satellite images using Gabor filter bank and neural networks. In the proposed method feature vectors are extracted by multi-channel decomposition. The spatial/spatial-frequency features of the input satellite image are extracted by optimized Gabor filter bank. Some important considerations about filter parameters, filter bank coverage in frequency domain and the reduction of feature dimensions are discussed. A competitive network is trained to extract the best features and to reduce the feature dimension. Eventually a Multi-Layer Perceptron (MLP) is employed to accomplish the segmentation task. Our MLP uses the sigmoid transfer function in all layers and during the training, random selected feature vectors are assigned to proper classes. After MLP is trained the optimized extracted features are classified into sections according to the textured land cover regions.

  8. Remote Sensing Image Classification of Geoeye-1 High-Resolution Satellite (United States)

    Yang, B.; Yu, X.


    Networks play the role of a high-level language, as is seen in Artificial Intelligence and statistics, because networks are used to build complex model from simple components. These years, Bayesian Networks, one of probabilistic networks, are a powerful data mining technique for handling uncertainty in complex domains. In this paper, we apply Bayesian Networks Augmented Naive Bayes (BAN) to texture classification of High-resolution satellite images and put up a new method to construct the network topology structure in terms of training accuracy based on the training samples. In the experiment, we choose GeoEye-1 satellite images. Experimental results demonstrate BAN outperform than NBC in the overall classification accuracy. Although it is time consuming, it will be an attractive and effective method in the future.

  9. Evaluation of different fitness functions integrated with genetic algorithm on unsupervised classification of satellite images (United States)

    Yang, Y. F.; Yang, M. D.; Tsai, T. Y.


    In traditional unsupervised classification method, the number of clusters usually needs to be assigned subjectively by analysts, but in fact, in most situations, the prior knowledge of the research subject is difficult to acquire, so the suitable and best cluster numbers are very difficult to define. Therefore, in this research, an effective heuristic unsupervised classification method-Genetic Algorithm (GA) is introduced and tested here, because it can be through the mathematical model and calculating procedure of optimization to determine the best cluster numbers and centers automatically. Furthermore, two well-known models--Davies-Bouldin's and the K-Means algorithm, which adopted by most research for the applications in pattern classification, are integrated with GA as the fitness functions. In a word, in this research, a heuristic method-Genetic Algorithm (GA), is adopted and integrated with two different indices as the fitness functions to automatically interpret the clusters of satellite images for unsupervised classification. The classification results were compared to conventional ISODATA results, and to ground truth information derived from a topographic map for the estimation of classification accuracy. All image-processing program is developed in MATLAB, and the GA unsupervised classifier is tested on several image examples.

  10. Topic Modelling for Object-Based Unsupervised Classification of VHR Panchromatic Satellite Images Based on Multiscale Image Segmentation

    Directory of Open Access Journals (Sweden)

    Li Shen


    Full Text Available Image segmentation is a key prerequisite for object-based classification. However, it is often difficult, or even impossible, to determine a unique optimal segmentation scale due to the fact that various geo-objects, and even an identical geo-object, present at multiple scales in very high resolution (VHR satellite images. To address this problem, this paper presents a novel unsupervised object-based classification for VHR panchromatic satellite images using multiple segmentations via the latent Dirichlet allocation (LDA model. Firstly, multiple segmentation maps of the original satellite image are produced by means of a common multiscale segmentation technique. Then, the LDA model is utilized to learn the grayscale histogram distribution for each geo-object and the mixture distribution of geo-objects within each segment. Thirdly, the histogram distribution of each segment is compared with that of each geo-object using the Kullback-Leibler (KL divergence measure, which is weighted with a constraint specified by the mixture distribution of geo-objects. Each segment is allocated a geo-object category label with the minimum KL divergence. Finally, the final classification map is achieved by integrating the multiple classification results at different scales. Extensive experimental evaluations are designed to compare the performance of our method with those of some state-of-the-art methods for three different types of images. The experimental results over three different types of VHR panchromatic satellite images demonstrate the proposed method is able to achieve scale-adaptive classification results, and improve the ability to differentiate the geo-objects with spectral overlap, such as water and grass, and water and shadow, in terms of both spatial consistency and semantic consistency.

  11. Hyperion and CBERS satellite image classification intercomparison for Cerrado and agricultural mapping (United States)

    Filippi, Anthony M.; Brannstrom, Christian; Cairns, David M.; Kim, Daehyun


    The Cerrado is a savanna ecoregion with grassland and woodland subtypes covering ~one-quarter of Brazil and is considered to be a biodiversity hotspot, threatened by land-use conversion. Hyperspectral remote sensing enables spatio-temporal monitoring, while providing the possibility of vegetation-mapping at a high level of specificity. However, because imaging spectrometer data availability/coverage is currently limited, a need exists for effective exploitation of multispectral satellite imagery with broad-area spatial coverage. The objective was to assess the utility of hyperspectral Hyperion and multispectral CBERS-2 satellite imagery in discriminating among Cerrado subtypes and agricultural classes. Temporally-coincident field-transect data for Cerrado physiognomies and agricultural sites were collected, including biophysical metrics. Nonmetric multidimensional scaling and hierarchical cluster analysis were used to identify potential environmental gradients of biophysical groupings. Four Cerrado subclasses were identified: Campo Limpo (Open Cerrado Grassland), Campo Sujo (Shrub Savanna), Cerrado Típico (Wooded Cerrado), and Cerrado Denso (Cerrado Woodland). Subclasses were then merged, forming two Cerrado subclasses. To facilitate sensor intercomparison, image classification involved PCA transformations, followed by unsupervised clustering of the component images. Results indicate that both dimensionality-reduced Hyperion and CBERS datasets were sufficient in distinguishing between the two more general Cerrado subclasses and agriculture, but the Hyperion-derived classification was more accurate.

  12. Tree Species Classification in Temperate Forests Using Formosat-2 Satellite Image Time Series

    Directory of Open Access Journals (Sweden)

    David Sheeren


    Full Text Available Mapping forest composition is a major concern for forest management, biodiversity assessment and for understanding the potential impacts of climate change on tree species distribution. In this study, the suitability of a dense high spatial resolution multispectral Formosat-2 satellite image time-series (SITS to discriminate tree species in temperate forests is investigated. Based on a 17-date SITS acquired across one year, thirteen major tree species (8 broadleaves and 5 conifers are classified in a study area of southwest France. The performance of parametric (GMM and nonparametric (k-NN, RF, SVM methods are compared at three class hierarchy levels for different versions of the SITS: (i a smoothed noise-free version based on the Whittaker smoother; (ii a non-smoothed cloudy version including all the dates; (iii a non-smoothed noise-free version including only 14 dates. Noise refers to pixels contaminated by clouds and cloud shadows. The results of the 108 distinct classifications show a very high suitability of the SITS to identify the forest tree species based on phenological differences (average κ = 0 . 93 estimated by cross-validation based on 1235 field-collected plots. SVM is found to be the best classifier with very close results from the other classifiers. No clear benefit of removing noise by smoothing can be observed. Classification accuracy is even improved using the non-smoothed cloudy version of the SITS compared to the 14 cloud-free image time series. However conclusions of the results need to be considered with caution because of possible overfitting. Disagreements also appear between the maps produced by the classifiers for complex mixed forests, suggesting a higher classification uncertainty in these contexts. Our findings suggest that time-series data can be a good alternative to hyperspectral data for mapping forest types. It also demonstrates the potential contribution of the recently launched Sentinel-2 satellite for

  13. Mapping vegetation of a wetland ecosystem by fuzzy classification of optical and microwave satellite images supported by various ancillary data (United States)

    Stankiewicz, Krystyna; Dabrowska-Zielinska, Katarzyna; Gruszczynska, Maryla; Hoscilo, Agata


    An approach to classification of satellite images aimed at vegetation mapping in a wetland ecosystem has been presented. The wetlands of the Biebrza Valley located in the NE part of Poland has been chosen as a site of interest. The difficulty of using satellite images for the classification of a wetland land cover lies in the strong variability of the hydration state of such ecosystem in time. Satellite images acquired by optical or microwave sensors depend heavily on the current water level which often masks the most interesting long-time scale features of vegetation. Therefore the images have to be interpreted in the context of various ancillary data related to the investigated site. In the case of Biebrza Valley the most useful information was obtained from the soil and hydration maps as well as from the old vegetation maps. The object oriented classification approach applied in eCognition software enabled simultaneous use of satellite images together with the additional thematic data. Some supplementary knowledge concerning possible plant cover changes was also introduced into the process of classification. The accuracy of the classification was assessed versus ground-truth data and results of visual interpretation of aerial photos. The achieved accuracy depends on the type of vegetation community in question and is better for forest or shrubs than for meadows.

  14. Vegetation classification and quatification by satellite image processing. A case study in north Portugal

    Energy Technology Data Exchange (ETDEWEB)

    Aranha, J.T. [Dept. Florestal, UTAD, 5001-801 Vila Real (Portugal); Viana, H.F. [Instituto Politecnico de Viseu, Escola Superior Agraria, Viseu (Portugal); Rodrigues, R. [Bioflag - Consulting - Santo Tirso (Portugal)


    The expected increase in Forest Biomass demand for energy production leads to derive expeditious and non-expensive techniques in order to classify vegetal land cover and evaluate the available biomass like to be harvested. Satellite image processing and classification, combined to field work, is a suitable tool to achieve these aims. A vegetation index (NDVI) was created by means of a Landsat TM image, from 2006, manipulation, in order to create a general vegetation map. Then, the same image was submitted to a supervised classification process in order to produce a land cover map (overall accuracy of 85%). In a second stage, they were collected NDVI values for each sampling plot, in order to update the database previous developed with data collected within forestry stands and shrubland. This data merging enabled to transform general vegetation map into available biomass within forestry stands and shrubland. The results showed a range of values from 0.25 up to 6.00 dry ton./ha for recent and former burnt areas recovered by Pinus pinaster (maritime pine) young trees and from 2.00 up to 9.00 dry ton./ha for recent and former burnt areas recovered by shrubs (e.g. genista or broom).

  15. A new tool for supervised classification of satellite images available on web servers: Google Maps as a case study (United States)

    García-Flores, Agustín.; Paz-Gallardo, Abel; Plaza, Antonio; Li, Jun


    This paper describes a new web platform dedicated to the classification of satellite images called Hypergim. The current implementation of this platform enables users to perform classification of satellite images from any part of the world thanks to the worldwide maps provided by Google Maps. To perform this classification, Hypergim uses unsupervised algorithms like Isodata and K-means. Here, we present an extension of the original platform in which we adapt Hypergim in order to use supervised algorithms to improve the classification results. This involves a significant modification of the user interface, providing the user with a way to obtain samples of classes present in the images to use in the training phase of the classification process. Another main goal of this development is to improve the runtime of the image classification process. To achieve this goal, we use a parallel implementation of the Random Forest classification algorithm. This implementation is a modification of the well-known CURFIL software package. The use of this type of algorithms to perform image classification is widespread today thanks to its precision and ease of training. The actual implementation of Random Forest was developed using CUDA platform, which enables us to exploit the potential of several models of NVIDIA graphics processing units using them to execute general purpose computing tasks as image classification algorithms. As well as CUDA, we use other parallel libraries as Intel Boost, taking advantage of the multithreading capabilities of modern CPUs. To ensure the best possible results, the platform is deployed in a cluster of commodity graphics processing units (GPUs), so that multiple users can use the tool in a concurrent way. The experimental results indicate that this new algorithm widely outperform the previous unsupervised algorithms implemented in Hypergim, both in runtime as well as precision of the actual classification of the images.

  16. Land Cover Classification Using a KOMPSAT-3A Multi-Spectral Satellite Image

    Directory of Open Access Journals (Sweden)

    Tri Dev Acharya


    Full Text Available New sets of satellite sensors are frequently being added to the constellation of remote sensing satellites. These new sets offer improved specification to collect imagery on-demand over specific locations and for specific purposes. The Korea Multi-Purpose Satellite (KOMPSAT series of satellites is a multi-purposed satellite system developed by Korea Aerospace Research Institute (KARI. The recent satellite of the KOMPSAT series, KOMPSAT-3A, demonstrates high resolution multi-spectral imagery with infrared and high resolution electro-optical bands for geographical information systems applications in environmental, agricultural and oceanographic sciences as well as natural disasters. In this study, land cover classification of multispectral data was performed using four supervised classification methods: Mahalanobis Distance (MahD, Minimum Distance (MinD, Maximum Likelihood (ML and Support Vector Machine (SVM, using a KOMPSAT-3A multi-spectral imagery with 2.2 m spatial resolution. The study area for this study was selected from southwestern region of South Korea, around Buan city. The training data for supervised classification was carefully selected by visual interpretation of KOMPSAT-3A imagery and field investigation. After classification, the results were then analyzed for the validation of classification accuracy by comparison with those of field investigation. For the validation, we calculated the User’s Accuracy (UA, Producer’s Accuracy (PA, Overall Accuracy (OA and Kappa statistics from the error matrix to check the classification accuracy for each class obtained individually from different methods. Finally, the comparative analysis was done for the study area for various results of land cover classification using a KOMPSAT-3A multi-spectral imagery.

  17. Land use/cover classification in the Brazilian Amazon using satellite images. (United States)

    Lu, Dengsheng; Batistella, Mateus; Li, Guiying; Moran, Emilio; Hetrick, Scott; Freitas, Corina da Costa; Dutra, Luciano Vieira; Sant'anna, Sidnei João Siqueira


    Land use/cover classification is one of the most important applications in remote sensing. However, mapping accurate land use/cover spatial distribution is a challenge, particularly in moist tropical regions, due to the complex biophysical environment and limitations of remote sensing data per se. This paper reviews experiments related to land use/cover classification in the Brazilian Amazon for a decade. Through comprehensive analysis of the classification results, it is concluded that spatial information inherent in remote sensing data plays an essential role in improving land use/cover classification. Incorporation of suitable textural images into multispectral bands and use of segmentation-based method are valuable ways to improve land use/cover classification, especially for high spatial resolution images. Data fusion of multi-resolution images within optical sensor data is vital for visual interpretation, but may not improve classification performance. In contrast, integration of optical and radar data did improve classification performance when the proper data fusion method was used. Of the classification algorithms available, the maximum likelihood classifier is still an important method for providing reasonably good accuracy, but nonparametric algorithms, such as classification tree analysis, has the potential to provide better results. However, they often require more time to achieve parametric optimization. Proper use of hierarchical-based methods is fundamental for developing accurate land use/cover classification, mainly from historical remotely sensed data.

  18. Classification of high-resolution multispectral satellite remote sensing images using extended morphological attribute profiles and independent component analysis (United States)

    Wu, Yu; Zheng, Lijuan; Xie, Donghai; Zhong, Ruofei


    In this study, the extended morphological attribute profiles (EAPs) and independent component analysis (ICA) were combined for feature extraction of high-resolution multispectral satellite remote sensing images and the regularized least squares (RLS) approach with the radial basis function (RBF) kernel was further applied for the classification. Based on the major two independent components, the geometrical features were extracted using the EAPs method. In this study, three morphological attributes were calculated and extracted for each independent component, including area, standard deviation, and moment of inertia. The extracted geometrical features classified results using RLS approach and the commonly used LIB-SVM library of support vector machines method. The Worldview-3 and Chinese GF-2 multispectral images were tested, and the results showed that the features extracted by EAPs and ICA can effectively improve the accuracy of the high-resolution multispectral image classification, 2% larger than EAPs and principal component analysis (PCA) method, and 6% larger than APs and original high-resolution multispectral data. Moreover, it is also suggested that both the GURLS and LIB-SVM libraries are well suited for the multispectral remote sensing image classification. The GURLS library is easy to be used with automatic parameter selection but its computation time may be larger than the LIB-SVM library. This study would be helpful for the classification application of high-resolution multispectral satellite remote sensing images.

  19. Object-Based Classification of Grasslands from High Resolution Satellite Image Time Series Using Gaussian Mean Map Kernels

    Directory of Open Access Journals (Sweden)

    Mailys Lopes


    Full Text Available This paper deals with the classification of grasslands using high resolution satellite image time series. Grasslands considered in this work are semi-natural elements in fragmented landscapes, i.e., they are heterogeneous and small elements. The first contribution of this study is to account for grassland heterogeneity while working at the object level by modeling its pixels distributions by a Gaussian distribution. To measure the similarity between two grasslands, a new kernel is proposed as a second contribution: the α -Gaussian mean kernel. It allows one to weight the influence of the covariance matrix when comparing two Gaussian distributions. This kernel is introduced in support vector machines for the supervised classification of grasslands from southwest France. A dense intra-annual multispectral time series of the Formosat-2 satellite is used for the classification of grasslands’ management practices, while an inter-annual NDVI time series of Formosat-2 is used for old and young grasslands’ discrimination. Results are compared to other existing pixel- and object-based approaches in terms of classification accuracy and processing time. The proposed method is shown to be a good compromise between processing speed and classification accuracy. It can adapt to the classification constraints, and it encompasses several similarity measures known in the literature. It is appropriate for the classification of small and heterogeneous objects such as grasslands.

  20. Comparision of Clustering Algorithms usingNeural Network Classifier for Satellite Image Classification


    S.Praveena; Dr. S.P Singh


    This paper presents a hybrid clustering algorithm and feed-forward neural network classifier for land-cover mapping of trees, shade, building and road. It starts with the single step preprocessing procedure to make the image suitable for segmentation. The pre-processed image is segmented using the hybrid genetic-Artificial Bee Colony(ABC) algorithm that is developed by hybridizing the ABC and FCM to obtain the effective segmentation in satellite image and classified using neural n...

  1. Investigating the Potential of Deep Neural Networks for Large-Scale Classification of Very High Resolution Satellite Images (United States)

    Postadjian, T.; Le Bris, A.; Sahbi, H.; Mallet, C.


    Semantic classification is a core remote sensing task as it provides the fundamental input for land-cover map generation. The very recent literature has shown the superior performance of deep convolutional neural networks (DCNN) for many classification tasks including the automatic analysis of Very High Spatial Resolution (VHR) geospatial images. Most of the recent initiatives have focused on very high discrimination capacity combined with accurate object boundary retrieval. Therefore, current architectures are perfectly tailored for urban areas over restricted areas but not designed for large-scale purposes. This paper presents an end-to-end automatic processing chain, based on DCNNs, that aims at performing large-scale classification of VHR satellite images (here SPOT 6/7). Since this work assesses, through various experiments, the potential of DCNNs for country-scale VHR land-cover map generation, a simple yet effective architecture is proposed, efficiently discriminating the main classes of interest (namely buildings, roads, water, crops, vegetated areas) by exploiting existing VHR land-cover maps for training.

  2. Learning-based roof style classification in 2D satellite images (United States)

    Zang, Andi; Zhang, Xi; Chen, Xin; Agam, Gady


    Accurately recognizing building roof style leads to a much more realistic 3D building modeling and rendering. In this paper, we propose a novel system for image based roof style classification using machine learning technique. Our system is capable of accurately recognizing four individual roof styles and a complex roof which is composed of multiple parts. We make several novel contributions in this paper. First, we propose an algorithm that segments a complex roof to parts which enable our system to recognize the entire roof based on recognition of each part. Second, to better characterize a roof image, we design a new feature extracted from a roof edge image. We demonstrate that this feature has much better performance compared to recognition results generated by Histogram of Oriented Gradient (HOG), Scale-invariant Feature Transform (SIFT) and Local Binary Patterns (LBP). Finally, to generate a classifier, we propose a learning scheme that trains the classifier using both synthetic and real roof images. Experiment results show that our classifier performs well on several test collections.

  3. Detection of facilities in satellite imagery using semi-supervized image classification and auxiliary contextual observables (United States)

    Harvey, Neal R.; Ruggiero, C.; Pawley, N. H.; MacDonald, B.; Oyer, A.; Balick, L.; Brumby, S. P.


    Detecting complex targets, such as facilities, in commercially available satellite imagery is a difficult problem that human analysts try to solve by applying world knowledge. Often there are known observables that can be extracted by pixel-level feature detectors that can assist in the facility detection process. Individually, each of these observables is not sufficient for an accurate and reliable detection, but in combination, these auxiliary observables may provide sufficient context for detection by a machine learning algorithm. We describe an approach for automatic detection of facilities that uses an automated feature extraction algorithm to extract auxiliary observables, and a semi-supervised assisted target recognition algorithm to then identify facilities of interest. We illustrate the approach using an example of finding schools in Quickbird image data of Albuquerque, New Mexico. We use Los Alamos National Laboratory's Genie Pro automated feature extraction algorithm to find a set of auxiliary features that should be useful in the search for schools, such as parking lots, large buildings, sports fields and residential areas and then combine these features using Genie Pro's assisted target recognition algorithm to learn a classifier that finds schools in the image data.

  4. Detection of facilities in satellite imagery using semi-supervised image classification and auxiliary contextual observables

    Energy Technology Data Exchange (ETDEWEB)

    Harvey, Neal R [Los Alamos National Laboratory; Ruggiero, Christy E [Los Alamos National Laboratory; Pawley, Norma H [Los Alamos National Laboratory; Brumby, Steven P [Los Alamos National Laboratory; Macdonald, Brian [Los Alamos National Laboratory; Balick, Lee [Los Alamos National Laboratory; Oyer, Alden [Los Alamos National Laboratory


    Detecting complex targets, such as facilities, in commercially available satellite imagery is a difficult problem that human analysts try to solve by applying world knowledge. Often there are known observables that can be extracted by pixel-level feature detectors that can assist in the facility detection process. Individually, each of these observables is not sufficient for an accurate and reliable detection, but in combination, these auxiliary observables may provide sufficient context for detection by a machine learning algorithm. We describe an approach for automatic detection of facilities that uses an automated feature extraction algorithm to extract auxiliary observables, and a semi-supervised assisted target recognition algorithm to then identify facilities of interest. We illustrate the approach using an example of finding schools in Quickbird image data of Albuquerque, New Mexico. We use Los Alamos National Laboratory's Genie Pro automated feature extraction algorithm to find a set of auxiliary features that should be useful in the search for schools, such as parking lots, large buildings, sports fields and residential areas and then combine these features using Genie Pro's assisted target recognition algorithm to learn a classifier that finds schools in the image data.

  5. Benefits of Red-Edge Spectral Band and Texture Features for the Object-based Classification using RapidEye sSatellite Image data (United States)

    Kim, H. O.; Yeom, J. M.


    Space-based remote sensing in agriculture is particularly relevant to issues such as global climate change, food security, and precision agriculture. Recent satellite missions have opened up new perspectives by offering high spatial resolution, various spectral properties, and fast revisit rates to the same regions. Here, we examine the utility of broadband red-edge spectral information in multispectral satellite image data for classifying paddy rice crops in South Korea. Additionally, we examine how object-based spectral features affect the classification of paddy rice growth stages. For the analysis, two seasons of RapidEye satellite image data were used. The results showed that the broadband red-edge information slightly improved the classification accuracy of the crop condition in heterogeneous paddy rice crop environments, particularly when single-season image data were used. This positive effect appeared to be offset by the multi-temporal image data. Additional texture information brought only a minor improvement or a slight decline, although it is well known to be advantageous for object-based classification in general. We conclude that broadband red-edge information derived from conventional multispectral satellite data has the potential to improve space-based crop monitoring. Because the positive or negative effects of texture features for object-based crop classification could barely be interpreted, the relationships between the textual properties and paddy rice crop parameters at the field scale should be further examined in depth.

  6. Research on the classification result and accuracy of building windows in high resolution satellite images: take the typical rural buildings in Guangxi, China, as an example (United States)

    Li, Baishou; Gao, Yujiu


    The information extracted from the high spatial resolution remote sensing images has become one of the important data sources of the GIS large scale spatial database updating. The realization of the building information monitoring using the high resolution remote sensing, building small scale information extracting and its quality analyzing has become an important precondition for the applying of the high-resolution satellite image information, because of the large amount of regional high spatial resolution satellite image data. In this paper, a clustering segmentation classification evaluation method for the high resolution satellite images of the typical rural buildings is proposed based on the traditional KMeans clustering algorithm. The factors of separability and building density were used for describing image classification characteristics of clustering window. The sensitivity of the factors influenced the clustering result was studied from the perspective of the separability between high image itself target and background spectrum. This study showed that the number of the sample contents is the important influencing factor to the clustering accuracy and performance, the pixel ratio of the objects in images and the separation factor can be used to determine the specific impact of cluster-window subsets on the clustering accuracy, and the count of window target pixels (Nw) does not alone affect clustering accuracy. The result can provide effective research reference for the quality assessment of the segmentation and classification of high spatial resolution remote sensing images.

  7. Continental land cover classification using satellite data (United States)

    Townshend, J. R. G.; Tucker, C. J.


    Four different approaches to the classification of land cover for whole continents using multitemporal images of the normalized difference vegetation index derived from the Advanced Very High Resolution Radiometer of the NOAA series of satellites are discussed. The first approach uses only two dates from different seasons and classification dependent upon subdivision of the resultant two-dimensional feature space by an analyst using a track ball. The second approach involves a similar method of partitioning the feature space, but with the two dimensions being the first and second principal components derived from 13 four-week composite images. The third approach uses the maximum likelihood rule to derive the classified map. In the fourth approach, the amount of deviation from characteristic curves is used as a basis for classification.


    Directory of Open Access Journals (Sweden)

    Claudia Arcidiacono


    Full Text Available Actual research challenges in automated recognition of crop shelters regard, among other issues, the accuracy of classification, contour detection and typology identification. In this field the use of high-resolution multispectral images has been found to improve the feature recognition in comparison to RGB images or low resolution multispectral ones. As for classification methodologies, per-pixel and object-oriented ones offer different tools to cope with image recognition and feature extraction. In this study, to improve the classification of cropshelter coverage, the per-pixel method was applied to high-resolution multispectral images, coupled with a texture analysis of high-resolution panchromatic images. In detail, the results of the classification accuracy assessment achieved by the use of native high-resolution panchromatic images and RGB-band images resampled accordingly, were compared with those found in a previous study in which panchromatic images degraded to the RGB-band image resolution were used. The results show that the proposed methodology is suitable to improve crop-shelter classification quality and contour detection of parcels.

  9. A spatial-structural model for classification and change detection of vegetation coverage on multispectral satellite image


    Hung, Trinh; Hoai, Dao


    In analyzing the spatial-structures of various object types represented on multispectral images, we propose a new spatial-structural model for classification and two models for change detection vegetation coverage. The model for evaluation of coastline dynamic change has eliminated the disadvantage of traditional methods. It can be applied to images received from various sensors. Both change detection models used the spatial-structural model for classification purpose. Results of analytical p...

  10. Statistical classification of images


    Giuliodori, María Andrea


    Image classification is a burgeoning field of study. Despite the advances achieved in this camp, there is no general agreement about what is the most effective methods for the classification of digital images. This dissertation contributes to this line of research by developing different statistical methods aim to classifying digital images. In Chapter 1 we introduce basic concepts of image classification and review some results and methodologies proposed previously in the literature. In Chap...

  11. Satellite image analysis using neural networks (United States)

    Sheldon, Roger A.


    The tremendous backlog of unanalyzed satellite data necessitates the development of improved methods for data cataloging and analysis. Ford Aerospace has developed an image analysis system, SIANN (Satellite Image Analysis using Neural Networks) that integrates the technologies necessary to satisfy NASA's science data analysis requirements for the next generation of satellites. SIANN will enable scientists to train a neural network to recognize image data containing scenes of interest and then rapidly search data archives for all such images. The approach combines conventional image processing technology with recent advances in neural networks to provide improved classification capabilities. SIANN allows users to proceed through a four step process of image classification: filtering and enhancement, creation of neural network training data via application of feature extraction algorithms, configuring and training a neural network model, and classification of images by application of the trained neural network. A prototype experimentation testbed was completed and applied to climatological data.

  12. Classification of remotely sensed images

    CSIR Research Space (South Africa)

    Dudeni, N


    Full Text Available images N. Dudeni, P. Debba Introduction to Remote Sensing Introduction to Image Classification Objective of the study Classification algorithms by group Unsupervised algorithms Supervised classification algorithms Spatial... of remotely sensed images N. Dudeni, P. Debba Introduction to Remote Sensing Introduction to Image Classification Objective of the study Classification algorithms by group Unsupervised algorithms Supervised classification algorithms...

  13. Cellular image classification

    CERN Document Server

    Xu, Xiang; Lin, Feng


    This book introduces new techniques for cellular image feature extraction, pattern recognition and classification. The authors use the antinuclear antibodies (ANAs) in patient serum as the subjects and the Indirect Immunofluorescence (IIF) technique as the imaging protocol to illustrate the applications of the described methods. Throughout the book, the authors provide evaluations for the proposed methods on two publicly available human epithelial (HEp-2) cell datasets: ICPR2012 dataset from the ICPR'12 HEp-2 cell classification contest and ICIP2013 training dataset from the ICIP'13 Competition on cells classification by fluorescent image analysis. First, the reading of imaging results is significantly influenced by one’s qualification and reading systems, causing high intra- and inter-laboratory variance. The authors present a low-order LP21 fiber mode for optical single cell manipulation and imaging staining patterns of HEp-2 cells. A focused four-lobed mode distribution is stable and effective in optical...

  14. Classification in Medical Imaging

    DEFF Research Database (Denmark)

    Chen, Chen

    detection in a cardiovascular disease study. The third focus is to deepen the understanding of classification mechanism by visualizing the knowledge learned by a classifier. More specifically, to build the most typical patterns recognized by the Fisher's linear discriminant rule with applications......Classification is extensively used in the context of medical image analysis for the purpose of diagnosis or prognosis. In order to classify image content correctly, one needs to extract efficient features with discriminative properties and build classifiers based on these features. In addition......, a good metric is required to measure distance or similarity between feature points so that the classification becomes feasible. Furthermore, in order to build a successful classifier, one needs to deeply understand how classifiers work. This thesis focuses on these three aspects of classification...

  15. Classification Of Cluster Area Forsatellite Image

    Directory of Open Access Journals (Sweden)

    Thwe Zin Phyo


    Full Text Available Abstract This paper describes area classification for Landsat7 satellite image. The main purpose of this system is to classify the area of each cluster contained in a satellite image. To classify this image firstly need to clusterthe satellite image into different land cover types. Clustering is an unsupervised learning method that aimsto classify an image into homogeneous regions. This system is implemented based on color features with K-means clustering unsupervised algorithm. This method does not need to train image before clustering.The clusters of satellite image are grouped into a set of three clusters for Landsat7 satellite image. For this work the combined band 432 from Landsat7 satellite is used as an input. Satellite imageMandalay area in 2001 is chosen to test the segmentation method. After clustering a specific range for three clustered images must be defined in order to obtain greenland water and urbanbalance.This system is implemented by using MATLAB programming language.

  16. Towards an Automatic Framework for Urban Settlement Mapping from Satellite Images: Applications of Geo-referenced Social Media and One Class Classification (United States)

    Miao, Zelang


    Currently, urban dwellers comprise more than half of the world's population and this percentage is still dramatically increasing. The explosive urban growth over the next two decades poses long-term profound impact on people as well as the environment. Accurate and up-to-date delineation of urban settlements plays a fundamental role in defining planning strategies and in supporting sustainable development of urban settlements. In order to provide adequate data about urban extents and land covers, classifying satellite data has become a common practice, usually with accurate enough results. Indeed, a number of supervised learning methods have proven effective in urban area classification, but they usually depend on a large amount of training samples, whose collection is a time and labor expensive task. This issue becomes particularly serious when classifying large areas at the regional/global level. As an alternative to manual ground truth collection, in this work we use geo-referenced social media data. Cities and densely populated areas are an extremely fertile land for the production of individual geo-referenced data (such as GPS and social network data). Training samples derived from geo-referenced social media have several advantages: they are easy to collect, usually they are freely exploitable; and, finally, data from social media are spatially available in many locations, and with no doubt in most urban areas around the world. Despite these advantages, the selection of training samples from social media meets two challenges: 1) there are many duplicated points; 2) method is required to automatically label them as "urban/non-urban". The objective of this research is to validate automatic sample selection from geo-referenced social media and its applicability in one class classification for urban extent mapping from satellite images. The findings in this study shed new light on social media applications in the field of remote sensing.

  17. An AdaBoost Based Approach to Automatic Classification and Detection of Buildings Footprints, Vegetation Areas and Roads from Satellite Images (United States)

    Gonulalan, Cansu

    In recent years, there has been an increasing demand for applications to monitor the targets related to land-use, using remote sensing images. Advances in remote sensing satellites give rise to the research in this area. Many applications ranging from urban growth planning to homeland security have already used the algorithms for automated object recognition from remote sensing imagery. However, they have still problems such as low accuracy on detection of targets, specific algorithms for a specific area etc. In this thesis, we focus on an automatic approach to classify and detect building foot-prints, road networks and vegetation areas. The automatic interpretation of visual data is a comprehensive task in computer vision field. The machine learning approaches improve the capability of classification in an intelligent way. We propose a method, which has high accuracy on detection and classification. The multi class classification is developed for detecting multiple objects. We present an AdaBoost-based approach along with the supervised learning algorithm. The combi- nation of AdaBoost with "Attentional Cascade" is adopted from Viola and Jones [1]. This combination decreases the computation time and gives opportunity to real time applications. For the feature extraction step, our contribution is to combine Haar-like features that include corner, rectangle and Gabor. Among all features, AdaBoost selects only critical features and generates in extremely efficient cascade structured classifier. Finally, we present and evaluate our experimental results. The overall system is tested and high performance of detection is achieved. The precision rate of the final multi-class classifier is over 98%.

  18. Geostationary Satellite (GOES) Images (United States)

    National Oceanic and Atmospheric Administration, Department of Commerce — Visible and Infrared satellite imagery taken from radiometer instruments on SMS (ATS) and GOES satellites in geostationary orbit. These satellites produced...

  19. Image classification using eigenpaxels (United States)

    McGuire, Peter Frederick

    The intelligent control of robotic is a major limiting factor in the utilization of current robotic technology. Although the technology to accurately position robotic manipulators is well developed, practical applications are often limited by the controller's ability to interact with a complex environment. Central to this plight is the integration of sensory signals, such as vision, into the control structure. Recently, a number of promising approaches to visual information processing have been developed using artificial neural networks (ANNs). These approaches, however, are often tailored to particular applications and are therefore disparate and limited in scope. In contrast, biological neural networks perform a wide range of visual tasks yet this behavior arises from a single integrated neural structure. The work presented in this thesis details a biologically inspired image processing algorithm and its application to an image classification problem. Based on the organization of cells in the primary visual cortex of primates, this algorithm utilizes key neural mechanisms to produce efficient representations of images. Dubbed the "eigenpaxel" algorithm, excellent results are obtained despite the relative simplicity of the method. In addition, the relationship between the algorithm and biological vision may help to shed light on the processing occurring within the brain and the basis of the organization found therein.

  20. Classification of Clouds in Satellite Imagery Using Adaptive Fuzzy Sparse Representation. (United States)

    Jin, Wei; Gong, Fei; Zeng, Xingbin; Fu, Randi


    Automatic cloud detection and classification using satellite cloud imagery have various meteorological applications such as weather forecasting and climate monitoring. Cloud pattern analysis is one of the research hotspots recently. Since satellites sense the clouds remotely from space, and different cloud types often overlap and convert into each other, there must be some fuzziness and uncertainty in satellite cloud imagery. Satellite observation is susceptible to noises, while traditional cloud classification methods are sensitive to noises and outliers; it is hard for traditional cloud classification methods to achieve reliable results. To deal with these problems, a satellite cloud classification method using adaptive fuzzy sparse representation-based classification (AFSRC) is proposed. Firstly, by defining adaptive parameters related to attenuation rate and critical membership, an improved fuzzy membership is introduced to accommodate the fuzziness and uncertainty of satellite cloud imagery; secondly, by effective combination of the improved fuzzy membership function and sparse representation-based classification (SRC), atoms in training dictionary are optimized; finally, an adaptive fuzzy sparse representation classifier for cloud classification is proposed. Experiment results on FY-2G satellite cloud image show that, the proposed method not only improves the accuracy of cloud classification, but also has strong stability and adaptability with high computational efficiency.

  1. Automatic Hierarchical Color Image Classification

    Directory of Open Access Journals (Sweden)

    Jing Huang


    Full Text Available Organizing images into semantic categories can be extremely useful for content-based image retrieval and image annotation. Grouping images into semantic classes is a difficult problem, however. Image classification attempts to solve this hard problem by using low-level image features. In this paper, we propose a method for hierarchical classification of images via supervised learning. This scheme relies on using a good low-level feature and subsequently performing feature-space reconfiguration using singular value decomposition to reduce noise and dimensionality. We use the training data to obtain a hierarchical classification tree that can be used to categorize new images. Our experimental results suggest that this scheme not only performs better than standard nearest-neighbor techniques, but also has both storage and computational advantages.

  2. Evaluating the Potential of PROBA-V Satellite Image Time Series for Improving LC Classification in Semi-Arid African Landscapes

    Directory of Open Access Journals (Sweden)

    Johannes Eberenz


    Full Text Available Satellite based land cover classification for Africa’s semi-arid ecosystems is hampered commonly by heterogeneous landscapes with mixed vegetation and small scale land use. Higher spatial resolution remote sensing time series data can improve classification results under these difficult conditions. While most large scale land cover mapping attempts rely on moderate resolution data, PROBA-V provides five-daily time series at 100 m spatial resolution. This improves spatial detail and resilience against high cloud cover, but increases the data load. Cloud-based processing platforms can leverage large scale land cover monitoring based on such finer time series. We demonstrate this with PROBA-V 100 m time series data from 2014–2015, using temporal metrics and cloud filtering in combination with in-situ training data and machine learning, implemented on the ESA (European Space Agency Cloud Toolbox infrastructure. We apply our approach to two use cases for a large study area over West Africa: land- and forest cover classification. Our land cover classification reaches a 7% to 21% higher overall accuracy when compared to four global land cover maps (i.e., Globcover-2009, Cover-CCI-2010, MODIS-2010, and Globeland30. Our forest cover classification shows 89% correspondence with the Tropical Ecosystem Environment Observation System (TREES-3 forest cover data which is based on spatially finer Landsat data. This paper illustrates a proof of concept for cloud-based “big-data” driven land cover monitoring. Furthermore, we show that a wide range of temporal metrics can be extracted from detailed PROBA-V 100 m time series data to continuously optimize land cover monitoring.

  3. Snake classification from images


    James, Alex.


    Incorrect snake identification from the observable visual traits is a major reason of death resulting from snake bites. So far no automatic classification method has been proposed to distinguish snakes by deciphering the taxonomy features of snake for the two major species of snakes i.e. Elapidae and Viperidae. We present a parallel processed inter-feature product similarity fusion based automatic classification of Spectacled Cobra, Russel's Viper, King Cobra, Common Krait, Saw Scaled Viper, ...

  4. Decision tree approach for classification of remotely sensed satellite ...

    Indian Academy of Sciences (India)

    DTC) algorithm for classification of remotely sensed satellite data (Landsat TM) using open source support. The decision tree is constructed by recursively partitioning the spectral distribution of the training dataset using WEKA, open source ...

  5. Classification in Medical Imaging

    DEFF Research Database (Denmark)

    Chen, Chen

    to segment breast tissue and pectoral muscle area from the background in mammogram. The second focus is the choices of metric and its influence to the feasibility of a classifier, especially on k-nearest neighbors (k-NN) algorithm, with medical applications on breast cancer prediction and calcification...... and explores these challenging areas. The first focus of the thesis is to properly combine different local feature experts and prior information to design an effective classifier. The preliminary classification results, provided by the experts, are fused in order to develop an automatic segmentation method...

  6. Classification of mangroves vegetation species using texture analysis on Rapideye satellite imagery (United States)

    Roslani, M. A.; Mustapha, M. A.; Lihan, T.; Juliana, W. A. Wan


    Mangroves are unique ecosystem structures that are typically made up of salt tolerant species of vegetation that can be found in tropical and subtropical climate country. Mangrove ecosystem plays important role and also is known as highly productive ecosystem with high diversity of flora and fauna. However, these ecosystems have been declining over time due to the various kinds of direct and indirect pressures. Thus, there is an increasing need to monitor and assess this ecosystem for better conservation and management efforts. The multispectral RapidEye satellite image was used to identify the mangrove vegetation species within the Matang Mangrove Forest Reserve in Perak, Malaysia using texture analysis. Classification was implemented using the maximum likelihood classifier (MLC) method. Total of eleven main mangrove species were found in the satellite image of the study site which includes Rhizophora mucronata, Rhizophora apiculata, Bruguiera parviflora, Bruguiera cylindrica, Bruguiera gymnorrhiza, Avicennia alba, Avicennia officinalis, Sonneratia alba, Sonneratia caseolaris, Sonneratia ovata and Xylocarpus granatum. The classification results showed that the textured image produced high overall classification assessment recorded at 84% and kappa statistic of 0.8016. Meanwhile, the non-textured image produces 80% of overall accuracy and kappa statistic of 0.7061. The classification result indicated the capability of high resolution satellite image to classify the mangrove species and inclusion of texture information in the classification increased the classification accuracy.

  7. Continental land cover classification using meteorological satellite data (United States)

    Tucker, C. J.; Townshend, J. R. G.; Goff, T. E.


    The use of the National Oceanic and Atmospheric Administration's advanced very high resolution radiometer satellite data for classifying land cover and monitoring of vegetation dynamics over an extremely large area is demonstrated for the continent of Africa. Data from 17 imaging periods of 21 consecutive days each were composited by a technique sensitive to the in situ green-leaf biomass to provide cloud-free imagery for the whole continent. Virtually cloud-free images were obtainable even for equatorial areas. Seasonal variation in the density and extent of green leaf vegetation corresponded to the patterns of rainfall associated with the inter-tropical convergence zone. Regional variations, such as the 1982 drought in east Africa, were also observed. Integration of the weekly satellite data with respect to time produced a remotely sensed assessment of biological activity based upon density and duration of green-leaf biomass. Two of the 21-day composited data sets were used to produce a general land cover classification. The resultant land cover distributions correspond well to those of existing maps.

  8. Deep Learning-Based Large-Scale Automatic Satellite Crosswalk Classification (United States)

    Berriel, Rodrigo F.; Lopes, Andre Teixeira; de Souza, Alberto F.; Oliveira-Santos, Thiago


    High-resolution satellite imagery have been increasingly used on remote sensing classification problems. One of the main factors is the availability of this kind of data. Even though, very little effort has been placed on the zebra crossing classification problem. In this letter, crowdsourcing systems are exploited in order to enable the automatic acquisition and annotation of a large-scale satellite imagery database for crosswalks related tasks. Then, this dataset is used to train deep-learning-based models in order to accurately classify satellite images that contains or not zebra crossings. A novel dataset with more than 240,000 images from 3 continents, 9 countries and more than 20 cities was used in the experiments. Experimental results showed that freely available crowdsourcing data can be used to accurately (97.11%) train robust models to perform crosswalk classification on a global scale.

  9. Enhancement classification of galaxy images (United States)

    Jenkinson, John

    With the advent of astronomical imaging technology developments, and the increased capacity of digital storage, the production of photographic atlases of the night sky have begun to generate volumes of data which need to be processed autonomously. As part of the Tonantzintla Digital Sky Survey construction, the present work involves software development for the digital image processing of astronomical images, in particular operations that preface feature extraction and classification. Recognition of galaxies in these images is the primary objective of the present work. Many galaxy images have poor resolution or contain faint galaxy features, resulting in the misclassification of galaxies. An enhancement of these images by the method of the Heap transform is proposed, and experimental results are provided which demonstrate the image enhancement to improve the presence of faint galaxy features thereby improving classification accuracy. The feature extraction was performed using morphological features that have been widely used in previous automated galaxy investigations. Principal component analysis was applied to the original and enhanced data sets for a performance comparison between the original and reduced features spaces. Classification was performed by the Support Vector Machine learning algorithm.

  10. Algorithms of Expert Classification Applied in Quickbird Satellite Images for Land Use Mapping Algoritmos de Clasificación Experta Aplicados en Imágenes Satelitales Quickbird para el Mapeo de la Cobertura de la Tierra

    National Research Council Canada - National Science Library

    Alberto Jesús Perea; José Emilio Meroño; María Jesús Aguilera


    The objective of this paper was the development of a methodology for the classification of digital aerial images, which, with the aid of object-based classification and the Normalized Difference Vegetation Index (NDVI...

  11. Classification of Dust Days by Satellite Remotely Sensed Aerosol Products (United States)

    Sorek-Hammer, M.; Cohen, A.; Levy, Robert C.; Ziv, B.; Broday, D. M.


    Considerable progress in satellite remote sensing (SRS) of dust particles has been seen in the last decade. From an environmental health perspective, such an event detection, after linking it to ground particulate matter (PM) concentrations, can proxy acute exposure to respirable particles of certain properties (i.e. size, composition, and toxicity). Being affected considerably by atmospheric dust, previous studies in the Eastern Mediterranean, and in Israel in particular, have focused on mechanistic and synoptic prediction, classification, and characterization of dust events. In particular, a scheme for identifying dust days (DD) in Israel based on ground PM10 (particulate matter of size smaller than 10 nm) measurements has been suggested, which has been validated by compositional analysis. This scheme requires information regarding ground PM10 levels, which is naturally limited in places with sparse ground-monitoring coverage. In such cases, SRS may be an efficient and cost-effective alternative to ground measurements. This work demonstrates a new model for identifying DD and non-DD (NDD) over Israel based on an integration of aerosol products from different satellite platforms (Moderate Resolution Imaging Spectroradiometer (MODIS) and Ozone Monitoring Instrument (OMI)). Analysis of ground-monitoring data from 2007 to 2008 in southern Israel revealed 67 DD, with more than 88 percent occurring during winter and spring. A Classification and Regression Tree (CART) model that was applied to a database containing ground monitoring (the dependent variable) and SRS aerosol product (the independent variables) records revealed an optimal set of binary variables for the identification of DD. These variables are combinations of the following primary variables: the calendar month, ground-level relative humidity (RH), the aerosol optical depth (AOD) from MODIS, and the aerosol absorbing index (AAI) from OMI. A logistic regression that uses these variables, coded as binary

  12. Sugarcane Land Classification with Satellite Imagery using Logistic Regression Model (United States)

    Henry, F.; Herwindiati, D. E.; Mulyono, S.; Hendryli, J.


    This paper discusses the classification of sugarcane plantation area from Landsat-8 satellite imagery. The classification process uses binary logistic regression method with time series data of normalized difference vegetation index as input. The process is divided into two steps: training and classification. The purpose of training step is to identify the best parameter of the regression model using gradient descent algorithm. The best fit of the model can be utilized to classify sugarcane and non-sugarcane area. The experiment shows high accuracy and successfully maps the sugarcane plantation area which obtained best result of Cohen’s Kappa value 0.7833 (strong) with 89.167% accuracy.

  13. Egypt satellite images for land surface characterization

    DEFF Research Database (Denmark)

    Hasager, Charlotte Bay

    Satellite images provide information on the land surface properties. From optical remote sensing images in the blue, green, red and near-infrared part of the electromagnetic spectrum it is possible to identify a large number of surface features. The report briefly describes different satellite im...... images used for mapping the vegetation cover types and other land cover types in Egypt. The mapping ranges from 1 km resolution to 30 m resolution. The aim is to provide satellite image mapping with land surface characteristics relevant for roughness mapping.......Satellite images provide information on the land surface properties. From optical remote sensing images in the blue, green, red and near-infrared part of the electromagnetic spectrum it is possible to identify a large number of surface features. The report briefly describes different satellite...

  14. Feature detection in satellite images using neural network technology (United States)

    Augusteijn, Marijke F.; Dimalanta, Arturo S.


    A feasibility study of automated classification of satellite images is described. Satellite images were characterized by the textures they contain. In particular, the detection of cloud textures was investigated. The method of second-order gray level statistics, using co-occurrence matrices, was applied to extract feature vectors from image segments. Neural network technology was employed to classify these feature vectors. The cascade-correlation architecture was successfully used as a classifier. The use of a Kohonen network was also investigated but this architecture could not reliably classify the feature vectors due to the complicated structure of the classification problem. The best results were obtained when data from different spectral bands were fused.

  15. Forest Cover Classification by Optimal Segmentation of High Resolution Satellite Imagery

    Directory of Open Access Journals (Sweden)

    Hyun-Kook Cho


    Full Text Available This study investigated whether high-resolution satellite imagery is suitable for preparing a detailed digital forest cover map that discriminates forest cover at the tree species level. First, we tried to find an optimal process for segmenting the high-resolution images using a region-growing method with the scale, color and shape factors in Definiens® Professional 5.0. The image was classified by a traditional, pixel-based, maximum likelihood classification approach using the spectral information of the pixels. The pixels in each segment were reclassified using a segment-based classification (SBC with a majority rule. Segmentation with strongly weighted color was less sensitive to the scale parameter and led to optimal forest cover segmentation and classification. The pixel-based classification (PBC suffered from the “salt-and-pepper effect” and performed poorly in the classification of forest cover types, whereas the SBC helped to attenuate the effect and notably improved the classification accuracy. As a whole, SBC proved to be more suitable for classifying and delineating forest cover using high-resolution satellite images.

  16. Validation assessment of shoreline extraction on medium resolution satellite image (United States)

    Manaf, Syaifulnizam Abd; Mustapha, Norwati; Sulaiman, Md Nasir; Husin, Nor Azura; Shafri, Helmi Zulhaidi Mohd


    Monitoring coastal zones helps provide information about the conditions of the coastal zones, such as erosion or accretion. Moreover, monitoring the shorelines can help measure the severity of such conditions. Such measurement can be performed accurately by using Earth observation satellite images rather than by using traditional ground survey. To date, shorelines can be extracted from satellite images with a high degree of accuracy by using satellite image classification techniques based on machine learning to identify the land and water classes of the shorelines. In this study, the researchers validated the results of extracted shorelines of 11 classifiers using a reference shoreline provided by the local authority. Specifically, the validation assessment was performed to examine the difference between the extracted shorelines and the reference shorelines. The research findings showed that the SVM Linear was the most effective image classification technique, as evidenced from the lowest mean distance between the extracted shoreline and the reference shoreline. Furthermore, the findings showed that the accuracy of the extracted shoreline was not directly proportional to the accuracy of the image classification.

  17. Discriminative models for robust image classification


    Srinivas, Umamahesh


    A variety of real-world tasks involve the classification of images into pre-determined categories. Designing image classification algorithms that exhibit robustness to acquisition noise and image distortions, particularly when the available training data are insufficient to learn accurate models, is a significant challenge. This dissertation explores the development of discriminative models for robust image classification that exploit underlying signal structure, via probabilistic graphical m...

  18. Machine Classification of Transient Images (United States)

    Buisson, Lise Du; Sivanandam, Navin; Bassett, Bruce A.; Smith, Mathew


    Using transient imaging data from the 2nd and 3rd years of the SDSS supernova survey, we apply various machine learning techniques to the problem of classifying transients (e.g. SNe) from artefacts, one of the first steps in any transient detection pipeline, and one that is often still carried out by human scanners. Using features mostly obtained from PCA, we show that we can match human levels of classification success, and find that a K-nearest neighbours algorithm and SkyNet perform best, while the Naive Bayes, SVM and minimum error classifier have performances varying from slightly to significantly worse.

  19. Decision tree approach for classification of remotely sensed satellite data using open source support (United States)

    Sharma, Richa; Ghosh, Aniruddha; Joshi, P. K.


    In this study, an attempt has been made to develop a decision tree classification (DTC) algorithm for classification of remotely sensed satellite data (Landsat TM) using open source support. The decision tree is constructed by recursively partitioning the spectral distribution of the training dataset using WEKA, open source data mining software. The classified image is compared with the image classified using classical ISODATA clustering and Maximum Likelihood Classifier (MLC) algorithms. Classification result based on DTC method provided better visual depiction than results produced by ISODATA clustering or by MLC algorithms. The overall accuracy was found to be 90% (kappa = 0.88) using the DTC, 76.67% (kappa = 0.72) using the Maximum Likelihood and 57.5% (kappa = 0.49) using ISODATA clustering method. Based on the overall accuracy and kappa statistics, DTC was found to be more preferred classification approach than others.

  20. Quality Assessment of Pre-Classification Maps Generated from Spaceborne/Airborne Multi-Spectral Images by the Satellite Image Automatic Mapper™ and Atmospheric/Topographic Correction™-Spectral Classification Software Products: Part 2 — Experimental Results

    Directory of Open Access Journals (Sweden)

    Andrea Baraldi


    Full Text Available This paper complies with the Quality Assurance Framework for Earth Observation (QA4EO international guidelines to provide a metrological/statistically-based quality assessment of the Spectral Classification of surface reflectance signatures (SPECL secondary product, implemented within the popular Atmospheric/Topographic Correction (ATCOR™ commercial software suite, and of the Satellite Image Automatic Mapper™ (SIAM™ software product, proposed to the remote sensing (RS community in recent years. The ATCOR™-SPECL and SIAM™ physical model-based expert systems are considered of potential interest to a wide RS audience: in operating mode, they require neither user-defined parameters nor training data samples to map, in near real-time, a spaceborne/airborne multi-spectral (MS image into a discrete and finite set of (pre-attentional first-stage spectral-based semi-concepts (e.g., “vegetation”, whose informative content is always equal or inferior to that of target (attentional second-stage land cover (LC concepts (e.g., “deciduous forest”. For the sake of simplicity, this paper is split into two: Part 1—Theory and Part 2—Experimental results. The Part 1 provides the present Part 2 with an interdisciplinary terminology and a theoretical background. To comply with the principle of statistics and the QA4EO guidelines discussed in the Part 1, the present Part 2 applies an original adaptation of a novel probability sampling protocol for thematic map quality assessment to the ATCOR™-SPECL and SIAM™ pre-classification maps, generated from three spaceborne/airborne MS test images. Collected metrological/ statistically-based quality indicators (QIs comprise: (i an original Categorical Variable Pair Similarity Index (CVPSI, capable of estimating the degree of match between a test pre-classification map’s legend and a reference LC map’s legend that do not coincide and must be harmonized (reconciled; (ii pixel-based Thematic (symbolic


    Directory of Open Access Journals (Sweden)

    Z. Li


    Full Text Available The data from remote sensing images are widely used for characterizing land use and land cover at present. With the increasing availability of very high resolution (VHR remote sensing images, the remote sensing image classification becomes more and more important for information extraction. The VHR remote sensing images are rich in details, but high within-class variance as well as low between-class variance make the classification of ground cover a difficult task. What’s more, some related studies show that the quality of VHR remote sensing images also has a great influence on the ability of the automatic image classification. Therefore, the research that how to select the appropriate VHR remote sensing images to meet the application of classification is of great significance. In this context, the factors of VHR remote sensing image classification ability are discussed and some indices are selected for describing the image quality and the image classification ability objectively. Then, we explore the relationship of the indices of image quality and image classification ability under a specific classification framework. The results of the experiments show that these image quality indices are not effective for indicating the image classification ability directly. However, according to the image quality metrics, we can still propose some suggestion for the application of classification.

  2. Remote sensing image classification by mean shift and colour quantization (United States)

    Taud, Hind; Couturier, Stéphane; Carrillo-Rivera, José Joel


    Remote sensing imagery involves large amounts of data acquired by several kinds of airborne, sensors, wavelengths spatial resolutions, and temporal frequencies. To extract the thematic information from this data, many algorithms and techniques for segmentation and classification have been proposed. The representation of the different multispectral bands as true or false color imaging has been widely employed for visual interpretation and classification. On the other hand, the color quantization, which is a well-known method for data compression, has been utilized for color image segmentation and classification in computer vision application. The number of colors in the original image is reduced by minimizing the distortion between the quantified and the original image with the aim of conserving the pattern representation. Considering the density estimation in the color or feature space, similar samples are grouped together to identify patterns by any clustering techniques. Mean shift algorithm has been successfully applied to different applications as the basis for nonparametric unsupervised clustering techniques. Based on an iterative manner, mean shift detects modes in a probability density function. In this article, the contribution consists in providing an unsupervised color quantization method for image classification based on mean shift. To avoid its high computational cost, the integral image is used. The method is evaluated on Landsat satellite imagery as a case study to underline forest mapping. A comparison between the proposed method and the simple mean shift is carried out. The results prove that the proposed method is useful in multispectral remote sensing image classification study.

  3. Hierarchical image classification in the bioscience literature. (United States)

    Kim, Daehyun; Yu, Hong


    Our previous work has shown that images appearing in bioscience articles can be classified into five types: Gel-Image, Image-of-Thing, Graph, Model, and Mix. For this paper, we explored and analyzed features strongly associated with each image type and developed a hierarchical image classification approach for classifying an image into one of the five types. First, we applied texture features to separate images into two groups: 1) a texture group comprising Gel Image, Image-of-Thing, and Mix, and 2) a non-texture group comprising Graph and Model. We then applied entropy, skewness, and uniformity for the first group, and edge difference, uniformity, and smoothness for the second group to classify images into specific types. Our results show that hierarchical image classification accurately divided images into the two groups during the initial classification and that the overall accuracy of the image classification was higher than that of our previous approach. In particular, the recall of hierarchical image classification was greatly improved due to the high accuracy of the initial classification.

  4. Accuracy assessment between different image classification ...

    African Journals Online (AJOL)

    What image classification does is to assign pixel to a particular land cover and land use type that has the most similar spectral signature. However, there are possibilities that different methods or algorithms of image classification of the same data set could produce appreciable variant results in the sizes, shapes and areas of ...

  5. Assessment of Satellite Images for Soil Salinity Studies

    Directory of Open Access Journals (Sweden)

    S.H. Sanaeinejad


    Full Text Available Soil salinity is one of the main environmental problems affecting extensive area in the world. There are some problems with traditional data collection methods for soil studies. Using the new methods and techniques such as remote sensing could overcome most of these problems. However using these data in areas with uncommon usages needed some researches to find the best calibration between the data and real situations in soil. This research was carried out using Landsat satellite images in Neyshabour area, North East of Iran. In order to prepare suitable learning samples for the image processing in this study, 300 locations were randomly selected in the area, among which 273 locations were finally selected as suitable surface soil samples. All samples were moved to laboratory and their electrical conductivity was measured. Six reflective bands of ETM+ satellite images taken from the study area in 2002 were used for the image processing analysis. Classification of different soil salinities was carried out using common algorithms of image classification based on the best composition bands and using statistical methods between soil salinity variables and digital numbers of the images to represent a suitable method. the research results showed that the reflective bands 7, 3, 4 and 1 are the best band composition for preparing the color composite images and for the classification of the salinity in this area. The highest coefficient of determination was R2=0.311 and R2=0.44 for saline and non-saline soil respectively using band 2 and 3 of the images at 5% significant level. Based on the results, it can be concluded that the potential of ETM+ images for delineation and identification of different soil salinity are limited.

  6. African land-cover classification using satellite data (United States)

    Tucker, C. J.; Goff, T. E.; Townshend, J. R. G.


    Data from the advanced very high resolution radiometer sensor on the National Oceanic and Atmospheric Administration's operational series of meteorological satellites were used to classify land cover and monitor vegetation dynamics for Africa over a 19-month period. There was a correspondence between seasonal variations in the density and extent of green leaf vegetation and the patterns of rainfall associated with the movement of the Intertropical Convergence Zone. Regional variations, such as the 1983 drought in the Sahel of western Africa, were observed. Integration of the weekly satellite data with respect to time for a 12-month period produced a remotely sensed estimate of primary production based upon the density and duration of green leaf biomass. Eight of the 21-day composited data sets covering an 11-month period were used to produce a general land-cover classification that corresponded well with those of existing maps.

  7. Improving Accuracy of Image Classification Using GIS (United States)

    Gupta, R. K.; Prasad, T. S.; Bala Manikavelu, P. M.; Vijayan, D.

    The Remote Sensing signal which reaches sensor on-board the satellite is the complex aggregation of signals (in agriculture field for example) from soil (with all its variations such as colour, texture, particle size, clay content, organic and nutrition content, inorganic content, water content etc.), plant (height, architecture, leaf area index, mean canopy inclination etc.), canopy closure status and atmospheric effects, and from this we want to find say, characteristics of vegetation. If sensor on- board the satellite makes measurements in n-bands (n of n*1 dimension) and number of classes in an image are c (f of c*1 dimension), then considering linear mixture modeling the pixel classification problem could be written as n = m* f +, where m is the transformation matrix of (n*c) dimension and therepresents the error vector (noise). The problem is to estimate f by inverting the above equation and the possible solutions for such problem are many. Thus, getting back individual classes from satellite data is an ill-posed inverse problem for which unique solution is not feasible and this puts limit to the obtainable classification accuracy. Maximum Likelihood (ML) is the constraint mostly practiced in solving such a situation which suffers from the handicaps of assumed Gaussian distribution and random nature of pixels (in-fact there is high auto-correlation among the pixels of a specific class and further high auto-correlation among the pixels in sub- classes where the homogeneity would be high among pixels). Due to this, achieving of very high accuracy in the classification of remote sensing images is not a straight proposition. With the availability of the GIS for the area under study (i) a priori probability for different classes could be assigned to ML classifier in more realistic terms and (ii) the purity of training sets for different thematic classes could be better ascertained. To what extent this could improve the accuracy of classification in ML classifier

  8. Shallow water bathymetry correction using sea bottom classification with multispectral satellite imagery (United States)

    Kazama, Yoriko; Yamamoto, Tomonori


    Bathymetry at shallow water especially shallower than 15m is an important area for environmental monitoring and national defense. Because the depth of shallow water is changeable by the sediment deposition and the ocean waves, the periodic monitoring at shoe area is needed. Utilization of satellite images are well matched for widely and repeatedly monitoring at sea area. Sea bottom terrain model using by remote sensing data have been developed and these methods based on the radiative transfer model of the sun irradiance which is affected by the atmosphere, water, and sea bottom. We adopted that general method of the sea depth extraction to the satellite imagery, WorldView-2; which has very fine spatial resolution (50cm/pix) and eight bands at visible to near-infrared wavelengths. From high-spatial resolution satellite images, there is possibility to know the coral reefs and the rock area's detail terrain model which offers important information for the amphibious landing. In addition, the WorldView-2 satellite sensor has the band at near the ultraviolet wavelength that is transmitted through the water. On the other hand, the previous study showed that the estimation error by the satellite imagery was related to the sea bottom materials such as sand, coral reef, sea alga, and rocks. Therefore, in this study, we focused on sea bottom materials, and tried to improve the depth estimation accuracy. First, we classified the sea bottom materials by the SVM method, which used the depth data acquired by multi-beam sonar as supervised data. Then correction values in the depth estimation equation were calculated applying the classification results. As a result, the classification accuracy of sea bottom materials was 93%, and the depth estimation error using the correction by the classification result was within 1.2m.

  9. Classification images and bubbles images in the generalized linear model. (United States)

    Murray, Richard F


    Classification images and bubbles images are psychophysical tools that use stimulus noise to investigate what features people use to make perceptual decisions. Previous work has shown that classification images can be estimated using the generalized linear model (GLM), and here I show that this is true for bubbles images as well. Expressing the two approaches in terms of a single statistical model clarifies their relationship to one another, makes it possible to measure classification images and bubbles images simultaneously, and allows improvements developed for one method to be used with the other.

  10. Evaluation of Multiple Kernel Learning Algorithms for Crop Mapping Using Satellite Image Time-Series Data (United States)

    Niazmardi, S.; Safari, A.; Homayouni, S.


    Crop mapping through classification of Satellite Image Time-Series (SITS) data can provide very valuable information for several agricultural applications, such as crop monitoring, yield estimation, and crop inventory. However, the SITS data classification is not straightforward. Because different images of a SITS data have different levels of information regarding the classification problems. Moreover, the SITS data is a four-dimensional data that cannot be classified using the conventional classification algorithms. To address these issues in this paper, we presented a classification strategy based on Multiple Kernel Learning (MKL) algorithms for SITS data classification. In this strategy, initially different kernels are constructed from different images of the SITS data and then they are combined into a composite kernel using the MKL algorithms. The composite kernel, once constructed, can be used for the classification of the data using the kernel-based classification algorithms. We compared the computational time and the classification performances of the proposed classification strategy using different MKL algorithms for the purpose of crop mapping. The considered MKL algorithms are: MKL-Sum, SimpleMKL, LPMKL and Group-Lasso MKL algorithms. The experimental tests of the proposed strategy on two SITS data sets, acquired by SPOT satellite sensors, showed that this strategy was able to provide better performances when compared to the standard classification algorithm. The results also showed that the optimization method of the used MKL algorithms affects both the computational time and classification accuracy of this strategy.

  11. Segmentation Based Fuzzy Classification of High Resolution Images (United States)

    Rao, Mukund; Rao, Suryaprakash; Masser, Ian; Kasturirangan, K.

    Information extraction from satellite images is the process of delineation of entities in the image which pertain to some feature on the earth and to which on associating an attribute, a classification of the image is obtained. Classification is a common technique to extract information from remote sensing data and, by and large, the common classification techniques mainly exploit the spectral characteristics of remote sensing images and attempt to detect patterns in spectral information to classify images. These are based on a per-pixel analysis of the spectral information, "clustering" or "grouping" of pixels is done to generate meaningful thematic information. Most of the classification techniques apply statistical pattern recognition of image spectral vectors to "label" each pixel with appropriate class information from a set of training information. On the other hand, Segmentation is not new, but it is yet seldom used in image processing of remotely sensed data. Although there has been a lot of development in segmentation of grey tone images in this field and other fields, like robotic vision, there has been little progress in segmentation of colour or multi-band imagery. Especially within the last two years many new segmentation algorithms as well as applications were developed, but not all of them lead to qualitatively convincing results while being robust and operational. One reason is that the segmentation of an image into a given number of regions is a problem with a huge number of possible solutions. Newer algorithms based on fractal approach could eventually revolutionize image processing of remotely sensed data. The paper looks at applying spatial concepts to image processing, paving the way to algorithmically formulate some more advanced aspects of cognition and inference. In GIS-based spatial analysis, vector-based tools already have been able to support advanced tasks generating new knowledge. By identifying objects (as segmentation results) from

  12. Naive Bayes Image Classification: beyond Nearest Neighbors


    Timofte, Radu; Tuytelaars, Tinne; Van Gool, Luc


    Timofte R., Tuytelaars T., Van Gool L., ''Naive bayes image classification: beyond nearest neighbors'', 11th Asian conference on computer vision - ACCV 2012, 13 pp., November 5-9, 2012, Daejeon, Korea.


    Directory of Open Access Journals (Sweden)

    D. Chakraborty


    Full Text Available RISAT-II or Radar Imaging satellite – II is a microwave-imaging satellite lunched by ISRO to take images of the earth during day and night as well as all weather condition. This satellite enhances the ISRO's capability for disaster management application together with forestry, agricultural, urban and oceanographic applications. The conventional pixel based classification technique cannot classify these type of images since it do not take into account the texture information of the image. This paper presents a method to classify the high-resolution RISAT-II microwave images based on texture analysis. It suppress the speckle noise from the microwave image before analysis the texture of the image since speckle is essentially a form of noise, which degrades the quality of an image; make interpretation (visual or digital more difficult. A local adaptive median filter is developed that uses local statistics to detect the speckle noise of microwave image and to replace it with a local median value. Local Binary Pattern (LBP operator is proposed to measure the texture around each pixel of the speckle suppressed microwave image. It considers a series of circles (2D centered on the pixel with incremental radius values and the intersected pixels on the perimeter of the circles of radius r (where r = 1, 3 and 5 are used for measuring the LBP of the center pixel. The significance of LBP is that it measure the texture around each pixel of the image and computationally simple. ISODATA method is used to cluster the transformed LBP image. The proposed method adequately classifies RISAT-II X band microwave images without human intervention.

  14. Pigmented Skin Lesions Classification Using Dermatoscopic Images (United States)

    Capdehourat, Germán; Corez, Andrés; Bazzano, Anabella; Musé, Pablo

    In this paper we propose a machine learning approach to classify melanocytic lesions in malignant and benign from dermatoscopic images. The image database is composed of 433 benign lesions and 80 malignant melanoma. After an image pre-processing stage that includes hair removal filtering, each image is automatically segmented using well known image segmentation algorithms. Then, each lesion is characterized by a feature vector that contains shape, color and texture information, as well as local and global parameters that try to reflect structures used in medical diagnosis. The learning and classification stage is performed using AdaBoost.M1 with C4.5 decision trees. For the automatically segmented database, classification delivered a false positive rate of 8.75% for a sensitivity of 95%. The same classification procedure applied to manually segmented images by an experienced dermatologist yielded a false positive rate of 4.62% for a sensitivity of 95%.

  15. Spectrally Consistent Satellite Image Fusion with Improved Image Priors

    DEFF Research Database (Denmark)

    Nielsen, Allan Aasbjerg; Aanæs, Henrik; Jensen, Thomas B.S.


    Here an improvement to our previous framework for satellite image fusion is presented. A framework purely based on the sensor physics and on prior assumptions on the fused image. The contributions of this paper are two fold. Firstly, a method for ensuring 100% spectrally consistency is proposed......, even when more sophisticated image priors are applied. Secondly, a better image prior is introduced, via data-dependent image smoothing....

  16. Crop classification using temporal stacks of multispectral satellite imagery (United States)

    Moody, Daniela I.; Brumby, Steven P.; Chartrand, Rick; Keisler, Ryan; Longbotham, Nathan; Mertes, Carly; Skillman, Samuel W.; Warren, Michael S.


    The increase in performance, availability, and coverage of multispectral satellite sensor constellations has led to a drastic increase in data volume and data rate. Multi-decadal remote sensing datasets at the petabyte scale are now available in commercial clouds, with new satellite constellations generating petabytes/year of daily high-resolution global coverage imagery. The data analysis capability, however, has lagged behind storage and compute developments, and has traditionally focused on individual scene processing. We present results from an ongoing effort to develop satellite imagery analysis tools that aggregate temporal, spatial, and spectral information and can scale with the high-rate and dimensionality of imagery being collected. We investigate and compare the performance of pixel-level crop identification using tree-based classifiers and its dependence on both temporal and spectral features. Classification performance is assessed using as ground-truth Cropland Data Layer (CDL) crop masks generated by the US Department of Agriculture (USDA). The CDL maps contain 30m spatial resolution, pixel-level labels for around 200 categories of land cover, but are however only available post-growing season. The analysis focuses on McCook county in South Dakota and shows crop classification using a temporal stack of Landsat 8 (L8) imagery over the growing season, from April through October. Specifically, we consider the temporal L8 stack depth, as well as different normalized band difference indices, and evaluate their contribution to crop identification. We also show an extension of our algorithm to map corn and soy crops in the state of Mato Grosso, Brazil.

  17. Unsupervised Classification of Images: A Review


    Abass Olaode; Golshah Naghdy; Catherine Todd


    Unsupervised image classification is the process by which each image in a dataset is identified to be a member of one of the inherent categories present in the image collection without the use of labelled training samples. Unsupervised categorisation of images relies on unsupervised machine learning algorithms for its implementation. This paper identifies clustering algorithms and dimension reduction algorithms as the two main classes of unsupervised machine learning algorithms needed in unsu...

  18. Satellite Imaging in the Study of Pennsylvania's Environmental Issues. (United States)

    Nous, Albert P.

    This document focuses on using satellite images from space in the classroom. There are two types of environmental satellites routinely broadcasting: (1) Polar-Orbiting Operational Environmental Satellites (POES), and (2) Geostationary Operational Environmental Satellites (GOES). Imaging and visualization techniques provide students with a better…

  19. Satellite image compression using wavelet (United States)

    Santoso, Alb. Joko; Soesianto, F.; Dwiandiyanto, B. Yudi


    Image data is a combination of information and redundancies, the information is part of the data be protected because it contains the meaning and designation data. Meanwhile, the redundancies are part of data that can be reduced, compressed, or eliminated. Problems that arise are related to the nature of image data that spends a lot of memory. In this paper will compare 31 wavelet function by looking at its impact on PSNR, compression ratio, and bits per pixel (bpp) and the influence of decomposition level of PSNR and compression ratio. Based on testing performed, Haar wavelet has the advantage that is obtained PSNR is relatively higher compared with other wavelets. Compression ratio is relatively better than other types of wavelets. Bits per pixel is relatively better than other types of wavelet.

  20. A hierarchical classification scheme of psoriasis images

    DEFF Research Database (Denmark)

    Maletti, Gabriela Mariel; Ersbøll, Bjarne Kjær


    A two-stage hierarchical classification scheme of psoriasis lesion images is proposed. These images are basically composed of three classes: normal skin, lesion and background. The scheme combines conventional tools to separate the skin from the background in the first stage, and the lesion from...

  1. Pulmonary CT image classification with evolutionary programming. (United States)

    Madsen, M T; Uppaluri, R; Hoffman, E A; McLennan, G


    It is often difficult to classify information in medical images from derived features. The purpose of this research was to investigate the use of evolutionary programming as a tool for selecting important features and generating algorithms to classify computed tomographic (CT) images of the lung. Training and test sets consisting of 11 features derived from multiple lung CT images were generated, along with an indicator of the target area from which features originated. The images included five parameters based on histogram analysis, 11 parameters based on run length and co-occurrence matrix measures, and the fractal dimension. Two classification experiments were performed. In the first, the classification task was to distinguish between the subtle but known differences between anterior and posterior portions of transverse lung CT sections. The second classification task was to distinguish normal lung CT images from emphysematous images. The performance of the evolutionary programming approach was compared with that of three statistical classifiers that used the same training and test sets. Evolutionary programming produced solutions that compared favorably with those of the statistical classifiers. In separating the anterior from the posterior lung sections, the evolutionary programming results were better than two of the three statistical approaches. The evolutionary programming approach correctly identified all the normal and abnormal lung images and accomplished this by using less features than the best statistical method. The results of this study demonstrate the utility of evolutionary programming as a tool for developing classification algorithms.


    Directory of Open Access Journals (Sweden)

    M. De Giglio


    Full Text Available Within coastal systems, sand dunes are the only natural barriers able to counteract erosive processes. Since their equilibrium is often threatened by human activities and high vulnerability of the coastal environment, dunes require increasing attention and specific monitoring. Located between the mainland and the sea, dunes are unique residue habitats for some plant and animal species. In particular, their vegetation is important because it has a consolidation function and promotes the vertical dune accretion. A georeferenced vegetation classification can be useful to define the advancements or erosion stage of the dune, usually based only on the geometric reconstruction. The proposed study aims to compare the classifications performed with some combinations of two of the last generation sensors and traditional image processing techniques. High spectral resolution satellite image (WorldView-2 and a multispectral orthophoto, obtained from data acquired by an unmanned aerial vehicle, were used. Objects and pixel algorithms were applied and the results were compared by a statistical test. Using the same bands, the findings show that both data are suitable for monitoring the evolutionary dune status. Specifically, the WorldView-2 pixel-based classification and UAV object-based classification provide the same accurate results.

  3. Lissencephaly: Expanded imaging and clinical classification. (United States)

    Di Donato, Nataliya; Chiari, Sara; Mirzaa, Ghayda M; Aldinger, Kimberly; Parrini, Elena; Olds, Carissa; Barkovich, A James; Guerrini, Renzo; Dobyns, William B


    Lissencephaly ("smooth brain," LIS) is a malformation of cortical development associated with deficient neuronal migration and abnormal formation of cerebral convolutions or gyri. The LIS spectrum includes agyria, pachygyria, and subcortical band heterotopia. Our first classification of LIS and subcortical band heterotopia (SBH) was developed to distinguish between the first two genetic causes of LIS-LIS1 (PAFAH1B1) and DCX. However, progress in molecular genetics has led to identification of 19 LIS-associated genes, leaving the existing classification system insufficient to distinguish the increasingly diverse patterns of LIS. To address this challenge, we reviewed clinical, imaging and molecular data on 188 patients with LIS-SBH ascertained during the last 5 years, and reviewed selected archival data on another ∼1,400 patients. Using these data plus published reports, we constructed a new imaging based classification system with 21 recognizable patterns that reliably predict the most likely causative genes. These patterns do not correlate consistently with the clinical outcome, leading us to also develop a new scale useful for predicting clinical severity and outcome. Taken together, our work provides new tools that should prove useful for clinical management and genetic counselling of patients with LIS-SBH (imaging and severity based classifications), and guidance for prioritizing and interpreting genetic testing results (imaging based- classification). © 2017 Wiley Periodicals, Inc.

  4. Image Classification Workflow Using Machine Learning Methods (United States)

    Christoffersen, M. S.; Roser, M.; Valadez-Vergara, R.; Fernández-Vega, J. A.; Pierce, S. A.; Arora, R.


    Recent increases in the availability and quality of remote sensing datasets have fueled an increasing number of scientifically significant discoveries based on land use classification and land use change analysis. However, much of the software made to work with remote sensing data products, specifically multispectral images, is commercial and often prohibitively expensive. The free to use solutions that are currently available come bundled up as small parts of much larger programs that are very susceptible to bugs and difficult to install and configure. What is needed is a compact, easy to use set of tools to perform land use analysis on multispectral images. To address this need, we have developed software using the Python programming language with the sole function of land use classification and land use change analysis. We chose Python to develop our software because it is relatively readable, has a large body of relevant third party libraries such as GDAL and Spectral Python, and is free to install and use on Windows, Linux, and Macintosh operating systems. In order to test our classification software, we performed a K-means unsupervised classification, Gaussian Maximum Likelihood supervised classification, and a Mahalanobis Distance based supervised classification. The images used for testing were three Landsat rasters of Austin, Texas with a spatial resolution of 60 meters for the years of 1984 and 1999, and 30 meters for the year 2015. The testing dataset was easily downloaded using the Earth Explorer application produced by the USGS. The software should be able to perform classification based on any set of multispectral rasters with little to no modification. Our software makes the ease of land use classification using commercial software available without an expensive license.

  5. Geometric calibration of ERS satellite SAR images

    DEFF Research Database (Denmark)

    Mohr, Johan Jacob; Madsen, Søren Nørvang


    Geometric calibration of the European Remote Sensing (ERS) Satellite synthetic aperture radar (SAR) slant range images is important in relation to mapping areas without ground reference points and also in relation to automated processing. The relevant SAR system parameters are discussed and calib......Geometric calibration of the European Remote Sensing (ERS) Satellite synthetic aperture radar (SAR) slant range images is important in relation to mapping areas without ground reference points and also in relation to automated processing. The relevant SAR system parameters are discussed...... on a seven-year ERS-1 and a four-year ERS-2 time series, the long term stability is found to be sufficient to allow a single calibration covering the entire mission period. A descending and an ascending orbit tandem pair of the ESA calibration site on Flevoland, suitable for calibration of ERS SAR processors...

  6. Wind Statistics Offshore based on Satellite Images

    DEFF Research Database (Denmark)

    Hasager, Charlotte Bay; Mouche, Alexis; Badger, Merete


    -based observations become available. At present preliminary results are obtained using the routine methods. The first step in the process is to retrieve raw SAR data, calibrate the images and use a priori wind direction as input to the geophysical model function. From this process the wind speed maps are produced....... Results comparing satellite scatterometer winds to offshore meteorological observations have shown good results, and more comparisons are planned in this respect during the Norsewind project....

  7. Large margin image set representation and classification

    KAUST Repository

    Wang, Jim Jing-Yan


    In this paper, we propose a novel image set representation and classification method by maximizing the margin of image sets. The margin of an image set is defined as the difference of the distance to its nearest image set from different classes and the distance to its nearest image set of the same class. By modeling the image sets by using both their image samples and their affine hull models, and maximizing the margins of the images sets, the image set representation parameter learning problem is formulated as an minimization problem, which is further optimized by an expectation - maximization (EM) strategy with accelerated proximal gradient (APG) optimization in an iterative algorithm. To classify a given test image set, we assign it to the class which could provide the largest margin. Experiments on two applications of video-sequence-based face recognition demonstrate that the proposed method significantly outperforms state-of-the-art image set classification methods in terms of both effectiveness and efficiency.

  8. Estimating seasonal evapotranspiration from temporal satellite images (United States)

    Singh, Ramesh K.; Liu, Shu-Guang; Tieszen, Larry L.; Suyker, Andrew E.; Verma, Shashi B.


    Estimating seasonal evapotranspiration (ET) has many applications in water resources planning and management, including hydrological and ecological modeling. Availability of satellite remote sensing images is limited due to repeat cycle of satellite or cloud cover. This study was conducted to determine the suitability of different methods namely cubic spline, fixed, and linear for estimating seasonal ET from temporal remotely sensed images. Mapping Evapotranspiration at high Resolution with Internalized Calibration (METRIC) model in conjunction with the wet METRIC (wMETRIC), a modified version of the METRIC model, was used to estimate ET on the days of satellite overpass using eight Landsat images during the 2001 crop growing season in Midwest USA. The model-estimated daily ET was in good agreement (R2 = 0.91) with the eddy covariance tower-measured daily ET. The standard error of daily ET was 0.6 mm (20%) at three validation sites in Nebraska, USA. There was no statistically significant difference (P > 0.05) among the cubic spline, fixed, and linear methods for computing seasonal (July–December) ET from temporal ET estimates. Overall, the cubic spline resulted in the lowest standard error of 6 mm (1.67%) for seasonal ET. However, further testing of this method for multiple years is necessary to determine its suitability.

  9. Linear distance coding for image classification. (United States)

    Wang, Zilei; Feng, Jiashi; Yan, Shuicheng; Xi, Hongsheng


    The feature coding-pooling framework is shown to perform well in image classification tasks, because it can generate discriminative and robust image representations. The unavoidable information loss incurred by feature quantization in the coding process and the undesired dependence of pooling on the image spatial layout, however, may severely limit the classification. In this paper, we propose a linear distance coding (LDC) method to capture the discriminative information lost in traditional coding methods while simultaneously alleviating the dependence of pooling on the image spatial layout. The core of the LDC lies in transforming local features of an image into more discriminative distance vectors, where the robust image-to-class distance is employed. These distance vectors are further encoded into sparse codes to capture the salient features of the image. The LDC is theoretically and experimentally shown to be complementary to the traditional coding methods, and thus their combination can achieve higher classification accuracy. We demonstrate the effectiveness of LDC on six data sets, two of each of three types (specific object, scene, and general object), i.e., Flower 102 and PFID 61, Scene 15 and Indoor 67, Caltech 101 and Caltech 256. The results show that our method generally outperforms the traditional coding methods, and achieves or is comparable to the state-of-the-art performance on these data sets.

  10. Fast Image Texture Classification Using Decision Trees (United States)

    Thompson, David R.


    Texture analysis would permit improved autonomous, onboard science data interpretation for adaptive navigation, sampling, and downlink decisions. These analyses would assist with terrain analysis and instrument placement in both macroscopic and microscopic image data products. Unfortunately, most state-of-the-art texture analysis demands computationally expensive convolutions of filters involving many floating-point operations. This makes them infeasible for radiation- hardened computers and spaceflight hardware. A new method approximates traditional texture classification of each image pixel with a fast decision-tree classifier. The classifier uses image features derived from simple filtering operations involving integer arithmetic. The texture analysis method is therefore amenable to implementation on FPGA (field-programmable gate array) hardware. Image features based on the "integral image" transform produce descriptive and efficient texture descriptors. Training the decision tree on a set of training data yields a classification scheme that produces reasonable approximations of optimal "texton" analysis at a fraction of the computational cost. A decision-tree learning algorithm employing the traditional k-means criterion of inter-cluster variance is used to learn tree structure from training data. The result is an efficient and accurate summary of surface morphology in images. This work is an evolutionary advance that unites several previous algorithms (k-means clustering, integral images, decision trees) and applies them to a new problem domain (morphology analysis for autonomous science during remote exploration). Advantages include order-of-magnitude improvements in runtime, feasibility for FPGA hardware, and significant improvements in texture classification accuracy.

  11. Bayesian Classification of Image Structures

    DEFF Research Database (Denmark)

    Goswami, Dibyendu; Kalkan, Sinan; Krüger, Norbert


    In this paper, we describe work on Bayesian classi ers for distinguishing between homogeneous structures, textures, edges and junctions. We build semi-local classiers from hand-labeled images to distinguish between these four different kinds of structures based on the concept of intrinsic...

  12. Attribute Learning for SAR Image Classification

    Directory of Open Access Journals (Sweden)

    Chu He


    Full Text Available This paper presents a classification approach based on attribute learning for high spatial resolution Synthetic Aperture Radar (SAR images. To explore the representative and discriminative attributes of SAR images, first, an iterative unsupervised algorithm is designed to cluster in the low-level feature space, where the maximum edge response and the ratio of mean-to-variance are included; a cross-validation step is applied to prevent overfitting. Second, the most discriminative clustering centers are sorted out to construct an attribute dictionary. By resorting to the attribute dictionary, a representation vector describing certain categories in the SAR image can be generated, which in turn is used to perform the classifying task. The experiments conducted on TerraSAR-X images indicate that those learned attributes have strong visual semantics, which are characterized by bright and dark spots, stripes, or their combinations. The classification method based on these learned attributes achieves better results.

  13. Model-based satellite image fusion

    DEFF Research Database (Denmark)

    Aanæs, Henrik; Sveinsson, J. R.; Nielsen, Allan Aasbjerg


    A method is proposed for pixel-level satellite image fusion derived directly from a model of the imaging sensor. By design, the proposed method is spectrally consistent. It is argued that the proposed method needs regularization, as is the case for any method for this problem. A framework for pixel...... neighborhood regularization is presented. This framework enables the formulation of the regularization in a way that corresponds well with our prior assumptions of the image data. The proposed method is validated and compared with other approaches on several data sets. Lastly, the intensity......-hue-saturation method is revisited in order to gain additional insight of what implications the spectral consistency has for an image fusion method....

  14. Texture classification of lung computed tomography images (United States)

    Pheng, Hang See; Shamsuddin, Siti M.


    Current development of algorithms in computer-aided diagnosis (CAD) scheme is growing rapidly to assist the radiologist in medical image interpretation. Texture analysis of computed tomography (CT) scans is one of important preliminary stage in the computerized detection system and classification for lung cancer. Among different types of images features analysis, Haralick texture with variety of statistical measures has been used widely in image texture description. The extraction of texture feature values is essential to be used by a CAD especially in classification of the normal and abnormal tissue on the cross sectional CT images. This paper aims to compare experimental results using texture extraction and different machine leaning methods in the classification normal and abnormal tissues through lung CT images. The machine learning methods involve in this assessment are Artificial Immune Recognition System (AIRS), Naive Bayes, Decision Tree (J48) and Backpropagation Neural Network. AIRS is found to provide high accuracy (99.2%) and sensitivity (98.0%) in the assessment. For experiments and testing purpose, publicly available datasets in the Reference Image Database to Evaluate Therapy Response (RIDER) are used as study cases.

  15. Embedded Implementation of VHR Satellite Image Segmentation

    Directory of Open Access Journals (Sweden)

    Chao Li


    Full Text Available Processing and analysis of Very High Resolution (VHR satellite images provide a mass of crucial information, which can be used for urban planning, security issues or environmental monitoring. However, they are computationally expensive and, thus, time consuming, while some of the applications, such as natural disaster monitoring and prevention, require high efficiency performance. Fortunately, parallel computing techniques and embedded systems have made great progress in recent years, and a series of massively parallel image processing devices, such as digital signal processors or Field Programmable Gate Arrays (FPGAs, have been made available to engineers at a very convenient price and demonstrate significant advantages in terms of running-cost, embeddability, power consumption flexibility, etc. In this work, we designed a texture region segmentation method for very high resolution satellite images by using the level set algorithm and the multi-kernel theory in a high-abstraction C environment and realize its register-transfer level implementation with the help of a new proposed high-level synthesis-based design flow. The evaluation experiments demonstrate that the proposed design can produce high quality image segmentation with a significant running-cost advantage.

  16. System refinement for content based satellite image retrieval

    Directory of Open Access Journals (Sweden)

    NourElDin Laban


    Full Text Available We are witnessing a large increase in satellite generated data especially in the form of images. Hence intelligent processing of the huge amount of data received by dozens of earth observing satellites, with specific satellite image oriented approaches, presents itself as a pressing need. Content based satellite image retrieval (CBSIR approaches have mainly been driven so far by approaches dealing with traditional images. In this paper we introduce a novel approach that refines image retrieval process using the unique properties to satellite images. Our approach uses a Query by polygon (QBP paradigm for the content of interest instead of using the more conventional rectangular query by image approach. First, we extract features from the satellite images using multiple tiling sizes. Accordingly the system uses these multilevel features within a multilevel retrieval system that refines the retrieval process. Our multilevel refinement approach has been experimentally validated against the conventional one yielding enhanced precision and recall rates.

  17. Land cover and forest formation distributions for St. Kitts, Nevis, St. Eustatius, Grenada and Barbados from decision tree classification of cloud-cleared satellite imagery. Caribbean Journal of Science. 44(2):175-198. (United States)

    E.H. Helmer; T.A. Kennaway; D.H. Pedreros; M.L. Clark; H. Marcano-Vega; L.L. Tieszen; S.R. Schill; C.M.S. Carrington


    Satellite image-based mapping of tropical forests is vital to conservation planning. Standard methods for automated image classification, however, limit classification detail in complex tropical landscapes. In this study, we test an approach to Landsat image interpretation on four islands of the Lesser Antilles, including Grenada and St. Kitts, Nevis and St. Eustatius...

  18. Coastal Land Cover Classification Using Sentinel-1 Images


    Datcu, Mihai; Dumitru, Corneliu; Espinoza-Molina, Daniela; Schwarz, Gottfried; Clerk, Sebastien


    An ESA-funde The ESA-funded Coastal Thematic Exploitation Platform(C-TEP) can be used for the classification of Sentinel-1 images. This classification can be used for land cover classification of coastal areas. It turns out that the SAR images provided by Sentinel-1 lend themselves well to a robust land cover classification.

  19. Retrieval and classification of food images. (United States)

    Farinella, Giovanni Maria; Allegra, Dario; Moltisanti, Marco; Stanco, Filippo; Battiato, Sebastiano


    Automatic food understanding from images is an interesting challenge with applications in different domains. In particular, food intake monitoring is becoming more and more important because of the key role that it plays in health and market economies. In this paper, we address the study of food image processing from the perspective of Computer Vision. As first contribution we present a survey of the studies in the context of food image processing from the early attempts to the current state-of-the-art methods. Since retrieval and classification engines able to work on food images are required to build automatic systems for diet monitoring (e.g., to be embedded in wearable cameras), we focus our attention on the aspect of the representation of the food images because it plays a fundamental role in the understanding engines. The food retrieval and classification is a challenging task since the food presents high variableness and an intrinsic deformability. To properly study the peculiarities of different image representations we propose the UNICT-FD1200 dataset. It was composed of 4754 food images of 1200 distinct dishes acquired during real meals. Each food plate is acquired multiple times and the overall dataset presents both geometric and photometric variabilities. The images of the dataset have been manually labeled considering 8 categories: Appetizer, Main Course, Second Course, Single Course, Side Dish, Dessert, Breakfast, Fruit. We have performed tests employing different representations of the state-of-the-art to assess the related performances on the UNICT-FD1200 dataset. Finally, we propose a new representation based on the perceptual concept of Anti-Textons which is able to encode spatial information between Textons outperforming other representations in the context of food retrieval and Classification. Copyright © 2016 Elsevier Ltd. All rights reserved.

  20. Fast automated cell phenotype image classification

    Directory of Open Access Journals (Sweden)

    Pantelic Radosav S


    Full Text Available Abstract Background The genomic revolution has led to rapid growth in sequencing of genes and proteins, and attention is now turning to the function of the encoded proteins. In this respect, microscope imaging of a protein's sub-cellular localisation is proving invaluable, and recent advances in automated fluorescent microscopy allow protein localisations to be imaged in high throughput. Hence there is a need for large scale automated computational techniques to efficiently quantify, distinguish and classify sub-cellular images. While image statistics have proved highly successful in distinguishing localisation, commonly used measures suffer from being relatively slow to compute, and often require cells to be individually selected from experimental images, thus limiting both throughput and the range of potential applications. Here we introduce threshold adjacency statistics, the essence which is to threshold the image and to count the number of above threshold pixels with a given number of above threshold pixels adjacent. These novel measures are shown to distinguish and classify images of distinct sub-cellular localization with high speed and accuracy without image cropping. Results Threshold adjacency statistics are applied to classification of protein sub-cellular localization images. They are tested on two image sets (available for download, one for which fluorescently tagged proteins are endogenously expressed in 10 sub-cellular locations, and another for which proteins are transfected into 11 locations. For each image set, a support vector machine was trained and tested. Classification accuracies of 94.4% and 86.6% are obtained on the endogenous and transfected sets, respectively. Threshold adjacency statistics are found to provide comparable or higher accuracy than other commonly used statistics while being an order of magnitude faster to calculate. Further, threshold adjacency statistics in combination with Haralick measures give

  1. ASTER 2002-2003 Kansas Satellite Image Database (KSID) (United States)

    Kansas Data Access and Support Center — The Kansas Satellite Image Database (KSID):2002-2003 consists of image data gathered by three sensors. The first image data are terrain-corrected, precision...

  2. MODIS 2002-2003 Kansas Satellite Image Database (KSID) (United States)

    Kansas Data Access and Support Center — The Kansas Satellite Image Database (KSID):2002-2003 consists of image data gathered by three sensors. The first image data are terrain-corrected, precision...

  3. Scalable active learning for multiclass image classification. (United States)

    Joshi, Ajay J; Porikli, Fatih; Papanikolopoulos, Nikolaos P


    Machine learning techniques for computer vision applications like object recognition, scene classification, etc., require a large number of training samples for satisfactory performance. Especially when classification is to be performed over many categories, providing enough training samples for each category is infeasible. This paper describes new ideas in multiclass active learning to deal with the training bottleneck, making it easier to train large multiclass image classification systems. First, we propose a new interaction modality for training which requires only yes-no type binary feedback instead of a precise category label. The modality is especially powerful in the presence of hundreds of categories. For the proposed modality, we develop a Value-of-Information (VOI) algorithm that chooses informative queries while also considering user annotation cost. Second, we propose an active selection measure that works with many categories and is extremely fast to compute. This measure is employed to perform a fast seed search before computing VOI, resulting in an algorithm that scales linearly with dataset size. Third, we use locality sensitive hashing to provide a very fast approximation to active learning, which gives sublinear time scaling, allowing application to very large datasets. The approximation provides up to two orders of magnitude speedups with little loss in accuracy. Thorough empirical evaluation of classification accuracy, noise sensitivity, imbalanced data, and computational performance on a diverse set of image datasets demonstrates the strengths of the proposed algorithms.

  4. Polar-Orbiting Satellite (POES) Images (United States)

    National Oceanic and Atmospheric Administration, Department of Commerce — Visible and Infrared satellite imagery taken from camera systems or radiometer instruments on satellites in orbit around the poles. Satellite campaigns include...

  5. Thermal and Visible Satellite Image Fusion Using Wavelet in Remote Sensing and Satellite Image Processing (United States)

    Ahrari, A. H.; Kiavarz, M.; Hasanlou, M.; Marofi, M.


    Multimodal remote sensing approach is based on merging different data in different portions of electromagnetic radiation that improves the accuracy in satellite image processing and interpretations. Remote Sensing Visible and thermal infrared bands independently contain valuable spatial and spectral information. Visible bands make enough information spatially and thermal makes more different radiometric and spectral information than visible. However low spatial resolution is the most important limitation in thermal infrared bands. Using satellite image fusion, it is possible to merge them as a single thermal image that contains high spectral and spatial information at the same time. The aim of this study is a performance assessment of thermal and visible image fusion quantitatively and qualitatively with wavelet transform and different filters. In this research, wavelet algorithm (Haar) and different decomposition filters (mean.linear,ma,min and rand) for thermal and panchromatic bands of Landast8 Satellite were applied as shortwave and longwave fusion method . Finally, quality assessment has been done with quantitative and qualitative approaches. Quantitative parameters such as Entropy, Standard Deviation, Cross Correlation, Q Factor and Mutual Information were used. For thermal and visible image fusion accuracy assessment, all parameters (quantitative and qualitative) must be analysed with respect to each other. Among all relevant statistical factors, correlation has the most meaningful result and similarity to the qualitative assessment. Results showed that mean and linear filters make better fused images against the other filters in Haar algorithm. Linear and mean filters have same performance and there is not any difference between their qualitative and quantitative results.

  6. Synergetics Framework for Hyperspectral Image Classification (United States)

    Müller, R.; Cerra, D.; Reinartz, P.


    In this paper a new classification technique for hyperspectral data based on synergetics theory is presented. Synergetics - originally introduced by the physicist H. Haken - is an interdisciplinary theory to find general rules for pattern formation through selforganization and has been successfully applied in fields ranging from biology to ecology, chemistry, cosmology, and thermodynamics up to sociology. Although this theory describes general rules for pattern formation it was linked also to pattern recognition. Pattern recognition algorithms based on synergetics theory have been applied to images in the spatial domain with limited success in the past, given their dependence on the rotation, shifting, and scaling of the images. These drawbacks can be discarded if such methods are applied to data acquired by a hyperspectral sensor in the spectral domain, as each single spectrum, related to an image element in the hyperspectral scene, can be analysed independently. The classification scheme based on synergetics introduces also methods for spatial regularization to get rid of "salt and pepper" classification results and for iterative parameter tuning to optimize class weights. The paper reports an experiment on a benchmark data set frequently used for method comparisons. This data set consists of a hyperspectral scene acquired by the Airborne Visible Infrared Imaging Spectrometer AVIRIS sensor of the Jet Propulsion Laboratory acquired over the Salinas Valley in CA, USA, with 15 vegetation classes. The results are compared to state-of-the-art methodologies like Support Vector Machines (SVM), Spectral Information Divergence (SID), Neural Networks, Logistic Regression, Factor Graphs or Spectral Angle Mapper (SAM). The outcomes are promising and often outperform state-of-the-art classification methodologies.

  7. Satellite image based methods for fuels maps updating (United States)

    Alonso-Benito, Alfonso; Hernandez-Leal, Pedro A.; Arbelo, Manuel; Gonzalez-Calvo, Alejandro; Moreno-Ruiz, Jose A.; Garcia-Lazaro, Jose R.


    Regular updating of fuels maps is important for forest fire management. Nevertheless complex and time consuming field work is usually necessary for this purpose, which prevents a more frequent update. That is why the assessment of the usefulness of satellite data and the development of remote sensing techniques that enable the automatic updating of these maps, is of vital interest. In this work, we have tested the use of the spectral bands of OLI (Operational Land Imager) sensor on board Landsat 8 satellite, for updating the fuels map of El Hierro Island (Spain). From previously digitized map, a set of 200 reference plots for different fuel types was created. A 50% of the plots were randomly used as a training set and the rest were considered for validation. Six supervised and 2 unsupervised classification methods were applied, considering two levels of detail. A first level with only 5 classes (Meadow, Brushwood, Undergrowth canopy cover >50%, Undergrowth canopy cover 84% for Maximun Likelihood. Meanwhile, level 2 results showed at best, an unacceptable overall accuracy of 34%, which prevents the use of this data for such a detailed characterization. Anyway it has been demonstrated that in some conditions, images of medium spatial resolution, like Landsat 8-OLI, could be a valid tool for an automatic upgrade of fuels maps, minimizing costs and complementing traditional methodologies.

  8. Airport runway detection in satellite images by Adaboost learning (United States)

    Zongur, Ugur; Halici, Ugur; Aytekin, Orsan; Ulusoy, Ilkay


    Advances in hardware and pattern recognition techniques, along with the widespread utilization of remote sensing satellites, have urged the development of automatic target detection systems in satellite images. Automatic detection of airports is particularly essential, due to the strategic importance of these targets. In this paper, a runway detection method using a segmentation process based on textural properties is proposed for the detection of airport runways, which is the most distinguishing element of an airport. Several local textural features are extracted including not only low level features such as mean, standard deviation of image intensity and gradient, but also Zernike Moments, Circular-Mellin Features, Haralick Features, as well as features involving Gabor Filters, Wavelets and Fourier Power Spectrum Analysis. Since the subset of the mentioned features, which have a role in the discrimination of airport runways from other structures and landforms, cannot be predicted trivially, Adaboost learning algorithm is employed for both classification and determining the feature subset, due to its feature selector nature. By means of the features chosen in this way, a coarse representation of possible runway locations is obtained. Promising experimental results are achieved and given.

  9. Prioritization criteria of objective index for disaster management by satellite image processing (United States)

    Poursaber, Mohammad R.; Ariki, Yasuo; Safi, Mohammad


    The outputs obtained from satellite image processing generally presents various information based on the interpretation technique, selected objects for object based processing, precision of processing, the number and time of images used for this process. This issue should be managed well during a disaster management process based on satellite images. Very high resolution (VHR) optical satellite data are potential sources to provide detailed information on damage and geological changes for a large area in a short time. In this paper, we studied tsunami triggered area, which was caused on 11 March 2011 by Tohoku earthquake, using VHR data from GeoEye-1satellite images. A set of pre and post-earthquake images were used to perform visual change analysis through comparison of these data. These images include the data of the same area before the disaster in normal condition and after the disaster which caused changes and also some modification imposed to that area. Upon occurrence of a disaster, the images are used to estimate the extent of the damage. Then based on disaster management criteria and the needs for recovery and reconstruction, the priorities for object based classification indexes are defined. In post-disaster management, they are used for reconstruction and sustainable development activities. Finally a classified characteristic definition has been proposed which can be used as sample indexes prioritization criteria for disaster management based on satellite image processing. This prioritization criteria are based on an object based processing technique and can be further developed for other image processing methods.

  10. Spectroscopic classification of icy satellites of Saturn I: Identification of terrain units on Dione (United States)

    Scipioni, F.; Tosi, F.; Stephan, K.; Filacchione, G.; Ciarniello, M.; Capaccioni, F.; Cerroni, P.


    Dione is one of the largest and densest icy satellites of Saturn. Its surface shows a marked asymmetry between its leading and trailing hemispheres, the leading side being brighter than the trailing side, which shows regions mantled by a dark veneer whose origin is likely exogenic. In order to identify different terrain units we applied the Spectral Angle Mapper (SAM) classification technique to Dione’s hyperspectral images acquired by the Visual and Infrared Mapping Spectrometer (VIMS) onboard the Cassini Orbiter in the infrared range (0.88-5.12 μm). On a relatively limited portion of the surface of Dione we first identified nine spectral endmembers, corresponding to as many terrain units, which mostly distinguish for water ice abundance and ice grain size. We then used these endmembers in SAM to achieve a comprehensive classification of the entire surface. The analysis of the infrared spectra returned by VIMS shows that different regions of Dione have variations in water ice bands depths, in average ice grain size, and in the concentration of contaminants, such as CO2 and hydrocarbons, which are clearly connected to morphological and geological structures. Generally, the spectral units that classify optically dark terrains are those showing suppressed water ice bands, a finer ice grain size and a higher concentration of carbon dioxide. Conversely, spectral units labeling brighter regions have deeper water ice absorption bands, higher albedo and a smaller concentration of contaminants. We also considered VIMS cubes of the small satellite Helene (one of the two Dione’s trojan moons) and we compared its infrared spectra to those of the spectral units found on Dione. We observe that the closest match between the spectra of the two satellites occurs for one of the youngest and freshest terrain units on Dione: the Creusa crater region.

  11. Clustering and Bayesian network for image of faces classification


    Jayech, Khlifia; Mahjoub, Mohamed Ali


    In a content based image classification system, target images are sorted by feature similarities with respect to the query (CBIR). In this paper, we propose to use new approach combining distance tangent, k-means algorithm and Bayesian network for image classification. First, we use the technique of tangent distance to calculate several tangent spaces representing the same image. The objective is to reduce the error in the classification phase. Second, we cut the image in a whole of blocks. F...

  12. Application of Object Based Classification and High Resolution Satellite Imagery for Savanna Ecosystem Analysis

    Directory of Open Access Journals (Sweden)

    Jane Southworth


    Full Text Available Savanna ecosystems are an important component of dryland regions and yet are exceedingly difficult to study using satellite imagery. Savannas are composed are varying amounts of trees, shrubs and grasses and typically traditional classification schemes or vegetation indices cannot differentiate across class type. This research utilizes object based classification (OBC for a region in Namibia, using IKONOS imagery, to help differentiate tree canopies and therefore woodland savanna, from shrub or grasslands. The methodology involved the identification and isolation of tree canopies within the imagery and the creation of tree polygon layers had an overall accuracy of 84%. In addition, the results were scaled up to a corresponding Landsat image of the same region, and the OBC results compared to corresponding pixel values of NDVI. The results were not compelling, indicating once more the problems of these traditional image analysis techniques for savanna ecosystems. Overall, the use of the OBC holds great promise for this ecosystem and could be utilized more frequently in studies of vegetation structure.

  13. One-class kernel subspace ensemble for medical image classification (United States)

    Zhang, Yungang; Zhang, Bailing; Coenen, Frans; Xiao, Jimin; Lu, Wenjin


    Classification of medical images is an important issue in computer-assisted diagnosis. In this paper, a classification scheme based on a one-class kernel principle component analysis (KPCA) model ensemble has been proposed for the classification of medical images. The ensemble consists of one-class KPCA models trained using different image features from each image class, and a proposed product combining rule was used for combining the KPCA models to produce classification confidence scores for assigning an image to each class. The effectiveness of the proposed classification scheme was verified using a breast cancer biopsy image dataset and a 3D optical coherence tomography (OCT) retinal image set. The combination of different image features exploits the complementary strengths of these different feature extractors. The proposed classification scheme obtained promising results on the two medical image sets. The proposed method was also evaluated on the UCI breast cancer dataset (diagnostic), and a competitive result was obtained.

  14. Region-based Unsupervised Classification of SAR Images

    NARCIS (Netherlands)

    K. Kayabol (Koray)


    htmlabstractMany applications in remote sensing, varying from crop and forest classification to urban area extraction, use Synthetic Aperture Radar (SAR) image classification. As ERCIM Fellows, we have studied the classification of land covers for a year. Our results on the classification of water,

  15. Albedo recovery for hyperspectral image classification (United States)

    Zhan, Kun; Wang, Haibo; Xie, Yuange; Zhang, Chutong; Min, Yufang


    Image intensity value is determined by both the albedo component and the shading component. The albedo component describes the physical nature of different objects at the surface of the earth, and land-cover classes are different from each other because of their intrinsic physical materials. We, therefore, recover the intrinsic albedo feature of the hyperspectral image to exploit the spatial semantic information. Then, we use the support vector machine (SVM) to classify the recovered intrinsic albedo hyperspectral image. The SVM tries to maximize the minimum margin to achieve good generalization performance. Experimental results show that the SVM with the intrinsic albedo feature method achieves a better classification performance than the state-of-the-art methods in terms of visual quality and three quantitative metrics.

  16. Decision tree approach for classification of remotely sensed satellite ...

    Indian Academy of Sciences (India)

    using classical ISODATA clustering and Maximum Likelihood Classifier (MLC) algorithms. Classification ... clustering method. Based on the overall accuracy and kappa statistics, DTC was found to be more preferred classification approach than others. 1. Introduction .... trees branch or split the dataset; terminal nodes.

  17. Detecting aircrafts from satellite images using saliency and conical ...

    Indian Academy of Sciences (India)

    Samik Banerjee

    Abstract. Automatic target localization in satellite images still remains as a challenging problem in the field of computer vision. The issues involved in locating targets in satellite images are viewpoint, spectral (intensity) and scale variations. Diversity in background texture and target clutter also adds up to the complexity of ...

  18. Moving Target Information Extraction Based on Single Satellite Image

    Directory of Open Access Journals (Sweden)

    ZHAO Shihu


    Full Text Available The spatial and time variant effects in high resolution satellite push broom imaging are analyzed. A spatial and time variant imaging model is established. A moving target information extraction method is proposed based on a single satellite remote sensing image. The experiment computes two airplanes' flying speed using ZY-3 multispectral image and proves the validity of spatial and time variant model and moving information extracting method.

  19. Using Structural Features to Detect Buildings in Panchromatic Satellite Images


    Sirmacek, Beril; Unsalan, Cem


    Detecting buildings from very high resolution aerial and satellite images is very important for mapping, urban planning, and land use analysis. Although it is possible to manually locate buildings from these very high resolution images; this operation may not be robust and fast. Therefore, automated systems to detect buildings from very high resolution aerial and satellite images are needed. Unfortunately, solution is not straightforward due to diverse characteristics and uncontrolled imaging...


    Directory of Open Access Journals (Sweden)

    A. H. Ahrari


    Full Text Available Multimodal remote sensing approach is based on merging different data in different portions of electromagnetic radiation that improves the accuracy in satellite image processing and interpretations. Remote Sensing Visible and thermal infrared bands independently contain valuable spatial and spectral information. Visible bands make enough information spatially and thermal makes more different radiometric and spectral information than visible. However low spatial resolution is the most important limitation in thermal infrared bands. Using satellite image fusion, it is possible to merge them as a single thermal image that contains high spectral and spatial information at the same time. The aim of this study is a performance assessment of thermal and visible image fusion quantitatively and qualitatively with wavelet transform and different filters. In this research, wavelet algorithm (Haar and different decomposition filters (mean.linear,ma,min and rand for thermal and panchromatic bands of Landast8 Satellite were applied as shortwave and longwave fusion method . Finally, quality assessment has been done with quantitative and qualitative approaches. Quantitative parameters such as Entropy, Standard Deviation, Cross Correlation, Q Factor and Mutual Information were used. For thermal and visible image fusion accuracy assessment, all parameters (quantitative and qualitative must be analysed with respect to each other. Among all relevant statistical factors, correlation has the most meaningful result and similarity to the qualitative assessment. Results showed that mean and linear filters make better fused images against the other filters in Haar algorithm. Linear and mean filters have same performance and there is not any difference between their qualitative and quantitative results.

  1. Visualization and unsupervised classification of changes in multispectral satellite imagery

    DEFF Research Database (Denmark)

    Canty, Morton J.; Nielsen, Allan Aasbjerg


    The statistical techniques of multivariate alteration detection, minimum/maximum autocorrelation factors transformation, expectation maximization and probabilistic label relaxation are combined in a unified scheme to visualize and to classify changes in multispectral satellite data. The methods...

  2. Unsupervised classification of changes in multispectral satellite imagery

    DEFF Research Database (Denmark)

    Canty, Morton J.; Nielsen, Allan Aasbjerg


    The statistical techniques of multivariate alteration detection, maximum autocorrelation factor transformation, expectation maximization, fuzzy maximum likelihood estimation and probabilistic label relaxation are combined in a unified scheme to classify changes in multispectral satellite data...

  3. Building damage scale proposal from VHR satellite image (United States)

    Sandu, Constantin; Giulio Tonolo, Fabio; Cotrufo, Silvana; Boccardo, Piero


    Natural hazards have a huge impact in terms of economic losses, affected and killed people. Current exploitation of remote sensed images play a fundamental role in the delineation of damages generated by catastrophic events. Institutions like the United Nations and the European Commission designed services that provide information about the impact of disasters rapidly. One of the approach currently used to carry out the damage assessment is based on very high resolution remote sensing imagery (including both aerial and satellite platforms). One of the main focus of the responders, especially in case of events like earthquakes, is on buildings and infrastructures. As far as the buildings are concerned, to date international standard guidelines that provide essential information on how to assess building damages using VHR images still does not exist. The aim of this study is to develop a building damage scale tailored for analyses based on VHR vertical imagery and to propose a standard for the related interpretation guidelines. The task is carried out by comparing the current scales used for damage assessment by the main satellite based emergency mapping services. The study will analyze the datasets produced after the Ecuador (April 2016) and Central Italy(August and October 2016) earthquakes. The results suggest that by using VHR remotely sensed images it is not possible to directly use damage classification scales addressing structural damages (e.g the 5 grades proposed by EMS-98). A fine-tuning of existing damage classes is therefore required and the adoption of an internationally agreed standard should be encouraged, to streamline the use of SEM products generated by different services.

  4. Object Manifold Alignment for Multi-Temporal High Resolution Remote Sensing Images Classification (United States)

    Gao, G.; Zhang, M.; Gu, Y.


    Multi-temporal remote sensing images classification is very useful for monitoring the land cover changes. Traditional approaches in this field mainly face to limited labelled samples and spectral drift of image information. With spatial resolution improvement, "pepper and salt" appears and classification results will be effected when the pixelwise classification algorithms are applied to high-resolution satellite images, in which the spatial relationship among the pixels is ignored. For classifying the multi-temporal high resolution images with limited labelled samples, spectral drift and "pepper and salt" problem, an object-based manifold alignment method is proposed. Firstly, multi-temporal multispectral images are cut to superpixels by simple linear iterative clustering (SLIC) respectively. Secondly, some features obtained from superpixels are formed as vector. Thirdly, a majority voting manifold alignment method aiming at solving high resolution problem is proposed and mapping the vector data to alignment space. At last, all the data in the alignment space are classified by using KNN method. Multi-temporal images from different areas or the same area are both considered in this paper. In the experiments, 2 groups of multi-temporal HR images collected by China GF1 and GF2 satellites are used for performance evaluation. Experimental results indicate that the proposed method not only has significantly outperforms than traditional domain adaptation methods in classification accuracy, but also effectively overcome the problem of "pepper and salt".

  5. Detecting Weather Radar Clutter by Information Fusion With Satellite Images and Numerical Weather Prediction Model Output

    DEFF Research Database (Denmark)

    Bøvith, Thomas; Nielsen, Allan Aasbjerg; Hansen, Lars Kai


    A method for detecting clutter in weather radar images by information fusion is presented. Radar data, satellite images, and output from a numerical weather prediction model are combined and the radar echoes are classified using supervised classification. The presented method uses indirect...... information on precipitation in the atmosphere from Meteosat-8 multispectral images and near-surface temperature estimates from the DMI-HIRLAM-S05 numerical weather prediction model. Alternatively, an operational nowcasting product called 'Precipitating Clouds' based on Meteosat-8 input is used. A scale......-space ensemble method is used for classification and the clutter detection method is illustrated on a case of severe sea clutter contaminated radar data. Detection accuracies above 90 % are achieved and using an ensemble classification method the error rate is reduced by 40 %....

  6. Automatic Classification of High Resolution Satellite Imagery - a Case Study for Urban Areas in the Kingdom of Saudi Arabia (United States)

    Maas, A.; Alrajhi, M.; Alobeid, A.; Heipke, C.


    Updating topographic geospatial databases is often performed based on current remotely sensed images. To automatically extract the object information (labels) from the images, supervised classifiers are being employed. Decisions to be taken in this process concern the definition of the classes which should be recognised, the features to describe each class and the training data necessary in the learning part of classification. With a view to large scale topographic databases for fast developing urban areas in the Kingdom of Saudi Arabia we conducted a case study, which investigated the following two questions: (a) which set of features is best suitable for the classification?; (b) what is the added value of height information, e.g. derived from stereo imagery? Using stereoscopic GeoEye and Ikonos satellite data we investigate these two questions based on our research on label tolerant classification using logistic regression and partly incorrect training data. We show that in between five and ten features can be recommended to obtain a stable solution, that height information consistently yields an improved overall classification accuracy of about 5%, and that label noise can be successfully modelled and thus only marginally influences the classification results.

  7. Satellite Data Visualization, Processing and Mapping using VIIRS Imager Data (United States)

    Phyu, A. N.


    A satellite is a manmade machine that is launched into space and orbits the Earth. These satellites are used for various purposes for examples: Environmental satellites help us monitor and protect our environment; Navigation (GPS) satellites provides accurate time and position information: and Communication satellites allows us the interact with each other over long distances. Suomi NPP is part of the constellation of Joint Polar Satellite System (JPSS) fleet of satellites which is an Environmental satellite that carries the Visual Infrared Imaging Radiometer Suite (VIIRS) instrument. VIIRS is a scanning radiometer that takes high resolution images of the Earth. VIIRS takes visible, infrared and radiometric measurements of the land, oceans, atmosphere and cryosphere. These high resolution images provide information that helps weather prediction and environmental forecasting of extreme events such as forest fires, ice jams, thunder storms and hurricane. This project will describe how VIIRS instrument data is processed, mapped, and visualized using variety of software and application. It will focus on extreme events like Hurricane Sandy and demonstrate how to use the satellite to map the extent of a storm. Data from environmental satellites such as Suomi NPP-VIIRS is important for monitoring climate change, sea level rise, land surface temperature changes as well as extreme weather events.

  8. Classification and Segmentation of Satellite Orthoimagery Using Convolutional Neural Networks

    Directory of Open Access Journals (Sweden)

    Martin Längkvist


    Full Text Available The availability of high-resolution remote sensing (HRRS data has opened up the possibility for new interesting applications, such as per-pixel classification of individual objects in greater detail. This paper shows how a convolutional neural network (CNN can be applied to multispectral orthoimagery and a digital surface model (DSM of a small city for a full, fast and accurate per-pixel classification. The predicted low-level pixel classes are then used to improve the high-level segmentation. Various design choices of the CNN architecture are evaluated and analyzed. The investigated land area is fully manually labeled into five categories (vegetation, ground, roads, buildings and water, and the classification accuracy is compared to other per-pixel classification works on other land areas that have a similar choice of categories. The results of the full classification and segmentation on selected segments of the map show that CNNs are a viable tool for solving both the segmentation and object recognition task for remote sensing data.

  9. Improved Wetland Classification Using Eight-Band High Resolution Satellite Imagery and a Hybrid Approach

    Directory of Open Access Journals (Sweden)

    Charles R. Lane


    Full Text Available Although remote sensing technology has long been used in wetland inventory and monitoring, the accuracy and detail level of wetland maps derived with moderate resolution imagery and traditional techniques have been limited and often unsatisfactory. We explored and evaluated the utility of a newly launched high-resolution, eight-band satellite system (Worldview-2; WV2 for identifying and classifying freshwater deltaic wetland vegetation and aquatic habitats in the Selenga River Delta of Lake Baikal, Russia, using a hybrid approach and a novel application of Indicator Species Analysis (ISA. We achieved an overall classification accuracy of 86.5% (Kappa coefficient: 0.85 for 22 classes of aquatic and wetland habitats and found that additional metrics, such as the Normalized Difference Vegetation Index and image texture, were valuable for improving the overall classification accuracy and particularly for discriminating among certain habitat classes. Our analysis demonstrated that including WV2’s four spectral bands from parts of the spectrum less commonly used in remote sensing analyses, along with the more traditional bandwidths, contributed to the increase in the overall classification accuracy by ~4% overall, but with considerable increases in our ability to discriminate certain communities. The coastal band improved differentiating open water and aquatic (i.e., vegetated habitats, and the yellow, red-edge, and near-infrared 2 bands improved discrimination among different vegetated aquatic and terrestrial habitats. The use of ISA provided statistical rigor in developing associations between spectral classes and field-based data. Our analyses demonstrated the utility of a hybrid approach and the benefit of additional bands and metrics in providing the first spatially explicit mapping of a large and heterogeneous wetland system.

  10. Iris Image Classification Based on Hierarchical Visual Codebook. (United States)

    Zhenan Sun; Hui Zhang; Tieniu Tan; Jianyu Wang


    Iris recognition as a reliable method for personal identification has been well-studied with the objective to assign the class label of each iris image to a unique subject. In contrast, iris image classification aims to classify an iris image to an application specific category, e.g., iris liveness detection (classification of genuine and fake iris images), race classification (e.g., classification of iris images of Asian and non-Asian subjects), coarse-to-fine iris identification (classification of all iris images in the central database into multiple categories). This paper proposes a general framework for iris image classification based on texture analysis. A novel texture pattern representation method called Hierarchical Visual Codebook (HVC) is proposed to encode the texture primitives of iris images. The proposed HVC method is an integration of two existing Bag-of-Words models, namely Vocabulary Tree (VT), and Locality-constrained Linear Coding (LLC). The HVC adopts a coarse-to-fine visual coding strategy and takes advantages of both VT and LLC for accurate and sparse representation of iris texture. Extensive experimental results demonstrate that the proposed iris image classification method achieves state-of-the-art performance for iris liveness detection, race classification, and coarse-to-fine iris identification. A comprehensive fake iris image database simulating four types of iris spoof attacks is developed as the benchmark for research of iris liveness detection.

  11. Cloud classification using whole-sky imager data

    Energy Technology Data Exchange (ETDEWEB)

    Buch, K.A. Jr.; Sun, C.H.; Thorne, L.R. [Sandia National Labs., Livermore, CA (United States)


    Clouds are one of the most important moderators of the earth radiation budget and one of the least understood. The effect that clouds have on the reflection and absorption of solar and terrestrial radiation is strongly influenced by their shape, size, and composition. Physically accurate parameterization of clouds is necessary for any general circulation model (GCM) to yield meaningful results. The work presented here is part of a larger project that is aimed at producing realistic three-dimensional (3D) volume renderings of cloud scenes based on measured data from real cloud scenes. These renderings will provide the important shape information for parameterizing GCMs. The specific goal of the current study is to develop an algorithm that automatically classifies (by cloud type) the clouds observed in the scene. This information will assist the volume rendering program in determining the shape of the cloud. Much work has been done on cloud classification using multispectral satellite images. Most of these references use some kind of texture measure to distinguish the different cloud types and some also use topological features (such as cloud/sky connectivity or total number of clouds). A wide variety of classification methods has been used, including neural networks, various types of clustering, and thresholding. The work presented here uses binary decision trees to distinguish the different cloud types based on cloud features vectors.

  12. Acne image analysis: lesion localization and classification (United States)

    Abas, Fazly Salleh; Kaffenberger, Benjamin; Bikowski, Joseph; Gurcan, Metin N.


    Acne is a common skin condition present predominantly in the adolescent population, but may continue into adulthood. Scarring occurs commonly as a sequel to severe inflammatory acne. The presence of acne and resultant scars are more than cosmetic, with a significant potential to alter quality of life and even job prospects. The psychosocial effects of acne and scars can be disturbing and may be a risk factor for serious psychological concerns. Treatment efficacy is generally determined based on an invalidated gestalt by the physician and patient. However, the validated assessment of acne can be challenging and time consuming. Acne can be classified into several morphologies including closed comedones (whiteheads), open comedones (blackheads), papules, pustules, cysts (nodules) and scars. For a validated assessment, the different morphologies need to be counted independently, a method that is far too time consuming considering the limited time available for a consultation. However, it is practical to record and analyze images since dermatologists can validate the severity of acne within seconds after uploading an image. This paper covers the processes of region-ofinterest determination using entropy-based filtering and thresholding as well acne lesion feature extraction. Feature extraction methods using discrete wavelet frames and gray-level co-occurence matrix were presented and their effectiveness in separating the six major acne lesion classes were discussed. Several classifiers were used to test the extracted features. Correct classification accuracy as high as 85.5% was achieved using the binary classification tree with fourteen principle components used as descriptors. Further studies are underway to further improve the algorithm performance and validate it on a larger database.

  13. Mapping soil heterogeneity using RapidEye satellite images (United States)

    Piccard, Isabelle; Eerens, Herman; Dong, Qinghan; Gobin, Anne; Goffart, Jean-Pierre; Curnel, Yannick; Planchon, Viviane


    In the frame of BELCAM, a project funded by the Belgian Science Policy Office (BELSPO), researchers from UCL, ULg, CRA-W and VITO aim to set up a collaborative system to develop and deliver relevant information for agricultural monitoring in Belgium. The main objective is to develop remote sensing methods and processing chains able to ingest crowd sourcing data, provided by farmers or associated partners, and to deliver in return relevant and up-to-date information for crop monitoring at the field and district level based on Sentinel-1 and -2 satellite imagery. One of the developments within BELCAM concerns an automatic procedure to detect soil heterogeneity within a parcel using optical high resolution images. Such heterogeneity maps can be used to adjust farming practices according to the detected heterogeneity. This heterogeneity may for instance be caused by differences in mineral composition of the soil, organic matter content, soil moisture or soil texture. Local differences in plant growth may be indicative for differences in soil characteristics. As such remote sensing derived vegetation indices may be used to reveal soil heterogeneity. VITO started to delineate homogeneous zones within parcels by analyzing a series of RapidEye images acquired in 2015 (as a precursor for Sentinel-2). Both unsupervised classification (ISODATA, K-means) and segmentation techniques were tested. Heterogeneity maps were generated from images acquired at different moments during the season (13 May, 30 June, 17 July, 31 August, 11 September and 1 November 2015). Tests were performed using blue, green, red, red edge and NIR reflectances separately and using derived indices such as NDVI, fAPAR, CIrededge, NDRE2. The results for selected winter wheat, maize and potato fields were evaluated together with experts from the collaborating agricultural research centers. For a few fields UAV images and/or yield measurements were available for comparison.

  14. Potential Evaluation of Different Types of Images and Their Combination for the Classification of GIS Objects Cropland and Grassland (United States)

    Recio, J. A.; Helmholz, P.; Müller, S.


    In many publications the performance of different classification algorithms regarding to agricultural classes is evaluated. In contrast, this paper focuses on the potential of different imagery for the classification of the two most frequent classes: cropland and grassland. For our experiments three categories of imagery, high resolution aerial images, high resolution RapidEye satellite images and medium resolution Disaster Monitoring Constellation (DMC) satellite images are examined. An object-based image classification, as one of the most reliable methods for the automatic updating and evaluation of landuse geospatial databases, is chosen. The object boundaries are taken from a GIS database, each object is described by means of a set of image based features. Spectral, textural and structural (semivariogram derived) features are extracted from images of different dates and sensors. During classification a supervised decision trees generating algorithm is applied. To evaluate the potential of the different images, all possible combinations of the available image data are tested during classification. The results show that the best performance of landuse classification is based on RapidEye data (overall accuracy of 90%), obtaining slightly accuracy increases when this imagery is combined with additional image data (overall accuracy of 92%).


    Directory of Open Access Journals (Sweden)

    J. A. Recio


    Full Text Available In many publications the performance of different classification algorithms regarding to agricultural classes is evaluated. In contrast, this paper focuses on the potential of different imagery for the classification of the two most frequent classes: cropland and grassland. For our experiments three categories of imagery, high resolution aerial images, high resolution RapidEye satellite images and medium resolution Disaster Monitoring Constellation (DMC satellite images are examined. An object-based image classification, as one of the most reliable methods for the automatic updating and evaluation of landuse geospatial databases, is chosen. The object boundaries are taken from a GIS database, each object is described by means of a set of image based features. Spectral, textural and structural (semivariogram derived features are extracted from images of different dates and sensors. During classification a supervised decision trees generating algorithm is applied. To evaluate the potential of the different images, all possible combinations of the available image data are tested during classification. The results show that the best performance of landuse classification is based on RapidEye data (overall accuracy of 90%, obtaining slightly accuracy increases when this imagery is combined with additional image data (overall accuracy of 92%.

  16. Recent development of feature extraction and classification multispectral/hyperspectral images: a systematic literature review (United States)

    Setiyoko, A.; Dharma, I. G. W. S.; Haryanto, T.


    Multispectral data and hyperspectral data acquired from satellite sensor have the ability in detecting various objects on the earth ranging from low scale to high scale modeling. These data are increasingly being used to produce geospatial information for rapid analysis by running feature extraction or classification process. Applying the most suited model for this data mining is still challenging because there are issues regarding accuracy and computational cost. This research aim is to develop a better understanding regarding object feature extraction and classification applied for satellite image by systematically reviewing related recent research projects. A method used in this research is based on PRISMA statement. After deriving important points from trusted sources, pixel based and texture-based feature extraction techniques are promising technique to be analyzed more in recent development of feature extraction and classification.

  17. Image Processing Technique for Automatic Detection of Satellite Streaks (United States)


    centaines d’images chaque semaine, toutes les tâches d’acquisition et de réduction des données doivent être automatisées dans la mesure du possible...of the satellite that must be reacquired. This satellite and its orbital parameters are already known. There is only incertitude in its exact

  18. Polarimetric SAR Image Supervised Classification Method Integrating Eigenvalues


    Xing Yanxiao; Zhang Yi; Li Ning; Wang Yu; Hu Guixiang


    Since classification methods based on H/α space have the drawback of yielding poor classification results for terrains with similar scattering features, in this study, we propose a polarimetric Synthetic Aperture Radar (SAR) image classification method based on eigenvalues. First, we extract eigenvalues and fit their distribution with an adaptive Gaussian mixture model. Then, using the naive Bayesian classifier, we obtain preliminary classification results. The distribution of eigenvalues in ...

  19. Kansas Satellite Image Database (KSID) 2004-2005 (United States)

    Kansas Data Access and Support Center — The Kansas Satellite Image Database (KSID) 2004-2005 consists of terrain-corrected, precision rectified spring, summer, and fall Landsat 5 Thematic Mapper (TM)...

  20. Landsat TM and ETM+ Kansas Satellite Image Database (KSID) (United States)

    Kansas Data Access and Support Center — The Kansas Satellite Image Database (KSID):2000-2001 consists of terrain-corrected, precision rectified spring, summer, and fall Landsat 5 Thematic Mapper (TM) and...

  1. Data acquisition for knowledge-based image classification and interpretation of remotely sensed multispectral images (United States)

    Simmeth, Robert-Josef; Spitzer, Hartwig H.


    An experiment is reported which had as its main requirement the gathering of a wide range of information about the scene under investigation. It took place at the area of the Nurnberg airport (Bavaria, West Germany) in the summer of 1991 and the spring of 1992. The time frame of the experiment was planned to get satellite images in addition to airborne images at nearly the same time. The airborne scanner provided images in eleven spectral channels from the visible to the thermal infrared with geometric resolutions between 0.75 m and 4.50 m. In parallel we performed several radiometric measurements of reference targets at the ground as well as meteorological measurements to take care of atmospheric effects and lighting conditions. To get a better knowledge of the whole area we gathered additional information of the Nurnberg airport and surroundings. In particular, we investigated the functionality and task of certain areas (airport, agricultural, and industrial) and the type of surface materials of objects (airplane, taxi way, park way, shed or hangar roof, natural surfaces) within the scene of investigation. A combination of vegetation filters, unsupervised classification, and gray scale morphological image processing was applied to the data. As a result we obtained pixel by pixel and morphological classification of buildings, roads, and vegetation.

  2. Retinex Preprocessing for Improved Multi-Spectral Image Classification (United States)

    Thompson, B.; Rahman, Z.; Park, S.


    The goal of multi-image classification is to identify and label "similar regions" within a scene. The ability to correctly classify a remotely sensed multi-image of a scene is affected by the ability of the classification process to adequately compensate for the effects of atmospheric variations and sensor anomalies. Better classification may be obtained if the multi-image is preprocessed before classification, so as to reduce the adverse effects of image formation. In this paper, we discuss the overall impact on multi-spectral image classification when the retinex image enhancement algorithm is used to preprocess multi-spectral images. The retinex is a multi-purpose image enhancement algorithm that performs dynamic range compression, reduces the dependence on lighting conditions, and generally enhances apparent spatial resolution. The retinex has been successfully applied to the enhancement of many different types of grayscale and color images. We show in this paper that retinex preprocessing improves the spatial structure of multi-spectral images and thus provides better within-class variations than would otherwise be obtained without the preprocessing. For a series of multi-spectral images obtained with diffuse and direct lighting, we show that without retinex preprocessing the class spectral signatures vary substantially with the lighting conditions. Whereas multi-dimensional clustering without preprocessing produced one-class homogeneous regions, the classification on the preprocessed images produced multi-class non-homogeneous regions. This lack of homogeneity is explained by the interaction between different agronomic treatments applied to the regions: the preprocessed images are closer to ground truth. The principle advantage that the retinex offers is that for different lighting conditions classifications derived from the retinex preprocessed images look remarkably "similar", and thus more consistent, whereas classifications derived from the original

  3. An Evolutionary Algorithm for Enhanced Magnetic Resonance Imaging Classification


    T.S. Murunya; S. Audithan


    This study presents an image classification method for retrieval of images from a multi-varied MRI database. With the development of sophisticated medical imaging technology which helps doctors in diagnosis, medical image databases contain a huge amount of digital images. Magnetic Resonance Imaging (MRI) is a widely used imaging technique which picks signals from a body's magnetic particles spinning to magnetic tune and through a computer converts scanned data into pictures of internal organs...


    Directory of Open Access Journals (Sweden)

    K. M. Buddhiraju


    Full Text Available In this paper a virtual laboratory for the Satellite Image Processing and Analysis (v-SIPAL being developed at the Indian Institute of Technology Bombay is described. v-SIPAL comprises a set of experiments that are normally carried out by students learning digital processing and analysis of satellite images using commercial software. Currently, the experiments that are available on the server include Image Viewer, Image Contrast Enhancement, Image Smoothing, Edge Enhancement, Principal Component Transform, Texture Analysis by Co-occurrence Matrix method, Image Indices, Color Coordinate Transforms, Fourier Analysis, Mathematical Morphology, Unsupervised Image Classification, Supervised Image Classification and Accuracy Assessment. The virtual laboratory includes a theory module for each option of every experiment, a description of the procedure to perform each experiment, the menu to choose and perform the experiment, a module on interpretation of results when performed with a given image and pre-specified options, bibliography, links to useful internet resources and user-feedback. The user can upload his/her own images for performing the experiments and can also reuse outputs of one experiment in another experiment where applicable. Some of the other experiments currently under development include georeferencing of images, data fusion, feature evaluation by divergence andJ-M distance, image compression, wavelet image analysis and change detection. Additions to the theory module include self-assessment quizzes, audio-video clips on selected concepts, and a discussion of elements of visual image interpretation. V-SIPAL is at the satge of internal evaluation within IIT Bombay and will soon be open to selected educational institutions in India for evaluation.

  5. Control of satellite imaging formations in multi-body regimes (United States)

    Howell, Kathleen C.; Millard, Lindsay D.


    Libration point orbits may be ideal locations for satellite imaging formations. Therefore, control of these arrays in multi-body regimes is critical. A continuous feedback control algorithm is developed that maintains a formation of satellites in motion that is bounded relative to a halo orbit. This algorithm is derived based on the dynamic characteristics of the phase space near periodic orbits in the circular restricted three-body problem (CR3BP). By adjusting parameters of the control algorithm appropriately, satellites in the formation follow trajectories that are particularly advantageous to imaging arrays. Image reconstruction and coverage of the ( u, v) plane are simulated for interferometric satellite configurations, demonstrating potential applications of the algorithm and the resulting motion.

  6. Determination of the Impact of Urbanization on Agricultural Lands using Multi-temporal Satellite Sensor Images (United States)

    Kaya, S.; Alganci, U.; Sertel, E.; Ustundag, B.


    Throughout the history, agricultural activities have been performed close to urban areas. Main reason behind this phenomenon is the need of fast marketing of the agricultural production to urban residents and financial provision. Thus, using the areas nearby cities for agricultural activities brings out advantage of easy transportation of productions and fast marketing. For decades, heavy migration to cities has directly and negatively affected natural grasslands, forests and agricultural lands. This pressure has caused agricultural lands to be changed into urban areas. Dense urbanization causes increase in impervious surfaces, heat islands and many other problems in addition to destruction of agricultural lands. Considering the negative impacts of urbanization on agricultural lands and natural resources, a periodic monitoring of these changes becomes indisputably important. At this point, satellite images are known to be good data sources for land cover / use change monitoring with their fast data acquisition, large area coverages and temporal resolution properties. Classification of the satellite images provides thematic the land cover / use maps of the earth surface and changes can be determined with GIS based analysis multi-temporal maps. In this study, effects of heavy urbanization over agricultural lands in Istanbul, metropolitan city of Turkey, were investigated with use of multi-temporal Landsat TM satellite images acquired between 1984 and 2011. Images were geometrically registered to each other and classified using supervised maximum likelihood classification algorithm. Resulting thematic maps were exported to GIS environment and destructed agricultural lands by urbanization were determined using spatial analysis.

  7. Application of Convolutional Neural Network in Classification of High Resolution Agricultural Remote Sensing Images (United States)

    Yao, C.; Zhang, Y.; Zhang, Y.; Liu, H.


    With the rapid development of Precision Agriculture (PA) promoted by high-resolution remote sensing, it makes significant sense in management and estimation of agriculture through crop classification of high-resolution remote sensing image. Due to the complex and fragmentation of the features and the surroundings in the circumstance of high-resolution, the accuracy of the traditional classification methods has not been able to meet the standard of agricultural problems. In this case, this paper proposed a classification method for high-resolution agricultural remote sensing images based on convolution neural networks(CNN). For training, a large number of training samples were produced by panchromatic images of GF-1 high-resolution satellite of China. In the experiment, through training and testing on the CNN under the toolbox of deep learning by MATLAB, the crop classification finally got the correct rate of 99.66 % after the gradual optimization of adjusting parameter during training. Through improving the accuracy of image classification and image recognition, the applications of CNN provide a reference value for the field of remote sensing in PA.


    Directory of Open Access Journals (Sweden)

    C. Yao


    Full Text Available With the rapid development of Precision Agriculture (PA promoted by high-resolution remote sensing, it makes significant sense in management and estimation of agriculture through crop classification of high-resolution remote sensing image. Due to the complex and fragmentation of the features and the surroundings in the circumstance of high-resolution, the accuracy of the traditional classification methods has not been able to meet the standard of agricultural problems. In this case, this paper proposed a classification method for high-resolution agricultural remote sensing images based on convolution neural networks(CNN. For training, a large number of training samples were produced by panchromatic images of GF-1 high-resolution satellite of China. In the experiment, through training and testing on the CNN under the toolbox of deep learning by MATLAB, the crop classification finally got the correct rate of 99.66 % after the gradual optimization of adjusting parameter during training. Through improving the accuracy of image classification and image recognition, the applications of CNN provide a reference value for the field of remote sensing in PA.

  9. Automatic Matching of High Resolution Satellite Images Based on RFM


    JI Shunping; YUAN Xiuxiao


    A matching method for high resolution satellite images based on RFM is presented.Firstly,the RFM parameters are used to predict the initial parallax of corresponding points and the prediction accuracy is analyzed.Secondly,the approximate epipolar equation is constructed based on projection tracking and its accuracy is analyzed.Thirdly,approximate 1D image matching is executed on pyramid images and least square matching on base images.At last RANSAC is imbedded to eliminate mis-matching points...

  10. Image classification by semisupervised sparse coding with confident unlabeled samples (United States)

    Li, Xiao; Fang, Min; Wu, Jinqiao; He, Liang; Tian, Xian


    Sparse coding has achieved very excellent performance in image classification tasks, especially when the supervision information is incorporated into the dictionary learning process. However, there is a large amount of unlabeled samples that are expensive and boring to annotate. We propose an image classification algorithm by semisupervised sparse coding with confident unlabeled samples. In order to make the learnt sparse coding more discriminative, we select and annotate some confident unlabeled samples. A minimization model is developed in which the reconstruction error of the labeled, the selected unlabeled and the remaining unlabeled data and the classification error are integrated, which enhances the discriminant property of the dictionary and sparse representations. The experimental results on image classification tasks demonstrate that our algorithm can significantly improve the image classification performance.

  11. Robust Transfer Metric Learning for Image Classification. (United States)

    Ding, Zhengming; Fu, Yun


    Metric learning has attracted increasing attention due to its critical role in image analysis and classification. Conventional metric learning always assumes that the training and test data are sampled from the same or similar distribution. However, to build an effective distance metric, we need abundant supervised knowledge (i.e., side/label information), which is generally inaccessible in practice, because of the expensive labeling cost. In this paper, we develop a robust transfer metric learning (RTML) framework to effectively assist the unlabeled target learning by transferring the knowledge from the well-labeled source domain. Specifically, RTML exploits knowledge transfer to mitigate the domain shift in two directions, i.e., sample space and feature space. In the sample space, domain-wise and class-wise adaption schemes are adopted to bridge the gap of marginal and conditional distribution disparities across two domains. In the feature space, our metric is built in a marginalized denoising fashion and low-rank constraint, which make it more robust to tackle noisy data in reality. Furthermore, we design an explicit rank constraint regularizer to replace the rank minimization NP-hard problem to guide the low-rank metric learning. Experimental results on several standard benchmarks demonstrate the effectiveness of our proposed RTML by comparing it with the state-of-the-art transfer learning and metric learning algorithms.


    Directory of Open Access Journals (Sweden)

    T. Partovi


    Full Text Available 3D building reconstruction from remote sensing image data from satellites is still an active research topic and very valuable for 3D city modelling. The roof model is the most important component to reconstruct the Level of Details 2 (LoD2 for a building in 3D modelling. While the general solution for roof modelling relies on the detailed cues (such as lines, corners and planes extracted from a Digital Surface Model (DSM, the correct detection of the roof type and its modelling can fail due to low quality of the DSM generated by dense stereo matching. To reduce dependencies of roof modelling on DSMs, the pansharpened satellite images as a rich resource of information are used in addition. In this paper, two strategies are employed for roof type classification. In the first one, building roof types are classified in a state-of-the-art supervised pre-trained convolutional neural network (CNN framework. In the second strategy, deep features from deep layers of different pre-trained CNN model are extracted and then an RBF kernel using SVM is employed to classify the building roof type. Based on roof complexity of the scene, a roof library including seven types of roofs is defined. A new semi-automatic method is proposed to generate training and test patches of each roof type in the library. Using the pre-trained CNN model does not only decrease the computation time for training significantly but also increases the classification accuracy.

  13. Roof Type Selection Based on Patch-Based Classification Using Deep Learning for High Resolution Satellite Imagery (United States)

    Partovi, T.; Fraundorfer, F.; Azimi, S.; Marmanis, D.; Reinartz, P.


    3D building reconstruction from remote sensing image data from satellites is still an active research topic and very valuable for 3D city modelling. The roof model is the most important component to reconstruct the Level of Details 2 (LoD2) for a building in 3D modelling. While the general solution for roof modelling relies on the detailed cues (such as lines, corners and planes) extracted from a Digital Surface Model (DSM), the correct detection of the roof type and its modelling can fail due to low quality of the DSM generated by dense stereo matching. To reduce dependencies of roof modelling on DSMs, the pansharpened satellite images as a rich resource of information are used in addition. In this paper, two strategies are employed for roof type classification. In the first one, building roof types are classified in a state-of-the-art supervised pre-trained convolutional neural network (CNN) framework. In the second strategy, deep features from deep layers of different pre-trained CNN model are extracted and then an RBF kernel using SVM is employed to classify the building roof type. Based on roof complexity of the scene, a roof library including seven types of roofs is defined. A new semi-automatic method is proposed to generate training and test patches of each roof type in the library. Using the pre-trained CNN model does not only decrease the computation time for training significantly but also increases the classification accuracy.

  14. Image interpretation for a multilevel land use classification system (United States)


    The potential use is discussed of three remote sensors for developing a four level land use classification system. Three types of imagery for photointerpretation are presented: ERTS-1 satellite imagery, high altitude photography, and medium altitude photography. Suggestions are given as to which remote sensors and imagery scales may be most effectively employed to provide data on specific types of land use.

  15. Fusion of Modis and Palsar Principal Component Images Through Curvelet Transform for Land Cover Classification (United States)

    Singh, Dharmendra; Kumar, Harish

    Earth observation satellites provide data that covers different portions of the electromagnetic spectrum at different spatial and spectral resolutions. The increasing availability of information products generated from satellite images are extending the ability to understand the patterns and dynamics of the earth resource systems at all scales of inquiry. In which one of the most important application is the generation of land cover classification from satellite images for understanding the actual status of various land cover classes. The prospect for the use of satel-lite images in land cover classification is an extremely promising one. The quality of satellite images available for land-use mapping is improving rapidly by development of advanced sensor technology. Particularly noteworthy in this regard is the improved spatial and spectral reso-lution of the images captured by new satellite sensors like MODIS, ASTER, Landsat 7, and SPOT 5. For the full exploitation of increasingly sophisticated multisource data, fusion tech-niques are being developed. Fused images may enhance the interpretation capabilities. The images used for fusion have different temporal, and spatial resolution. Therefore, the fused image provides a more complete view of the observed objects. It is one of the main aim of image fusion to integrate different data in order to obtain more information that can be de-rived from each of the single sensor data alone. A good example of this is the fusion of images acquired by different sensors having a different spatial resolution and of different spectral res-olution. Researchers are applying the fusion technique since from three decades and propose various useful methods and techniques. The importance of high-quality synthesis of spectral information is well suited and implemented for land cover classification. More recently, an underlying multiresolution analysis employing the discrete wavelet transform has been used in image fusion. It was found

  16. Roads Data Conflation Using Update High Resolution Satellite Images (United States)

    Abdollahi, A.; Riyahi Bakhtiari, H. R.


    Urbanization, industrialization and modernization are rapidly growing in developing countries. New industrial cities, with all the problems brought on by rapid population growth, need infrastructure to support the growth. This has led to the expansion and development of the road network. A great deal of road network data has made by using traditional methods in the past years. Over time, a large amount of descriptive information has assigned to these map data, but their geometric accuracy and precision is not appropriate to today's need. In this regard, the improvement of the geometric accuracy of road network data by preserving the descriptive data attributed to them and updating of the existing geo databases is necessary. Due to the size and extent of the country, updating the road network maps using traditional methods is time consuming and costly. Conversely, using remote sensing technology and geographic information systems can reduce costs, save time and increase accuracy and speed. With increasing the availability of high resolution satellite imagery and geospatial datasets there is an urgent need to combine geographic information from overlapping sources to retain accurate data, minimize redundancy, and reconcile data conflicts. In this research, an innovative method for a vector-to-imagery conflation by integrating several image-based and vector-based algorithms presented. The SVM method for image classification and Level Set method used to extract the road the different types of road intersections extracted from imagery using morphological operators. For matching the extracted points and to find the corresponding points, matching function which uses the nearest neighborhood method was applied. Finally, after identifying the matching points rubber-sheeting method used to align two datasets. Two residual and RMSE criteria used to evaluate accuracy. The results demonstrated excellent performance. The average root-mean-square error decreased from 11.8 to 4.1 m.

  17. Cassini imaging of Jupiter's atmosphere, satellites, and rings. (United States)

    Porco, Carolyn C; West, Robert A; McEwen, Alfred; Del Genio, Anthony D; Ingersoll, Andrew P; Thomas, Peter; Squyres, Steve; Dones, Luke; Murray, Carl D; Johnson, Torrence V; Burns, Joseph A; Brahic, Andre; Neukum, Gerhard; Veverka, Joseph; Barbara, John M; Denk, Tilmann; Evans, Michael; Ferrier, Joseph J; Geissler, Paul; Helfenstein, Paul; Roatsch, Thomas; Throop, Henry; Tiscareno, Matthew; Vasavada, Ashwin R


    The Cassini Imaging Science Subsystem acquired about 26,000 images of the Jupiter system as the spacecraft encountered the giant planet en route to Saturn. We report findings on Jupiter's zonal winds, convective storms, low-latitude upper troposphere, polar stratosphere, and northern aurora. We also describe previously unseen emissions arising from Io and Europa in eclipse, a giant volcanic plume over Io's north pole, disk-resolved images of the satellite Himalia, circumstantial evidence for a causal relation between the satellites Metis and Adrastea and the main jovian ring, and information on the nature of the ring particles.

  18. Unsupervised feature learning for autonomous rock image classification (United States)

    Shu, Lei; McIsaac, Kenneth; Osinski, Gordon R.; Francis, Raymond


    Autonomous rock image classification can enhance the capability of robots for geological detection and enlarge the scientific returns, both in investigation on Earth and planetary surface exploration on Mars. Since rock textural images are usually inhomogeneous and manually hand-crafting features is not always reliable, we propose an unsupervised feature learning method to autonomously learn the feature representation for rock images. In our tests, rock image classification using the learned features shows that the learned features can outperform manually selected features. Self-taught learning is also proposed to learn the feature representation from a large database of unlabelled rock images of mixed class. The learned features can then be used repeatedly for classification of any subclass. This takes advantage of the large dataset of unlabelled rock images and learns a general feature representation for many kinds of rocks. We show experimental results supporting the feasibility of self-taught learning on rock images.

  19. Datamining the NOAO NVO Portal: Automated Image Classification (United States)

    Vaswani, Pooja; Miller, C. J.; Barg, I.; Smith, R. C.


    Image metadata describes the properties of an image and can be used for classification, e.g., galactic, extra-galactic, solar system, standard star, among others. We are developing a data mining application to automate such a classification process based on supervised learning using decision trees. We are applying this application to the NOAO NVO Portal ( The core concepts of Quinlan's C4.5 decision tree induction algorithm are used to train, build a decision tree, and generate classification rules. These rules are then used to classify previously unseen image metadata. We utilize a collection of decision trees instead of a single classifier and average the classification probabilities. The concept of ``Bagging'' was used to create the collection of classifiers. The classification algorithm also facilitates the addition of weights to the probability estimate of the classes when prior knowledge of the class distribution is known.

  20. Imaging of vascular tumors with an emphasis on ISSVA classification. (United States)

    Nozaki, Taiki; Matsusako, Masaki; Mimura, Hidefumi; Osuga, Keigo; Matsui, Mizuko; Eto, Hikaru; Ohtake, Naoyuki; Manabe, Atsushi; Kusakawa, Isao; Tsutsumi, Yoshiyuki; Nosaka, Shunsuke; Kamo, Minobu; Saida, Yukihisa


    The International Society for the Study of Vascular Anomalies (ISSVA) classification is becoming the international standard classification system for vascular tumors and vascular malformations. The ISSVA classification strictly distinguishes vascular tumors (neoplastic lesions) from vascular malformations (non-neoplastic lesions) based on whether there is a proliferation of vascular endothelial cells present, and it is an extremely useful classification system for determining therapeutic measures. For vascular tumors, it is clinically significant in terms of discriminating infantile hemangioma and rapidly involuting congenital hemangioma, which are expected to spontaneously regress, from other vascular tumors requiring treatment. Needless to say, clinical courses are important for diagnosis, and it is also important for radiologists to understand imaging findings on vascular tumors because such tumors have unique findings on diagnostic images. In this paper, vascular tumors are classified based on the ISSVA classification, and clinical and imaging findings are reviewed.

  1. Antenna Automation For NOAA Satellite Images Reception (United States)

    Rahal, W. L.; Benabadji, N.; Belbachir, A. H.


    In this paper, we present a novel, precise and efficient software tool (LAAR-TRACK) for Low Earth Orbit (LEO) Satellites orbit determination. It's based on using orbital elements, which are given by the NORAD (North American Aerospace Defence) by taking into considerations orbital perturbations due to the atmospheric drag, the influence of the moon and the sun and the geopotential field. The LAAR-TRACK gives the azimuth and the elevation that must have the antenna for pointing in real time the LEO satellites. This software is loaded on a computer directly connected, via the parallel port, to the tracking interface that we have developed, and which will be detailed in this paper. By this way the antenna can be automatically directed for receiving NOAA (National Oceanic and Atmospheric Administration) HRPT (High Resolution Picture Transmission) pictures.

  2. Shadow based building extraction from single satellite image (United States)

    Singh, Gurshamnjot; Jouppi, Mark; Zhang, Zhuoran; Zakhor, Avideh


    Automatic building extraction in satellite imagery is an important problem. Existing approaches typically involve stereo processing two or more satellite views of the same region. In this paper, we use shadow analysis coupled with line segment detection and texture segmentation to construct rectangular building approximations from a single satellite image. In addition, we extract building heights to construct a rectilinear height profile for a single region. We characterize the performance of the system in rural and urban regions of Jordan, Philippines, and Australia and demonstrate a detection rate of 76.2 - 86.1% and a false alarm rate of 26.5 - 40.1%.

  3. Entropy-Based Block Processing for Satellite Image Registration

    Directory of Open Access Journals (Sweden)

    Ikhyun Lee


    Full Text Available Image registration is an important task in many computer vision applications such as fusion systems, 3D shape recovery and earth observation. Particularly, registering satellite images is challenging and time-consuming due to limited resources and large image size. In such scenario, state-of-the-art image registration methods such as scale-invariant feature transform (SIFT may not be suitable due to high processing time. In this paper, we propose an algorithm based on block processing via entropy to register satellite images. The performance of the proposed method is evaluated using different real images. The comparative analysis shows that it not only reduces the processing time but also enhances the accuracy.

  4. Automatic Matching of High Resolution Satellite Images Based on RFM

    Directory of Open Access Journals (Sweden)

    JI Shunping


    Full Text Available A matching method for high resolution satellite images based on RFM is presented.Firstly,the RFM parameters are used to predict the initial parallax of corresponding points and the prediction accuracy is analyzed.Secondly,the approximate epipolar equation is constructed based on projection tracking and its accuracy is analyzed.Thirdly,approximate 1D image matching is executed on pyramid images and least square matching on base images.At last RANSAC is imbedded to eliminate mis-matching points and matching results are obtained.Test results verified the method more robust and with higher matching rate,compared to 2D gray correlation method and the popular SIFT matching method,and the method preferably solved the question of high resolution satellite image matching with different stereo model,different time and large rotation images.

  5. Improving settlement type classification of aerial images

    CSIR Research Space (South Africa)

    Mdakane, L


    Full Text Available (multitemporal imagery) tend to exhibit pronounced viewing- and illumination geometry effects, which result in a poor generalization performance in settlement type classification tasks. The study investigated the influence of contrast in settlement type...

  6. Rooftop Rainwater Harvesting for Mombasa: Scenario Development with Image Classification and Water Resources Simulation

    Directory of Open Access Journals (Sweden)

    Robert O. Ojwang


    Full Text Available Mombasa faces severe water scarcity problems. The existing supply is unable to satisfy the demand. This article demonstrates the combination of satellite image analysis and modelling as tools for the development of an urban rainwater harvesting policy. For developing a sustainable remedy policy, rooftop rainwater harvesting (RRWH strategies were implemented into the water supply and demand model WEAP (Water Evaluation and Planning System. Roof areas were detected using supervised image classification. Future population growth, improved living standards, and climate change predictions until 2035 were combined with four management strategies. Image classification techniques were able to detect roof areas with acceptable accuracy. The simulated annual yield of RRWH ranged from 2.3 to 23 million cubic meters (MCM depending on the extent of the roof area. Apart from potential RRWH, additional sources of water are required for full demand coverage.

  7. Image Analysis and Classification Based on Soil Strength (United States)


    Based on Soil Strength Co ld R eg io ns R es ea rc h an d En gi ne er in g La bo ra to ry Ariana M. Sopher, Sally A. Shoop, Jesse M...delineation, forestry, geology , and landslide potential. However, image classification for physical properties of surface soils, such as strength or...wetland delineation, forestry, geology , and landslide potential. However, image classification for physical properties of surface soils, such as

  8. Exploiting Sparsity in Hyperspectral Image Classification via Graphical Models (United States)


    Tang, “Boosting the tree augmented naive Bayes clas- sifier,” in Proc. Intell. Data Eng. Automated Learn., Lecture Notes in Computer Science, 2004...advance in hyperspectral image (HSI) classification relies on the observation that the spectral signature of a pixel can be represented by a sparse...significant recent advance in hyperspectral image (HSI) classification relies on the observation that the spectral signature of a pixel can be represented by a

  9. Land cover mapping based on random forest classification of multitemporal spectral and thermal images. (United States)

    Eisavi, Vahid; Homayouni, Saeid; Yazdi, Ahmad Maleknezhad; Alimohammadi, Abbas


    Thematic mapping of complex landscapes, with various phenological patterns from satellite imagery, is a particularly challenging task. However, supplementary information, such as multitemporal data and/or land surface temperature (LST), has the potential to improve the land cover classification accuracy and efficiency. In this paper, in order to map land covers, we evaluated the potential of multitemporal Landsat 8's spectral and thermal imageries using a random forest (RF) classifier. We used a grid search approach based on the out-of-bag (OOB) estimate of error to optimize the RF parameters. Four different scenarios were considered in this research: (1) RF classification of multitemporal spectral images, (2) RF classification of multitemporal LST images, (3) RF classification of all multitemporal LST and spectral images, and (4) RF classification of selected important or optimum features. The study area in this research was Naghadeh city and its surrounding region, located in West Azerbaijan Province, northwest of Iran. The overall accuracies of first, second, third, and fourth scenarios were equal to 86.48, 82.26, 90.63, and 91.82%, respectively. The quantitative assessments of the results demonstrated that the most important or optimum features increase the class separability, while the spectral and thermal features produced a more moderate increase in the land cover mapping accuracy. In addition, the contribution of the multitemporal thermal information led to a considerable increase in the user and producer accuracies of classes with a rapid temporal change behavior, such as crops and vegetation.

  10. Extreme learning machine and adaptive sparse representation for image classification. (United States)

    Cao, Jiuwen; Zhang, Kai; Luo, Minxia; Yin, Chun; Lai, Xiaoping


    Recent research has shown the speed advantage of extreme learning machine (ELM) and the accuracy advantage of sparse representation classification (SRC) in the area of image classification. Those two methods, however, have their respective drawbacks, e.g., in general, ELM is known to be less robust to noise while SRC is known to be time-consuming. Consequently, ELM and SRC complement each other in computational complexity and classification accuracy. In order to unify such mutual complementarity and thus further enhance the classification performance, we propose an efficient hybrid classifier to exploit the advantages of ELM and SRC in this paper. More precisely, the proposed classifier consists of two stages: first, an ELM network is trained by supervised learning. Second, a discriminative criterion about the reliability of the obtained ELM output is adopted to decide whether the query image can be correctly classified or not. If the output is reliable, the classification will be performed by ELM; otherwise the query image will be fed to SRC. Meanwhile, in the stage of SRC, a sub-dictionary that is adaptive to the query image instead of the entire dictionary is extracted via the ELM output. The computational burden of SRC thus can be reduced. Extensive experiments on handwritten digit classification, landmark recognition and face recognition demonstrate that the proposed hybrid classifier outperforms ELM and SRC in classification accuracy with outstanding computational efficiency. Copyright © 2016 Elsevier Ltd. All rights reserved.

  11. Performance Evaluation of Machine Learning Algorithms for Urban Pattern Recognition from Multi-spectral Satellite Images

    Directory of Open Access Journals (Sweden)

    Marc Wieland


    Full Text Available In this study, a classification and performance evaluation framework for the recognition of urban patterns in medium (Landsat ETM, TM and MSS and very high resolution (WorldView-2, Quickbird, Ikonos multi-spectral satellite images is presented. The study aims at exploring the potential of machine learning algorithms in the context of an object-based image analysis and to thoroughly test the algorithm’s performance under varying conditions to optimize their usage for urban pattern recognition tasks. Four classification algorithms, Normal Bayes, K Nearest Neighbors, Random Trees and Support Vector Machines, which represent different concepts in machine learning (probabilistic, nearest neighbor, tree-based, function-based, have been selected and implemented on a free and open-source basis. Particular focus is given to assess the generalization ability of machine learning algorithms and the transferability of trained learning machines between different image types and image scenes. Moreover, the influence of the number and choice of training data, the influence of the size and composition of the feature vector and the effect of image segmentation on the classification accuracy is evaluated.

  12. Smoothing of Fused Spectral Consistent Satellite Images

    DEFF Research Database (Denmark)

    Sveinsson, Johannes; Aanæs, Henrik; Benediktsson, Jon Atli


    Several widely used methods have been proposed for fusing high resolution panchromatic data and lower resolution multi-channel data. However, many of these methods fail to maintain spectral consistency of the fused high resolution image, which is of high importance to many of the applications based...... in a statistically meaningful way. The fusion method was called spectral consistent panshapen- ing (SC) and it was shown that spectral consistency was a direct consequence of imaging physics and hence guaranteed by the SCP. In this paper exploit this framework and investigate two smoothing methods of the fused image...... obtain by SCP. The first smoothing method is based on Markov random field (MRF) model, while the second method uses wavelet domain hidden Markov models (HMM) for smoothing of the SCP fused image....

  13. Influence of shadow removal on image classification in riverine environments. (United States)

    Filippi, Anthony M; Güneralp, İnci


    Shadows in remote-sensor images can yield marked errors in classification of riverine environments. We propose use of a modified shadow-removal algorithm as a preprocessing step for remote-sensing image classification of riverine landscapes. To accommodate characterization of spatially complex river features in the image, we investigate an illumination suppression-based shadow-removal algorithm, modified to include a user-defined tiling approach. We quantitatively evaluate the influence of shadow removal from aerial photography on classification accuracy as such studies are currently lacking. Experimental results demonstrate that this modified shadow-removal method significantly increases classification accuracy and improves detection of small river channels partially obscured by shadow.

  14. Hyperspectral image classification based on filtering: a comparative study (United States)

    Cao, Xianghai; Ji, Beibei; Ji, Yamei; Wang, Lin; Jiao, Licheng


    The classification of hyperspectral images benefits greatly from integration of spectral information and spatial context. There have been many means to incorporate spatial information into the classification, such as the Markov random field, extended morphological profiles, and segmentation-based methods. Recently, spatial filtering was introduced to improve the classification accuracy of hyperspectral images. Compared with other spectral-spatial algorithms, spatial filtering is simple and easy to implement. This advantage makes it suitable for practical applications. However, spatial filtering has not been given enough attention. A comprehensive comparative study of spatial filtering is conducted. Specifically, 10 kinds of filters are used to smooth the hyperspectral images and the classified maps, respectively. The experimental results show that most filtering-based classification methods perform well with high efficiency.

  15. Image Dodging Algorithm for GF-1 Satellite WFV Imagery

    Directory of Open Access Journals (Sweden)

    HAN Jie


    Full Text Available Image dodging method is one of the important processes that determines whether the mosaicking image can be used for remote sensing quantitative application. GF-1 satellite is the first satellite in CHEOS (Chinese high-resolution earth observation system. WFV multispectral sensor is one of the instruments onboard GF-1 satellite which consist of four cameras to mosaic imaging. According to the characteristics of WFV sensor, this paper proposes an image dodging algorithm based on cross/inter-radiometric calibration method. First, the traditional cross calibration method is applied to obtain the calibration coefficients of one WFV camera. Then statistical analysis and simulation methods are adopted to build the correlation models of DN and TOA (top of atmosphere radiances between adjacent cameras. The proposed method can not only accomplish the radiation performance transfer, but also can fulfill the image dodging. The experimental results show the cross/inter-radiometric calibration coefficients in this paper can effectively eliminate the radiation inconsistency problem of the adjacent camera image which realizes the image dodging. So our proposed dodging method can provide an important reference for other similar sensor in future.

  16. ROI image compression algorithm for reconnaissance satellite systems (United States)

    Tian, Xin; Wang, Chun-Ming; Tan, Yi-Hua; Tian, Jin-Wen


    The visual effect is an important fact in the coding algorithm. So the saliency of visual attention(SVA) can be used to determine the region of interest(ROI) in the ROI image coding. A novel SVA based ROI(SVA-ROI) image coding scheme is presented for the reconnaissance satellite systems. As the SVA of the original image and reconstructed image are usually the same, the same ROI can be automatically determined in the encoder and decoder with the SVA. Then the ROI side information is no need to be transmitted and the compression efficiency can be improved. Experimental results have demonstrated that SVA-ROI has better visual effect than the similar algorithms, which will be suitable for the reconnaissance satellite systems.

  17. 3-D Reconstruction From Satellite Images

    DEFF Research Database (Denmark)

    Denver, Troelz


    The aim of this project has been to implement a software system, that is able to create a 3-D reconstruction from two or more 2-D photographic images made from different positions. The height is determined from the disparity difference of the images. The general purpose of the system is mapping o......, where various methods have been tested in order to optimize the performance. The match results are used in the reconstruction part to establish a 3-D digital representation and finally, different presentation forms are discussed....

  18. GAN-Assisted Two-Stream Neural Network for High-Resolution Remote Sensing Image Classification

    Directory of Open Access Journals (Sweden)

    Yiting Tao


    Full Text Available Using deep learning to improve the capabilities of high-resolution satellite images has emerged recently as an important topic in automatic classification. Deep networks track hierarchical high-level features to identify objects; however, enhancing the classification accuracy from low-level features is often disregarded. We therefore proposed a two-stream deep-learning neural network strategy, with a main stream utilizing fine spatial-resolution panchromatic images to retain low-level information under a supervised residual network structure. An auxiliary line employed an unsupervised net to extract high-level abstract and discriminative features from multispectral images to supplement the spectral information in the main stream. Various feature extraction types from the neural network were selected and jointed in the novel net, as the combined high- and low-level features could provide a superior solution to image classification. In traditional convolutional neural networks, increased network depth might not influence the network performance perceptibly; however, we introduced a residual neural network to develop the expressive ability of the deeper net, increasing the role of net depth in feature extraction. To enhance feature robustness, we proposed a novel consolidation part in feature extraction. An adversarial net improved the feature extraction capabilities and aided digging the inherent and discriminative features from data, with increased extraction efficacy. Tests on satellite images indicated the high overall accuracy of our novel net, verifying that net depth or number of convolution kernels affected the classification capability. Various comparative tests proved the structural rationality for our two-stream structure.

  19. Very high resolution satellite data: New challenges in image analysis

    Digital Repository Service at National Institute of Oceanography (India)

    Sathe, P.V.; Muraleedharan, P.M.

    Early years of coming century will see a large number of satellites with very high spatial resolution reaching beyond 1 m in the visible range of electromagnetic spectrum. Such images will come very close to giving a ground-based view of a terrain...

  20. Lung cancer classification using neural networks for CT images. (United States)

    Kuruvilla, Jinsa; Gunavathi, K


    Early detection of cancer is the most promising way to enhance a patient's chance for survival. This paper presents a computer aided classification method in computed tomography (CT) images of lungs developed using artificial neural network. The entire lung is segmented from the CT images and the parameters are calculated from the segmented image. The statistical parameters like mean, standard deviation, skewness, kurtosis, fifth central moment and sixth central moment are used for classification. The classification process is done by feed forward and feed forward back propagation neural networks. Compared to feed forward networks the feed forward back propagation network gives better classification. The parameter skewness gives the maximum classification accuracy. Among the already available thirteen training functions of back propagation neural network, the Traingdx function gives the maximum classification accuracy of 91.1%. Two new training functions are proposed in this paper. The results show that the proposed training function 1 gives an accuracy of 93.3%, specificity of 100% and sensitivity of 91.4% and a mean square error of 0.998. The proposed training function 2 gives a classification accuracy of 93.3% and minimum mean square error of 0.0942. Copyright © 2013 Elsevier Ireland Ltd. All rights reserved.

  1. Deep Learning for Tumor Classification in Imaging Mass Spectrometry. (United States)

    Behrmann, Jens; Etmann, Christian; Boskamp, Tobias; Casadonte, Rita; Kriegsmann, Jörg; Maass, Peter


    Tumor classification using Imaging Mass Spectrometry (IMS) data has a high potential for future applications in pathology. Due to the complexity and size of the data, automated feature extraction and classification steps are required to fully process the data. Since mass spectra exhibit certain structural similarities to image data, deep learning may offer a promising strategy for classification of IMS data as it has been successfully applied to image classification. Methodologically, we propose an adapted architecture based on deep convolutional networks to handle the characteristics of mass spectrometry data, as well as a strategy to interpret the learned model in the spectral domain based on a sensitivity analysis. The proposed methods are evaluated on two algorithmically challenging tumor classification tasks and compared to a baseline approach. Competitiveness of the proposed methods are shown on both tasks by studying the performance via cross-validation. Moreover, the learned models are analyzed by the proposed sensitivity analysis revealing biologically plausible effects as well as confounding factors of the considered tasks. Thus, this study may serve as a starting point for further development of deep learning approaches in IMS classification tasks., Supplementary data are available at Bioinformatics online.

  2. Efficient temporal access of satellite image data

    CSIR Research Space (South Africa)

    Bachoo, A


    Full Text Available A single tile from the gridded MODIS products, spanning a region of interest of approximately 10° by 10°, is stored as an image containing close to six million pixels, with data in multiple spectral bands for each pixel. Time series analyses...

  3. Classifications of objects on hyperspectral images

    DEFF Research Database (Denmark)

    Kucheryavskiy, Sergey

    Hyperspectral imaging is a modern analytical technique combining benefits of digital imaging and vibrational spectroscopy. It allows to reveal and visualise spatial distribution of various chemical components. In a hyperspectral image every pixel is a spectrum (usually VNIR, SWIR or Raman...

  4. Performance indicators for the statistical evaluation of digital image classifications

    NARCIS (Netherlands)

    Urso, D' G.; Menenti, M.


    A statistical procedure is proposed to evaluate the algorithms for the numerical classification of images. The approach is based on the derivation of performance indicators from measurements of signature separability and thresholding analysis. Although these measurements are not new in image

  5. Image Classification with the Fisher Vector: Theory and Practice

    NARCIS (Netherlands)

    Sánchez, J.; Perronnin, F.; Mensink, T.; Verbeek, J.


    A standard approach to describe an image for classification and retrieval purposes is to extract a set of local patch descriptors, encode them into a high dimensional vector and pool them into an image-level signature. The most common patch encoding strategy consists in quantizing the local

  6. Improvements in Sample Selection Methods for Image Classification

    Directory of Open Access Journals (Sweden)

    Thales Sehn Körting


    Full Text Available Traditional image classification algorithms are mainly divided into unsupervised and supervised paradigms. In the first paradigm, algorithms are designed to automatically estimate the classes’ distributions in the feature space. The second paradigm depends on the knowledge of a domain expert to identify representative examples from the image to be used for estimating the classification model. Recent improvements in human-computer interaction (HCI enable the construction of more intuitive graphic user interfaces (GUIs to help users obtain desired results. In remote sensing image classification, GUIs still need advancements. In this work, we describe our efforts to develop an improved GUI for selecting the representative samples needed to estimate the classification model. The idea is to identify changes in the common strategies for sample selection to create a user-driven sample selection, which focuses on different views of each sample, and to help domain experts identify explicit classification rules, which is a well-established technique in geographic object-based image analysis (GEOBIA. We also propose the use of the well-known nearest neighbor algorithm to identify similar samples and accelerate the classification.

  7. Hyperspectral image classification based on NMF Features Selection Method (United States)

    Abe, Bolanle T.; Jordaan, J. A.


    Hyperspectral instruments are capable of collecting hundreds of images corresponding to wavelength channels for the same area on the earth surface. Due to the huge number of features (bands) in hyperspectral imagery, land cover classification procedures are computationally expensive and pose a problem known as the curse of dimensionality. In addition, higher correlation among contiguous bands increases the redundancy within the bands. Hence, dimension reduction of hyperspectral data is very crucial so as to obtain good classification accuracy results. This paper presents a new feature selection technique. Non-negative Matrix Factorization (NMF) algorithm is proposed to obtain reduced relevant features in the input domain of each class label. This aimed to reduce classification error and dimensionality of classification challenges. Indiana pines of the Northwest Indiana dataset is used to evaluate the performance of the proposed method through experiments of features selection and classification. The Waikato Environment for Knowledge Analysis (WEKA) data mining framework is selected as a tool to implement the classification using Support Vector Machines and Neural Network. The selected features subsets are subjected to land cover classification to investigate the performance of the classifiers and how the features size affects classification accuracy. Results obtained shows that performances of the classifiers are significant. The study makes a positive contribution to the problems of hyperspectral imagery by exploring NMF, SVMs and NN to improve classification accuracy. The performances of the classifiers are valuable for decision maker to consider tradeoffs in method accuracy versus method complexity.

  8. Automatic ship target classification based on aerial images (United States)

    Lan, Jinhui; Wan, Lili


    As the important reconnaissance and offensive weapon in future battlefield, Micro Aerial Vehicle (MAV) is applied more and more widely in civil and military field. In the sea battlefield, ship classification applied to MAV could effectively realize signals collection, force protection and strike to ship targets. At present, methods of ship classification are mostly based on signals from radar, infrared or ultrasonic. However, because of large volume and complex equipments, these methods can't meet the requirement of MAV. Thus, ship classification based on visible sensor is chosen and it could solve volume and weight limits of MAV. In order to realize ship classification in MAV, ship classification based on aerial images is first proposed and an effective robust algorithm for classification based on modified Zernike moment invariants is proposed in this paper. The task of classification is that the ships are classified into two categories, aircraft carrier and chaser. The experimental results show that the correct classification rate is more than 92% and the algorithm proposed is effective to solve classification problem for ship targets in MAV.

  9. An Image Matching Algorithm Integrating Global SRTM and Image Segmentation for Multi-Source Satellite Imagery

    Directory of Open Access Journals (Sweden)

    Xiao Ling


    Full Text Available This paper presents a novel image matching method for multi-source satellite images, which integrates global Shuttle Radar Topography Mission (SRTM data and image segmentation to achieve robust and numerous correspondences. This method first generates the epipolar lines as a geometric constraint assisted by global SRTM data, after which the seed points are selected and matched. To produce more reliable matching results, a region segmentation-based matching propagation is proposed in this paper, whereby the region segmentations are extracted by image segmentation and are considered to be a spatial constraint. Moreover, a similarity measure integrating Distance, Angle and Normalized Cross-Correlation (DANCC, which considers geometric similarity and radiometric similarity, is introduced to find the optimal correspondences. Experiments using typical satellite images acquired from Resources Satellite-3 (ZY-3, Mapping Satellite-1, SPOT-5 and Google Earth demonstrated that the proposed method is able to produce reliable and accurate matching results.

  10. Citizen science land cover classification based on ground and satellite imagery: Case study Day River in Vietnam (United States)

    Nguyen, Son Tung; Minkman, Ellen; Rutten, Martine


    Citizen science is being increasingly used in the context of environmental research, thus there are needs to evaluate cognitive ability of humans in classifying environmental features. With the focus on land cover, this study explores the extent to which citizen science can be applied in sensing and measuring the environment that contribute to the creation and validation of land cover data. The Day Basin in Vietnam was selected to be the study area. Different methods to examine humans' ability to classify land cover were implemented using different information sources: ground based photos - satellite images - field observation and investigation. Most of the participants were solicited from local people and/or volunteers. Results show that across methods and sources of information, there are similar patterns of agreement and disagreement on land cover classes among participants. Understanding these patterns is critical to create a solid basis for implementing human sensors in earth observation. Keywords: Land cover, classification, citizen science, Landsat 8

  11. Combined Use of Multi-Temporal Optical and Radar Satellite Images for Grassland Monitoring

    Directory of Open Access Journals (Sweden)

    Pauline Dusseux


    Full Text Available The aim of this study was to assess the ability of optical images, SAR (Synthetic Aperture Radar images and the combination of both types of data to discriminate between grasslands and crops in agricultural areas where cloud cover is very high most of the time, which restricts the use of visible and near-infrared satellite data. We compared the performances of variables extracted from four optical and five SAR satellite images with high/very high spatial resolutions acquired during the growing season. A vegetation index, namely the NDVI (Normalized Difference Vegetation Index, and two biophysical variables, the LAI (Leaf Area Index and the fCOVER (fraction of Vegetation Cover were computed using optical time series and polarization (HH, VV, HV, VH. The polarization ratio and polarimetric decomposition (Freeman–Durden and Cloude–Pottier were calculated using SAR time series. Then, variables derived from optical, SAR and both types of remotely-sensed data were successively classified using the Support Vector Machine (SVM technique. The results show that the classification accuracy of SAR variables is higher than those using optical data (0.98 compared to 0.81. They also highlight that the combination of optical and SAR time series data is of prime interest to discriminate grasslands from crops, allowing an improved classification accuracy.

  12. Response Classification Images in Vernier Acuity (United States)

    Ahumada, Albert J., Jr.; Beard, B. L.; Ellis, Stephen R. (Technical Monitor)


    Orientation selective and local sign mechanisms have been proposed as the basis for vernier acuity judgments. Linear image features contributing to discrimination can be determined for a two choice task by adding external noise to the images and then averaging the noises separately for the four types of stimulus/response trials. This method is applied to a vernier acuity task with different spatial separations to compare the predictions of the two theories. Three well-practiced observers were presented around 5000 trials of a vernier stimulus consisting of two dark horizontal lines (5 min by 0.3 min) within additive low-contrast white noise. Two spatial separations were tested, abutting and a 10 min horizontal separation. The task was to determine whether the target lines were aligned or vertically offset. The noises were averaged separately for the four stimulus/response trial types (e.g., stimulus = offset, response = aligned). The sum of the two 'not aligned' images was then subtracted from the sum of the 'aligned' images to obtain an overall image. Spatially smoothed images were quantized according to expected variability in the smoothed images to allow estimation of the statistical significance of image features. The response images from the 10 min separation condition are consistent with the local sign theory, having the appearance of two linear operators measuring vertical position with opposite sign. The images from the abutting stimulus have the same appearance with the two operators closer together. The image predicted by an oriented filter model is similar, but has its greatest weight in the abutting region, while the response images fall to nonsignificance there. The response correlation image method, previously demonstrated for letter discrimination, clarifies the features used in vernier acuity.

  13. Real-Time Protein Crystallization Image Acquisition and Classification System (United States)

    Sigdel, Madhav; Pusey, Marc L.; Aygun, Ramazan S.


    In this paper, we describe the design and implementation of a stand-alone real-time system for protein crystallization image acquisition and classification with a goal to assist crystallographers in scoring crystallization trials. In-house assembled fluorescence microscopy system is built for image acquisition. The images are classified into three categories as non-crystals, likely leads, and crystals. Image classification consists of two main steps – image feature extraction and application of classification based on multilayer perceptron (MLP) neural networks. Our feature extraction involves applying multiple thresholding techniques, identifying high intensity regions (blobs), and generating intensity and blob features to obtain a 45-dimensional feature vector per image. To reduce the risk of missing crystals, we introduce a max-class ensemble classifier which applies multiple classifiers and chooses the highest score (or class). We performed our experiments on 2250 images consisting 67% non-crystal, 18% likely leads, and 15% clear crystal images and tested our results using 10-fold cross validation. Our results demonstrate that the method is very efficient (< 3 seconds to process and classify an image) and has comparatively high accuracy. Our system only misses 1.2% of the crystals (classified as non-crystals) most likely due to low illumination or out of focus image capture and has an overall accuracy of 88%. PMID:24532991

  14. Modulation Classification of Satellite Communication Signals Using Cumulants and Neural Networks (United States)

    Smith, Aaron; Evans, Michael; Downey, Joseph


    National Aeronautics and Space Administration (NASA)'s future communication architecture is evaluating cognitive technologies and increased system intelligence. These technologies are expected to reduce the operational complexity of the network, increase science data return, and reduce interference to self and others. In order to increase situational awareness, signal classification algorithms could be applied to identify users and distinguish sources of interference. A significant amount of previous work has been done in the area of automatic signal classification for military and commercial applications. As a preliminary step, we seek to develop a system with the ability to discern signals typically encountered in satellite communication. Proposed is an automatic modulation classifier which utilizes higher order statistics (cumulants) and an estimate of the signal-to-noise ratio. These features are extracted from baseband symbols and then processed by a neural network for classification. The modulation types considered are phase-shift keying (PSK), amplitude and phase-shift keying (APSK),and quadrature amplitude modulation (QAM). Physical layer properties specific to the Digital Video Broadcasting - Satellite- Second Generation (DVB-S2) standard, such as pilots and variable ring ratios, are also considered. This paper will provide simulation results of a candidate modulation classifier, and performance will be evaluated over a range of signal-to-noise ratios, frequency offsets, and nonlinear amplifier distortions.


    Roy, Snehashis; Carass, Aaron; Bazin, Pierre-Louis; Prince, Jerry L.


    Tissue classification algorithms developed for magnetic resonance images commonly assume a Gaussian model on the statistics of noise in the image. While this is approximately true for voxels having large intensities, it is less true as the underlying intensity becomes smaller. In this paper, the Gaussian model is replaced with a Rician model, which is a better approximation to the observed signal. A new classification algorithm based on a finite mixture model of Rician signals is presented wherein the expectation maximization algorithm is used to find the joint maximum likelihood estimates of the unknown mixture parameters. Improved accuracy of tissue classification is demonstrated on several sample data sets. It is also shown that classification repeatability for the same subject under different MR acquisitions is improved using the new method. PMID:20126426


    Directory of Open Access Journals (Sweden)

    P. Zhong


    Full Text Available In recent years, researches in remote sensing demonstrated that deep architectures with multiple layers can potentially extract abstract and invariant features for better hyperspectral image classification. Since the usual real-world hyperspectral image classification task cannot provide enough training samples for a supervised deep model, such as convolutional neural networks (CNNs, this work turns to investigate the deep belief networks (DBNs, which allow unsupervised training. The DBN trained over limited training samples usually has many “dead” (never responding or “potential over-tolerant” (always responding latent factors (neurons, which decrease the DBN’s description ability and thus finally decrease the hyperspectral image classification performance. This work proposes a new diversified DBN through introducing a diversity promoting prior over the latent factors during the DBN pre-training and fine-tuning procedures. The diversity promoting prior in the training procedures will encourage the latent factors to be uncorrelated, such that each latent factor focuses on modelling unique information, and all factors will be summed up to capture a large proportion of information and thus increase description ability and classification performance of the diversified DBNs. The proposed method was evaluated over the well-known real-world hyperspectral image dataset. The experiments demonstrate that the diversified DBNs can obtain much better results than original DBNs and comparable or even better performances compared with other recent hyperspectral image classification methods.

  17. Stellar Source Selections for Image Validation of Earth Observation Satellite

    Directory of Open Access Journals (Sweden)

    Jiwoong Yu


    Full Text Available A method of stellar source selection for validating the quality of image is investigated for a low Earth orbit optical remote sensing satellite. Image performance of the optical payload needs to be validated after its launch into orbit. The stellar sources are ideal source points that can be used to validate the quality of optical images. For the image validation, stellar sources should be the brightest as possible in the charge-coupled device dynamic range. The time delayed and integration technique, which is used to observe the ground, is also performed to observe the selected stars. The relations between the incident radiance at aperture and V magnitude of a star are established using Gunn & Stryker's star catalogue of spectrum. Applying this result, an appropriate image performance index is determined, and suitable stars and areas of the sky scene are selected for the optical payload on a remote sensing satellite to observe. The result of this research can be utilized to validate the quality of optical payload of a satellite in orbit.

  18. Classification of maize kernels using NIR hyperspectral imaging

    DEFF Research Database (Denmark)

    Williams, Paul; Kucheryavskiy, Sergey V.


    NIR hyperspectral imaging was evaluated to classify maize kernels of three hardness categories: hard, medium and soft. Two approaches, pixel-wise and object-wise, were investigated to group kernels according to hardness. The pixel-wise classification assigned a class to every pixel from individua...... and specificity of 0.95 and 0.93). Both feature extraction methods can be recommended for classification of maize kernels on production scale....

  19. Improved image classification with neural networks by fusing multispectral signatures with topological data (United States)

    Harston, Craig; Schumacher, Chris


    Automated schemes are needed to classify multispectral remotely sensed data. Human intelligence is often required to correctly interpret images from satellites and aircraft. Humans suceed because they use various types of cues about a scene to accurately define the contents of the image. Consequently, it follows that computer techniques that integrate and use different types of information would perform better than single source approaches. This research illustrated that multispectral signatures and topographical information could be used in concert. Significantly, this dual source tactic classified a remotely sensed image better than the multispectral classification alone. These classifications were accomplished by fusing spectral signatures with topographical information using neural network technology. A neural network was trained to classify Landsat mulitspectral signatures. A file of georeferenced ground truth classifications were used as the training criterion. The network was trained to classify urban, agriculture, range, and forest with an accuracy of 65.7 percent. Another neural network was programmed and trained to fuse these multispectral signature results with a file of georeferenced altitude data. This topological file contained 10 levels of elevations. When this nonspectral elevation information was fused with the spectral signatures, the classifications were improved to 73.7 and 75.7 percent.

  20. Vascular anomalies in pediatric patients: updated classification, imaging, and therapy. (United States)

    Kollipara, Ramya; Odhav, Ashika; Rentas, Kenny E; Rivard, Douglas C; Lowe, Lisa H; Dinneen, Laura


    Recent advances in knowledge regarding histopathology, cause, and treatment of pediatric vascular anomalies have led to substantial changes in classification and terminology. Over the past two decades, various subspecialists have adopted a new classification system proposed by the International Society for the Study of Vascular Anomalies (ISSVA). The ISSVA classification of vascular anomalies divides vascular anomalies into two categories: vascular neoplasms and malformations. It has been widely adopted by various pediatric subspecialists, because it reliably correlates patient presentation and disease progression, with more accurate histology, diagnosis, imaging, and treatment. Copyright © 2013 Elsevier Inc. All rights reserved.

  1. Texture classification of aerial image based on PCA-NBC (United States)

    Yu, Xin; Zheng, Zhaoboa; Li, Linyi; Ye, Zhiwei


    Bayesian Networks have emerged in recent years as a powerful data mining technique for handling uncertainty in complex domains. The Bayesian Network represents the joint probability distribution and domain (or expert) knowledge in a compact way and provides a comprehensive method of representing relationships and influences among nodes (variables) with a graphical diagram. Actually, however, in the classification domain it was not paid attention to by researchers until the simplest of form of Bayesian Networks, Naive Bayes Classifier, turned up. Naive Bayes Classifier is a simple and efficient probability classification method, and has shown surprising performance in some domains, which owes to the independence assumption that makes Naive Bayes Classifier fit the classification more easily. However, the independence assumption obviously does not hold in the real world. Therefore, in order to meet the "naive" (unreal) assumption, this paper proposes a new image texture classification method of aerial images, PCA-NBC, which combines the Principal Components Analysis (PCA) and Naive Bayes Classifier (NBC). The PCA transforms the highly correlated features into statistically independent and orthogonal "features", so it is suitable to solve that problem and can lay a solid theoretic foundation in the application. One hundred and thirteen aerial images are used to evaluate the classification performance in the experiment. The experimental results demonstrate that the proposed method can cut down the number of features and computational costs and improve the accuracy during classification. In one word, the new method, PCA-NBC, is an attractive and effective method, which outperforms the Naive Bayes Classifier.

  2. Automatic segmentation of diatom images for classification

    NARCIS (Netherlands)

    Jalba, Andrei C.; Wilkinson, Michael H.F.; Roerdink, Jos B.T.M.

    A general framework for automatic segmentation of diatom images is presented. This segmentation is a critical first step in contour-based methods for automatic identification of diatoms by computerized image analysis. We review existing results, adapt popular segmentation methods to this difficult

  3. An Object-Based Image Analysis Approach for Detecting Penguin Guano in very High Spatial Resolution Satellite Images

    Directory of Open Access Journals (Sweden)

    Chandi Witharana


    Full Text Available The logistical challenges of Antarctic field work and the increasing availability of very high resolution commercial imagery have driven an interest in more efficient search and classification of remotely sensed imagery. This exploratory study employed geographic object-based analysis (GEOBIA methods to classify guano stains, indicative of chinstrap and Adélie penguin breeding areas, from very high spatial resolution (VHSR satellite imagery and closely examined the transferability of knowledge-based GEOBIA rules across different study sites focusing on the same semantic class. We systematically gauged the segmentation quality, classification accuracy, and the reproducibility of fuzzy rules. A master ruleset was developed based on one study site and it was re-tasked “without adaptation” and “with adaptation” on candidate image scenes comprising guano stains. Our results suggest that object-based methods incorporating the spectral, textural, spatial, and contextual characteristics of guano are capable of successfully detecting guano stains. Reapplication of the master ruleset on candidate scenes without modifications produced inferior classification results, while adapted rules produced comparable or superior results compared to the reference image. This work provides a road map to an operational “image-to-assessment pipeline” that will enable Antarctic wildlife researchers to seamlessly integrate VHSR imagery into on-demand penguin population census.

  4. Polarimetric SAR Image Supervised Classification Method Integrating Eigenvalues

    Directory of Open Access Journals (Sweden)

    Xing Yanxiao


    Full Text Available Since classification methods based on H/α space have the drawback of yielding poor classification results for terrains with similar scattering features, in this study, we propose a polarimetric Synthetic Aperture Radar (SAR image classification method based on eigenvalues. First, we extract eigenvalues and fit their distribution with an adaptive Gaussian mixture model. Then, using the naive Bayesian classifier, we obtain preliminary classification results. The distribution of eigenvalues in two kinds of terrains may be similar, leading to incorrect classification in the preliminary step. So, we calculate the similarity of every terrain pair, and add them to the similarity table if their similarity is greater than a given threshold. We then apply the Wishart distance-based KNN classifier to these similar pairs to obtain further classification results. We used the proposed method on both airborne and spaceborne SAR datasets, and the results show that our method can overcome the shortcoming of the H/α-based unsupervised classification method for eigenvalues usage, and produces comparable results with the Support Vector Machine (SVM-based classification method.

  5. Estimating classification images with generalized linear and additive models. (United States)

    Knoblauch, Kenneth; Maloney, Laurence T


    Conventional approaches to modeling classification image data can be described in terms of a standard linear model (LM). We show how the problem can be characterized as a Generalized Linear Model (GLM) with a Bernoulli distribution. We demonstrate via simulation that this approach is more accurate in estimating the underlying template in the absence of internal noise. With increasing internal noise, however, the advantage of the GLM over the LM decreases and GLM is no more accurate than LM. We then introduce the Generalized Additive Model (GAM), an extension of GLM that can be used to estimate smooth classification images adaptively. We show that this approach is more robust to the presence of internal noise, and finally, we demonstrate that GAM is readily adapted to estimation of higher order (nonlinear) classification images and to testing their significance.

  6. Automatic medical X-ray image classification using annotation. (United States)

    Zare, Mohammad Reza; Mueen, Ahmed; Seng, Woo Chaw


    The demand for automatically classification of medical X-ray images is rising faster than ever. In this paper, an approach is presented to gain high accuracy rate for those classes of medical database with high ratio of intraclass variability and interclass similarities. The classification framework was constructed via annotation using the following three techniques: annotation by binary classification, annotation by probabilistic latent semantic analysis, and annotation using top similar images. Next, final annotation was constructed by applying ranking similarity on annotated keywords made by each technique. The final annotation keywords were then divided into three levels according to the body region, specific bone structure in body region as well as imaging direction. Different weights were given to each level of the keywords; they are then used to calculate the weightage for each category of medical images based on their ground truth annotation. The weightage computed from the generated annotation of query image was compared with the weightage of each category of medical images, and then the query image would be assigned to the category with closest weightage to the query image. The average accuracy rate reported is 87.5 %.

  7. Enhancement of thematic mapper satellite images for geological mapping of the Cho Dien area, Northern Vietnam (United States)

    Won-In, Krit; Charusiri, Punya


    Information available from the earth science image processing package (ESIPP) software program was applied to enhance the satellite image data of the Cho Dien area, northern Vietnam. The area with dense vegetation covers is dominated by several small Zn-Pb prospects in middle Paleozoic limestone units. Interpretation of satellite image data using the digital enhancement ESIPP program, forms the prime objective of this study, which is to improve the image quality and visual interpretation of regional geology, lineament and structural geology. Thematic mapper of bands 7, 5 and 4 with the false-color composites: blue, green and red, respectively, are considered to be the most appropriate for geologic interpretation. Dark pixel correction is carried out prior to other enhancement analyses which include high-pass filtering, albedo correction, image classification, principle component analysis (PCA) and band ratios. High-pass filtering enhancement is considered to be the most suitable approach for lineament analysis. Albedo is good for differentiating lithology, and image classification is also successfully used for lineament interpretation and discrimination of lithologies but is regarded not better than high-pass filtering and albedo. PCA and ratio of band enhancements are considered not good because there are many disturbed and excavated land areas such as abandoned and current open pits in the concerned area. The result of Landsat interpretation indicate that most lineament structures developed in a roughly N-trending anticlinal structure are in NE-, E- and N-trends. Minor lineaments are in roughly NW-trend, and cross-cutting the NE- and E-trends. Interpretation from enhanced Landsat information also fits very well with field evidences. The interpreted map is slightly different from those of the previous mapping works, particularly with respect to detailed lithological boundaries.

  8. Protein crystallization image classification with elastic net (United States)

    Hung, Jeffrey; Collins, John; Weldetsion, Mehari; Newland, Oliver; Chiang, Eric; Guerrero, Steve; Okada, Kazunori


    Protein crystallization plays a crucial role in pharmaceutical research by supporting the investigation of a protein's molecular structure through X-ray diffraction of its crystal. Due to the rare occurrence of crystals, images must be manually inspected, a laborious process. We develop a solution incorporating a regularized, logistic regression model for automatically evaluating these images. Standard image features, such as shape context, Gabor filters and Fourier transforms, are first extracted to represent the heterogeneous appearance of our images. Then the proposed solution utilizes Elastic Net to select relevant features. Its L1-regularization mitigates the effects of our large dataset, and its L2- regularization ensures proper operation when the feature number exceeds the sample number. A two-tier cascade classifier based on naïve Bayes and random forest algorithms categorized the images. In order to validate the proposed method, we experimentally compare it with naïve Bayes, linear discriminant analysis, random forest, and their two-tier cascade classifiers, by 10-fold cross validation. Our experimental results demonstrate a 3-category accuracy of 74%, outperforming other models. In addition, Elastic Net better reduces the false negatives responsible for a high, domain specific risk. To the best of our knowledge, this is the first attempt to apply Elastic Net to classifying protein crystallization images. Performance measured on a large pharmaceutical dataset also fared well in comparison with those presented in the previous studies, while the reduction of the high-risk false negatives is promising.

  9. High-Resolution Imaging of Asteroids/Satellites with AO (United States)

    Merline, William


    We propose to make high-resolution observations of asteroids using AO, to measure size, shape, and pole position (spin vectors), and/or to search for satellites. We have demonstrated that AO imaging allows determination of the pole/dimensions in 1 or 2 nights on a single target, rather than the years of observations with lightcurve inversion techniques that only yield poles and axial ratios, not true dimensions. Our new technique (KOALA) combines AO imaging with lightcurve and occultation data for optimum size/shape determinations. We request that LGS be available for faint targets, but using NGS AO, we will measure several large and intermediate asteroids that are favorably placed in spring/summer of 2012 for size/shape/pole. Accurately determining the volume from the often-irregular shape allows us to derive densities to much greater precision in cases where the mass is known, e.g., from the presence of a satellite. We will search several d! ozen asteroids for the presence of satellites, particularly in under-studied populations, particularly NEOs (we have recently achieved the first-ever optical image of an NEO binary [Merline et al. 2008b, IAUC 8977]). Satellites provide a real-life lab for testing collisional models. We will search for satellites around special objects at the request of lightcurve observers, and we will make a search for debris in the vicinity of Pluto, in support of the New Horizons mission. Our shape/size work requires observations over most of a full rotation period (typically several hours).

  10. Land use mapping from CBERS-2 images with open source tools by applying different classification algorithms (United States)

    Sanhouse-García, Antonio J.; Rangel-Peraza, Jesús Gabriel; Bustos-Terrones, Yaneth; García-Ferrer, Alfonso; Mesas-Carrascosa, Francisco J.


    Land cover classification is often based on different characteristics between their classes, but with great homogeneity within each one of them. This cover is obtained through field work or by mean of processing satellite images. Field work involves high costs; therefore, digital image processing techniques have become an important alternative to perform this task. However, in some developing countries and particularly in Casacoima municipality in Venezuela, there is a lack of geographic information systems due to the lack of updated information and high costs in software license acquisition. This research proposes a low cost methodology to develop thematic mapping of local land use and types of coverage in areas with scarce resources. Thematic mapping was developed from CBERS-2 images and spatial information available on the network using open source tools. The supervised classification method per pixel and per region was applied using different classification algorithms and comparing them among themselves. Classification method per pixel was based on Maxver algorithms (maximum likelihood) and Euclidean distance (minimum distance), while per region classification was based on the Bhattacharya algorithm. Satisfactory results were obtained from per region classification, where overall reliability of 83.93% and kappa index of 0.81% were observed. Maxver algorithm showed a reliability value of 73.36% and kappa index 0.69%, while Euclidean distance obtained values of 67.17% and 0.61% for reliability and kappa index, respectively. It was demonstrated that the proposed methodology was very useful in cartographic processing and updating, which in turn serve as a support to develop management plans and land management. Hence, open source tools showed to be an economically viable alternative not only for forestry organizations, but for the general public, allowing them to develop projects in economically depressed and/or environmentally threatened areas.

  11. Classification of Architectural Heritage Images Using Deep Learning Techniques

    Directory of Open Access Journals (Sweden)

    Jose Llamas


    Full Text Available The classification of the images taken during the measurement of an architectural asset is an essential task within the digital documentation of cultural heritage. A large number of images are usually handled, so their classification is a tedious task (and therefore prone to errors and habitually consumes a lot of time. The availability of automatic techniques to facilitate these sorting tasks would improve an important part of the digital documentation process. In addition, a correct classification of the available images allows better management and more efficient searches through specific terms, thus helping in the tasks of studying and interpreting the heritage asset in question. The main objective of this article is the application of techniques based on deep learning for the classification of images of architectural heritage, specifically through the use of convolutional neural networks. For this, the utility of training these networks from scratch or only fine tuning pre-trained networks is evaluated. All this has been applied to classifying elements of interest in images of buildings with architectural heritage value. As no datasets of this type, suitable for network training, have been located, a new dataset has been created and made available to the public. Promising results have been obtained in terms of accuracy and it is considered that the application of these techniques can contribute significantly to the digital documentation of architectural heritage.

  12. Targeting Villages for Rural Development Using Satellite Image Analysis. (United States)

    Varshney, Kush R; Chen, George H; Abelson, Brian; Nowocin, Kendall; Sakhrani, Vivek; Xu, Ling; Spatocco, Brian L


    Satellite imagery is a form of big data that can be harnessed for many social good applications, especially those focusing on rural areas. In this article, we describe the common problem of selecting sites for and planning rural development activities as informed by remote sensing and satellite image analysis. Effective planning in poor rural areas benefits from information that is not available and is difficult to obtain at any appreciable scale by any means other than algorithms for estimation and inference from remotely sensed images. We discuss two cases in depth: the targeting of unconditional cash transfers to extremely poor villages in sub-Saharan Africa and the siting and planning of solar-powered microgrids in remote villages in India. From these cases, we draw out some common lessons broadly applicable to informed rural development.


    Directory of Open Access Journals (Sweden)

    H. Kim


    Full Text Available High resolution satellite images are widely used to produce and update a digital map since they became widely available. It is well known that the accuracy of digital map produced from satellite images is decided largely by the accuracy of geometric modelling. However digital maps are made by a series of photogrammetric workflow. Therefore the accuracy of digital maps are also affected by the quality of satellite images, such as image interpretability. For satellite images, parameters such as Modulation Transfer Function(MTF, Signal to Noise Ratio(SNR and Ground Sampling Distance(GSD are used to present images quality. Our previous research stressed that such quality parameters may not represent the quality of image products such as digital maps and that parameters for image interpretability such as Ground Resolved Distance(GRD and National Imagery Interpretability Rating Scale(NIIRS need to be considered. In this study, we analyzed the effects of the image quality on accuracy of digital maps produced by satellite images. QuickBird, IKONOS and KOMPSAT-2 imagery were used to analyze as they have similar GSDs. We measured various image quality parameters mentioned above from these images. Then we produced digital maps from the images using a digital photogrammetric workstation. We analyzed the accuracy of the digital maps in terms of their location accuracy and their level of details. Then we compared the correlation between various image quality parameters and the accuracy of digital maps. The results of this study showed that GRD and NIIRS were more critical for map production then GSD, MTF or SNR.

  14. The SUMO Ship Detector Algorithm for Satellite Radar Images

    Directory of Open Access Journals (Sweden)

    Harm Greidanus


    Full Text Available Search for Unidentified Maritime Objects (SUMO is an algorithm for ship detection in satellite Synthetic Aperture Radar (SAR images. It has been developed over the course of more than 15 years, using a large amount of SAR images from almost all available SAR satellites operating in L-, C- and X-band. As validated by benchmark tests, it performs very well on a wide range of SAR image modes (from Spotlight to ScanSAR and resolutions (from 1–100 m and for all types and sizes of ships, within the physical limits imposed by the radar imaging. This paper describes, in detail, the algorithmic approach in all of the steps of the ship detection: land masking, clutter estimation, detection thresholding, target clustering, ship attribute estimation and false alarm suppression. SUMO is a pixel-based CFAR (Constant False Alarm Rate detector for multi-look radar images. It assumes a K distribution for the sea clutter, corrected however for deviations of the actual sea clutter from this distribution, implementing a fast and robust method for the clutter background estimation. The clustering of detected pixels into targets (ships uses several thresholds to deal with the typically irregular distribution of the radar backscatter over a ship. In a multi-polarization image, the different channels are fused. Azimuth ambiguities, a common source of false alarms in ship detection, are removed. A reliability indicator is computed for each target. In post-processing, using the results of a series of images, additional false alarms from recurrent (fixed targets including range ambiguities are also removed. SUMO can run in semi-automatic mode, where an operator can verify each detected target. It can also run in fully automatic mode, where batches of over 10,000 images have successfully been processed in less than two hours. The number of satellite SAR systems keeps increasing, as does their application to maritime surveillance. The open data policy of the EU



    Chetneti Srisaan


    Internet pornography (Internet Porn) is addictive to teenagers and kids around the world. The normal practice is to block those websites or filter out pornography from kids. Many research papers have been published how to detect a human pornographic image on web pages. A new technique was proposed here to classify pornography images using range of YCbCr (colour feature) and three new measurements: %Face_Area, %AHB and Rmax. A computer algorithm such as C4.5 was applied to construct a decision...

  16. An Imaging System for Satellite Hypervelocity Impact Debris Characterization (United States)


    Debris Program Office and the Air Force Space and Missile Systems Center. 8. REFERENCES 1. Osiander, R., and Ostdiek, P., “Introduction to Space ... Debris ,” Handbook of Space Engineering, Archaeology, and Heritage, CRC Press, Boca Raton, FL, 2009, pp. 363-379. 2. Englert, C., et al., “Optical...An Imaging System for Satellite Hypervelocity Impact Debris Characterization Matthew Moraguez, Dr. Kunal Patankar University of Florida Dr

  17. Object Detection in Satellite and Aerial Images: Remote Sensing Applications


    Sirmacek, Beril; Ünsalan, Cem


    Very high resolution satellite and aerial images provide valuable information to researchers. With their availability, there has been much interest to extract man-made objects from such imagery. Among these, detection of objects such as buildings, road segments, and urban area boundaries play crucial roles especially for municipalities, government agencies, rescue teams, military, and other civil agencies. For a human expert, manually extracting this valuable information is tedious and prone ...

  18. Histopathological Image Classification using Discriminative Feature-oriented Dictionary Learning (United States)

    Vu, Tiep Huu; Mousavi, Hojjat Seyed; Monga, Vishal; Rao, Ganesh; Rao, UK Arvind


    In histopathological image analysis, feature extraction for classification is a challenging task due to the diversity of histology features suitable for each problem as well as presence of rich geometrical structures. In this paper, we propose an automatic feature discovery framework via learning class-specific dictionaries and present a low-complexity method for classification and disease grading in histopathology. Essentially, our Discriminative Feature-oriented Dictionary Learning (DFDL) method learns class-specific dictionaries such that under a sparsity constraint, the learned dictionaries allow representing a new image sample parsimoniously via the dictionary corresponding to the class identity of the sample. At the same time, the dictionary is designed to be poorly capable of representing samples from other classes. Experiments on three challenging real-world image databases: 1) histopathological images of intraductal breast lesions, 2) mammalian kidney, lung and spleen images provided by the Animal Diagnostics Lab (ADL) at Pennsylvania State University, and 3) brain tumor images from The Cancer Genome Atlas (TCGA) database, reveal the merits of our proposal over state-of-the-art alternatives. Moreover, we demonstrate that DFDL exhibits a more graceful decay in classification accuracy against the number of training images which is highly desirable in practice where generous training is often not available. PMID:26513781

  19. Geographical classification of apple based on hyperspectral imaging (United States)

    Guo, Zhiming; Huang, Wenqian; Chen, Liping; Zhao, Chunjiang; Peng, Yankun


    Attribute of apple according to geographical origin is often recognized and appreciated by the consumers. It is usually an important factor to determine the price of a commercial product. Hyperspectral imaging technology and supervised pattern recognition was attempted to discriminate apple according to geographical origins in this work. Hyperspectral images of 207 Fuji apple samples were collected by hyperspectral camera (400-1000nm). Principal component analysis (PCA) was performed on hyperspectral imaging data to determine main efficient wavelength images, and then characteristic variables were extracted by texture analysis based on gray level co-occurrence matrix (GLCM) from dominant waveband image. All characteristic variables were obtained by fusing the data of images in efficient spectra. Support vector machine (SVM) was used to construct the classification model, and showed excellent performance in classification results. The total classification rate had the high classify accuracy of 92.75% in the training set and 89.86% in the prediction sets, respectively. The overall results demonstrated that the hyperspectral imaging technique coupled with SVM classifier can be efficiently utilized to discriminate Fuji apple according to geographical origins.

  20. A global aerosol classification algorithm incorporating multiple satellite data sets of aerosol and trace gas abundances (United States)

    Penning de Vries, M. J. M.; Beirle, S.; Hörmann, C.; Kaiser, J. W.; Stammes, P.; Tilstra, L. G.; Tuinder, O. N. E.; Wagner, T.


    Detecting the optical properties of aerosols using passive satellite-borne measurements alone is a difficult task due to the broadband effect of aerosols on the measured spectra and the influences of surface and cloud reflection. We present another approach to determine aerosol type, namely by studying the relationship of aerosol optical depth (AOD) with trace gas abundance, aerosol absorption, and mean aerosol size. Our new Global Aerosol Classification Algorithm, GACA, examines relationships between aerosol properties (AOD and extinction Ångström exponent from the Moderate Resolution Imaging Spectroradiometer (MODIS), UV Aerosol Index from the second Global Ozone Monitoring Experiment, GOME-2) and trace gas column densities (NO2, HCHO, SO2 from GOME-2, and CO from MOPITT, the Measurements of Pollution in the Troposphere instrument) on a monthly mean basis. First, aerosol types are separated based on size (Ångström exponent) and absorption (UV Aerosol Index), then the dominating sources are identified based on mean trace gas columns and their correlation with AOD. In this way, global maps of dominant aerosol type and main source type are constructed for each season and compared with maps of aerosol composition from the global MACC (Monitoring Atmospheric Composition and Climate) model. Although GACA cannot correctly characterize transported or mixed aerosols, GACA and MACC show good agreement regarding the global seasonal cycle, particularly for urban/industrial aerosols. The seasonal cycles of both aerosol type and source are also studied in more detail for selected 5° × 5° regions. Again, good agreement between GACA and MACC is found for all regions, but some systematic differences become apparent: the variability of aerosol composition (yearly and/or seasonal) is often not well captured by MACC, the amount of mineral dust outside of the dust belt appears to be overestimated, and the abundance of secondary organic aerosols is underestimated in comparison

  1. A global aerosol classification algorithm incorporating multiple satellite data sets of aerosol and trace gas abundances

    Directory of Open Access Journals (Sweden)

    M. J. M. Penning de Vries


    Full Text Available Detecting the optical properties of aerosols using passive satellite-borne measurements alone is a difficult task due to the broadband effect of aerosols on the measured spectra and the influences of surface and cloud reflection. We present another approach to determine aerosol type, namely by studying the relationship of aerosol optical depth (AOD with trace gas abundance, aerosol absorption, and mean aerosol size. Our new Global Aerosol Classification Algorithm, GACA, examines relationships between aerosol properties (AOD and extinction Ångström exponent from the Moderate Resolution Imaging Spectroradiometer (MODIS, UV Aerosol Index from the second Global Ozone Monitoring Experiment, GOME-2 and trace gas column densities (NO2, HCHO, SO2 from GOME-2, and CO from MOPITT, the Measurements of Pollution in the Troposphere instrument on a monthly mean basis. First, aerosol types are separated based on size (Ångström exponent and absorption (UV Aerosol Index, then the dominating sources are identified based on mean trace gas columns and their correlation with AOD. In this way, global maps of dominant aerosol type and main source type are constructed for each season and compared with maps of aerosol composition from the global MACC (Monitoring Atmospheric Composition and Climate model. Although GACA cannot correctly characterize transported or mixed aerosols, GACA and MACC show good agreement regarding the global seasonal cycle, particularly for urban/industrial aerosols. The seasonal cycles of both aerosol type and source are also studied in more detail for selected 5° × 5° regions. Again, good agreement between GACA and MACC is found for all regions, but some systematic differences become apparent: the variability of aerosol composition (yearly and/or seasonal is often not well captured by MACC, the amount of mineral dust outside of the dust belt appears to be overestimated, and the abundance of secondary organic aerosols is underestimated in


    Directory of Open Access Journals (Sweden)

    Diego Correia Maia


    Full Text Available ABSTRACT: The satellite images are still largely unexplored as didactic resource in geography classes, particularly about meteorology. This article aims to contribute to the development of new methodologies of interpretation and understanding, beyond the construction of pedagogical practices involving meteorological satellite images, concepts and issues related to climate issues. The aim of this paper is to present possibilities for the use of meteorological satellite images in the Teaching of Geography, aiming the promoting and the understanding of contents of air masses and fronts and climatic factors. RESUMO: As imagens de satélite ainda são pouco exploradas como recurso didático nas aulas de Geografia, principalmente aquelas relativas à meteorologia. Este artigo visa contribuir com o desenvolvimento de novas metodologias de interpretação e compreensão, além da construção de práticas pedagógicas envolvendo imagens de satélite meteorológico, conceitos e temas ligados às questões climáticas. Seu objetivo é apresentar possibilidades de utilização das imagens de satélite meteorológico no Ensino de Geografia, visando à promoção e ao entendimento dos conteúdos de massas de ar e frentes e de elementos climáticos. Palavras chave

  3. Low Rank Sparse Coding for Image Classification (United States)


    Singapore 4 Institute of Automation, Chinese Academy of Sciences, P. R. China 5 University of Illinois at Urbana -Champaign, Urbana , IL USA Abstract In this...which contain 200 to 400 images each. The categories vary from outdoor scenes like mountain and forest to indoor environments like living room and

  4. Multispectral Image Analysis for Astaxanthin Coating Classification

    DEFF Research Database (Denmark)

    Ljungqvist, Martin Georg; Ersbøll, Bjarne Kjær; Nielsen, Michael Engelbrecht


    Industrial quality inspection using image analysis on astaxanthin coating in aquaculture feed pellets is of great importance for automatic production control. The pellets were divided into two groups: one with pellets coated using synthetic astaxanthin in fish oil and the other with pellets coated...

  5. Halftone image classification using LMS algorithm and naive Bayes. (United States)

    Liu, Yun-Fu; Guo, Jing-Ming; Lee, Jiann-Der


    Former research on inverse halftoning most focus on developing a general-purpose method for all types of halftone patterns, such as error diffusion, ordered dithering, etc., while fail to consider the natural discrepancies among various halftoning methods. To achieve optimal image quality for each halftoning method, the classification of halftone images is highly demanded. This study employed the least mean-square filter for improving the robustness of the extracted features, and employed the naive Bayes classifier to verify all the extracted features for classification. Nine of the most well-known halftoning methods were involved for testing. The experimental results demonstrated that the classification performance can achieve a 100% accuracy rate, and the number of distinguishable halftoning methods is more than that of a former method established by Chang and Yu. © 2011 IEEE

  6. Classification Method in Integrated Information Network Using Vector Image Comparison

    Directory of Open Access Journals (Sweden)

    Zhou Yuan


    Full Text Available Wireless Integrated Information Network (WMN consists of integrated information that can get data from its surrounding, such as image, voice. To transmit information, large resource is required which decreases the service time of the network. In this paper we present a Classification Approach based on Vector Image Comparison (VIC for WMN that improve the service time of the network. The available methods for sub-region selection and conversion are also proposed.

  7. Visual features underlying perceived brightness as revealed by classification images.

    Directory of Open Access Journals (Sweden)

    Ilmari Kurki

    Full Text Available Along with physical luminance, the perceived brightness is known to depend on the spatial structure of the stimulus. Often it is assumed that neural computation of the brightness is based on the analysis of luminance borders of the stimulus. However, this has not been tested directly. We introduce a new variant of the psychophysical reverse-correlation or classification image method to estimate and localize the physical features of the stimuli which correlate with the perceived brightness, using a brightness-matching task. We derive classification images for the illusory Craik-O'Brien-Cornsweet stimulus and a "real" uniform step stimulus. For both stimuli, classification images reveal a positive peak at the stimulus border, along with a negative peak at the background, but are flat at the center of the stimulus, suggesting that brightness is determined solely by the border information. Features in the perceptually completed area in the Craik-O'Brien-Cornsweet do not contribute to its brightness, nor could we see low-frequency boosting, which has been offered as an explanation for the illusion. Tuning of the classification image profiles changes remarkably little with stimulus size. This supports the idea that only certain spatial scales are used for computing the brightness of a surface.

  8. A graph-based approach to detect spatiotemporal dynamics in satellite image time series (United States)

    Guttler, Fabio; Ienco, Dino; Nin, Jordi; Teisseire, Maguelonne; Poncelet, Pascal


    Enhancing the frequency of satellite acquisitions represents a key issue for Earth Observation community nowadays. Repeated observations are crucial for monitoring purposes, particularly when intra-annual process should be taken into account. Time series of images constitute a valuable source of information in these cases. The goal of this paper is to propose a new methodological framework to automatically detect and extract spatiotemporal information from satellite image time series (SITS). Existing methods dealing with such kind of data are usually classification-oriented and cannot provide information about evolutions and temporal behaviors. In this paper we propose a graph-based strategy that combines object-based image analysis (OBIA) with data mining techniques. Image objects computed at each individual timestamp are connected across the time series and generates a set of evolution graphs. Each evolution graph is associated to a particular area within the study site and stores information about its temporal evolution. Such information can be deeply explored at the evolution graph scale or used to compare the graphs and supply a general picture at the study site scale. We validated our framework on two study sites located in the South of France and involving different types of natural, semi-natural and agricultural areas. The results obtained from a Landsat SITS support the quality of the methodological approach and illustrate how the framework can be employed to extract and characterize spatiotemporal dynamics.

  9. Low Dimensional Representation of Fisher Vectors for Microscopy Image Classification. (United States)

    Song, Yang; Li, Qing; Huang, Heng; Feng, Dagan; Chen, Mei; Cai, Weidong


    Microscopy image classification is important in various biomedical applications, such as cancer subtype identification, and protein localization for high content screening. To achieve automated and effective microscopy image classification, the representative and discriminative capability of image feature descriptors is essential. To this end, in this paper, we propose a new feature representation algorithm to facilitate automated microscopy image classification. In particular, we incorporate Fisher vector (FV) encoding with multiple types of local features that are handcrafted or learned, and we design a separation-guided dimension reduction method to reduce the descriptor dimension while increasing its discriminative capability. Our method is evaluated on four publicly available microscopy image data sets of different imaging types and applications, including the UCSB breast cancer data set, MICCAI 2015 CBTC challenge data set, and IICBU malignant lymphoma, and RNAi data sets. Our experimental results demonstrate the advantage of the proposed low-dimensional FV representation, showing consistent performance improvement over the existing state of the art and the commonly used dimension reduction techniques.

  10. Pixel classification based color image segmentation using quaternion exponent moments. (United States)

    Wang, Xiang-Yang; Wu, Zhi-Fang; Chen, Liang; Zheng, Hong-Liang; Yang, Hong-Ying


    Image segmentation remains an important, but hard-to-solve, problem since it appears to be application dependent with usually no a priori information available regarding the image structure. In recent years, many image segmentation algorithms have been developed, but they are often very complex and some undesired results occur frequently. In this paper, we propose a pixel classification based color image segmentation using quaternion exponent moments. Firstly, the pixel-level image feature is extracted based on quaternion exponent moments (QEMs), which can capture effectively the image pixel content by considering the correlation between different color channels. Then, the pixel-level image feature is used as input of twin support vector machines (TSVM) classifier, and the TSVM model is trained by selecting the training samples with Arimoto entropy thresholding. Finally, the color image is segmented with the trained TSVM model. The proposed scheme has the following advantages: (1) the effective QEMs is introduced to describe color image pixel content, which considers the correlation between different color channels, (2) the excellent TSVM classifier is utilized, which has lower computation time and higher classification accuracy. Experimental results show that our proposed method has very promising segmentation performance compared with the state-of-the-art segmentation approaches recently proposed in the literature. Copyright © 2015 Elsevier Ltd. All rights reserved.

  11. Monitoring flood inundation extent with means of Sentinel - 1 and Landsat 8 satellite images (United States)

    Papathanasiou, Kostas; Alexakis, Dimitrios D.; Tsanis, Ioannis K.


    Floods are among the most devastating natural hazards in the world, widely distributed leading to significant economic and social damages than any other natural phenomenon. The aim of this study was to develop a straightforward approach for flood area mapping in Strymonas River, Greece. This region experiences annual flooding and has caused several times in the recent past loss of livelihoods. For the needs of the study two Landsat 8 and two Sentinel-1 images were used along with the reference vector inundation data derived from the freely distributed Copernicus programmed data (European Flood Awareness System- EFAS). Various image analysis methods were implemented to monitor flood extent including images subtraction, classification methods and application of threshold values. Radar and optical sensor data were combined in order to enhance the operational capacity of satellite data. A strong agreement was found between Sentinel-1 flood extent monitoring and Copernicus EFAS data. The results denoted the potential of both radar and optical images in effective monitoring of flood inundation phenomena. Keywords: Sentinel-1, Landsat 8, floods, classification, Copernicus EFAS

  12. Object-oriented Markov random model for classification of high resolution satellite imagery based on wavelet transform (United States)

    Hong, Liang; Liu, Cun; Yang, Kun; Deng, Ming


    The high resolution satellite imagery (HRSI) have higher spatial resolution and less spectrum number, so there are some "object with different spectra, different objects with same spectrum" phenomena. The objective of this paper is to utilize the extracted features of high resolution satellite imagery (HRSI) obtained by the wavelet transform(WT) for segmentation. WT provides the spatial and spectral characteristics of a pixel along with its neighbors. The object-oriented Markov random Model in the wavelet domain is proposed in order to segment high resolution satellite imagery (HRSI). The proposed method is made up of three blocks: (1) WT-based feature extrcation.the aim of extraction of feature using WT for original spectral bands is to exploit the spatial and frequency information of the pixels; (2) over-segmentation object generation. Mean-Shift algorithm is employed to obtain over-segmentation objects; (3) classification based on Object-oriented Markov Random Model. Firstly the object adjacent graph (OAG) can be constructed on the over-segmentation objects. Secondly MRF model is easily defined on the OAG, in which WT-based feature of pixels are modeled in the feature field model and the neighbor system, potential cliques and energy functions of OAG are exploited in the labeling model. Experiments are conducted on one HRSI dataset-QuickBird images. We evaluate and compare the proposed approach with the well-known commercial software eCognition(object-based analysis approach) and Maximum Likelihood(ML) based pixels. Experimental results show that the proposed the method in this paper obviously outperforms the other methods.

  13. Automating sky object classification in astronomical survey images (United States)

    Fayyad, Usama M.; Doyle, Richard J.; Weir, Nicholas; Djorgovski, S. G.


    We describe the application of machine classification techniques to the development of an automated tool for the reduction of a large scientific data set. The 2nd Palomer Observatory Sky Survey is nearly completed. This survey provides comprehensive coverage of the northern celestial hemisphere in the form of photographic plates. The plates are being transformed into digitized images whose quality will probably not be surpassed in the next ten to twenty years. The images are expected to contain on the order of 10(exp 7) galaxies and 10(exp 8) stars. Astronomers wish to determine which of these sky objects belong to various classes of galaxies and stars. The size of this data set precludes manual analysis. Our approach is to develop a software system which integrates the functions of independently developed techniques for image processing and data classification. Digitized sky images are passed through image processing routines to identify sky objects and to extract a set of features for each object. These routines are used to help select a useful set of attributes for classifying sky objects. Then GID3* and O-BTree, two inductive learning techniques, learn classification decision trees from examples. These classifiers will be used to process the rest of the data. This paper gives an overview of the machine learning techniques used, describes the details of our specific application, and reports the initial encouraging results. The results indicate that our approach is well-suited to the problem. The primary benefits of the approach are increased data reduction throughput and consistency of classification. The classification rules which are the product of the inductive learning techniques will form an object, examinable basis for classifying sky objects. A final, not to be underestimated benefit is that astronomers will be freed from the tedium of an intensely visual task to pursue more challenging analysis and interpretation problems based on automatically cataloged


    Directory of Open Access Journals (Sweden)

    A. Sabuncu


    Full Text Available Earthquakes are the most destructive natural disasters, which result in massive loss of life, infrastructure damages and financial losses. Earthquake-induced building damage detection is a very important step after earthquakes since earthquake-induced building damage is one of the most critical threats to cities and countries in terms of the area of damage, rate of collapsed buildings, the damage grade near the epicenters and also building damage types for all constructions. Van-Ercis (Turkey earthquake (Mw= 7.1 was occurred on October 23th, 2011; at 10:41 UTC (13:41 local time centered at 38.75 N 43.36 E that places the epicenter about 30 kilometers northern part of the city of Van. It is recorded that, 604 people died and approximately 4000 buildings collapsed or seriously damaged by the earthquake. In this study, high-resolution satellite images of Van-Ercis, acquired by Quickbird-2 (© Digital Globe Inc. after the earthquake, were used to detect the debris areas using an object-based image classification. Two different land surfaces, having homogeneous and heterogeneous land covers, were selected as case study areas. As a first step of the object-based image processing, segmentation was applied with a convenient scale parameter and homogeneity criterion parameters. As a next step, condition based classification was used. In the final step of this preliminary study, outputs were compared with streetview/ortophotos for the verification and evaluation of the classification accuracy.

  15. Remote Sensing Image Classification With Large-Scale Gaussian Processes (United States)

    Morales-Alvarez, Pablo; Perez-Suay, Adrian; Molina, Rafael; Camps-Valls, Gustau


    Current remote sensing image classification problems have to deal with an unprecedented amount of heterogeneous and complex data sources. Upcoming missions will soon provide large data streams that will make land cover/use classification difficult. Machine learning classifiers can help at this, and many methods are currently available. A popular kernel classifier is the Gaussian process classifier (GPC), since it approaches the classification problem with a solid probabilistic treatment, thus yielding confidence intervals for the predictions as well as very competitive results to state-of-the-art neural networks and support vector machines. However, its computational cost is prohibitive for large scale applications, and constitutes the main obstacle precluding wide adoption. This paper tackles this problem by introducing two novel efficient methodologies for Gaussian Process (GP) classification. We first include the standard random Fourier features approximation into GPC, which largely decreases its computational cost and permits large scale remote sensing image classification. In addition, we propose a model which avoids randomly sampling a number of Fourier frequencies, and alternatively learns the optimal ones within a variational Bayes approach. The performance of the proposed methods is illustrated in complex problems of cloud detection from multispectral imagery and infrared sounding data. Excellent empirical results support the proposal in both computational cost and accuracy.

  16. Magnetic resonance imaging texture analysis classification of primary breast cancer

    Energy Technology Data Exchange (ETDEWEB)

    Waugh, S.A.; Lerski, R.A. [Ninewells Hospital and Medical School, Department of Medical Physics, Dundee (United Kingdom); Purdie, C.A.; Jordan, L.B. [Ninewells Hospital and Medical School, Department of Pathology, Dundee (United Kingdom); Vinnicombe, S. [University of Dundee, Division of Imaging and Technology, Ninewells Hospital and Medical School, Dundee (United Kingdom); Martin, P. [Ninewells Hospital and Medical School, Department of Clinical Radiology, Dundee (United Kingdom); Thompson, A.M. [University of Texas MD Anderson Cancer Center, Department of Surgical Oncology, Houston, TX (United States)


    Patient-tailored treatments for breast cancer are based on histological and immunohistochemical (IHC) subtypes. Magnetic Resonance Imaging (MRI) texture analysis (TA) may be useful in non-invasive lesion subtype classification. Women with newly diagnosed primary breast cancer underwent pre-treatment dynamic contrast-enhanced breast MRI. TA was performed using co-occurrence matrix (COM) features, by creating a model on retrospective training data, then prospectively applying to a test set. Analyses were blinded to breast pathology. Subtype classifications were performed using a cross-validated k-nearest-neighbour (k = 3) technique, with accuracy relative to pathology assessed and receiver operator curve (AUROC) calculated. Mann-Whitney U and Kruskal-Wallis tests were used to assess raw entropy feature values. Histological subtype classifications were similar across training (n = 148 cancers) and test sets (n = 73 lesions) using all COM features (training: 75 %, AUROC = 0.816; test: 72.5 %, AUROC = 0.823). Entropy features were significantly different between lobular and ductal cancers (p < 0.001; Mann-Whitney U). IHC classifications using COM features were also similar for training and test data (training: 57.2 %, AUROC = 0.754; test: 57.0 %, AUROC = 0.750). Hormone receptor positive and negative cancers demonstrated significantly different entropy features. Entropy features alone were unable to create a robust classification model. Textural differences on contrast-enhanced MR images may reflect underlying lesion subtypes, which merits testing against treatment response. (orig.)

  17. Characterization and classification of South American land cover types using satellite data (United States)

    Townshend, J. R. G.; Justice, C. O.; Kalb, V.


    Various methods are compared for carrying out land cover classifications of South America using multitemporal Advanced Very High Resolution Radiometer data. Fifty-two images of the normalized difference vegetation index (NDVI) from a 1-year period are used to generate multitemporal data sets. Three main approaches to land cover classification are considered, namely the use of the principal components transformed images, the use of a characteristic curves procedure based on NDVI values plotted against time, and finally application of the maximum likelihood rule to multitemporal data sets. Comparison of results from training sites indicates that the last approach yields the most accurate results. Despite the reliance on training site figures for performance assessment, the results are nevertheless extremely encouraging, with accuracies for several cover types exceeding 90 per cent.

  18. Multi-Channel Satellite Image Analysis Using a Variational Approach (United States)

    Alvarez, L.; Castaño, C. A.; García, M.; Krissian, K.; Mazorra, L.; Salgado, A.; Sánchez, J.


    Currently, meteorological satellites provide multichannel image sequences including visible, temperature and water vapor channels. Based on a variational approach, we propose mathematical models to address some of the usual challenges in satellite image analysis such as: (i) the estimation and smoothing of the cloud structures by decoupling them into different layers depending on their altitudes, (ii) the estimation of the cloud structure motion by combining information from all the channels, and (iii) the 3D visualization of both the cloud structure and the estimated displacements. We include information of all the channels in a single variational motion estimation model. The associated Euler-Lagrange equations yield to a nonlinear system of partial differential equations that we solve numerically using finite-difference schemes. We illustrate the performance of the proposed models with numerical experiments on two multichannel satellite sequences of the North Atlantic, one of them from the Hurricane Vince. Based on a realistic synthetic ground truth motion, we show that our multichannel approach overcomes the single channel estimation for both the average Euclidean and angular errors.

  19. Likelihood-based image segmentation and classification: a framework for the integration of expert knowledge in image classification procedures

    NARCIS (Netherlands)

    Abkar, Ali-Akbar; Mulder, Nanno; Sharifi, Mohammed Ali


    This paper describes a likelihood-based segmentation and classification method for remotely sensed images. It is based on optimization of a utility function that can be described as a cost-weighted likelihood for a collection of objects and their parameters. As the likelihood or posterior

  20. Classification of texture patterns in CT lung imaging (United States)

    Nuzhnaya, Tatyana; Megalooikonomou, Vasileios; Ling, Haibin; Kohn, Mark; Steiner, Robert


    Since several lung diseases can be potentially diagnosed based on the patterns of lung tissue observed in medical images, automated texture classification can be useful in assisting the diagnosis. In this paper, we propose a methodology for discriminating between various types of normal and diseased lung tissue in computed tomography (CT) images that utilizes Vector Quantization (VQ), an image compression technique, to extract discriminative texture features. Rather than focusing on images of the entire lung, we direct our attention to the extraction of local descriptors from individual regions of interest (ROIs) as determined by domain experts. After determining the ROIs, we generate "locally optimal" codebooks representing texture features of each region using the Generalized Lloyd Algorithm. We then utilize the codeword usage frequency of each codebook as a discriminative feature vector for the region it represents. We compare k-nearest neighbor, support vector machine and neural network classification approaches using the normalized histogram intersection as a similarity measure. The classification accuracy reached up to 98% for certain experimental settings, indicating that our approach may potentially assist clinicians in the interpretation of lung images and facilitate the investigation of relationships among structure, texture and function or pathology related to several lung diseases.


    Directory of Open Access Journals (Sweden)

    M. Modiri


    Full Text Available Automatic extraction of building roofs, street and vegetation are a prerequisite for many GIS (Geographic Information System applications, such as urban planning and 3D building reconstruction. Nowadays with advances in image processing and image matching technique by using feature base and template base image matching technique together dense point clouds are available. Point clouds classification is an important step in automatic features extraction. Therefore, in this study, the classification of point clouds based on features color and shape are implemented. We use two images by proper overlap getting by Ultracam-x camera in this study. The images are from Yasouj in IRAN. It is semi-urban area by building with different height. Our goal is classification buildings and vegetation in these points. In this article, an algorithm is developed based on the color characteristics of the point’s cloud, using an appropriate DEM (Digital Elevation Model and points clustering method. So that, firstly, trees and high vegetation are classified by using the point’s color characteristics and vegetation index. Then, bare earth DEM is used to separate ground and non-ground points. Non-ground points are then divided into clusters based on height and local neighborhood. One or more clusters are initialized based on the maximum height of the points and then each cluster is extended by applying height and neighborhood constraints. Finally, planar roof segments are extracted from each cluster of points following a region-growing technique.

  2. Automatic Segmentation of Dermoscopic Images by Iterative Classification

    Directory of Open Access Journals (Sweden)

    Maciel Zortea


    Full Text Available Accurate detection of the borders of skin lesions is a vital first step for computer aided diagnostic systems. This paper presents a novel automatic approach to segmentation of skin lesions that is particularly suitable for analysis of dermoscopic images. Assumptions about the image acquisition, in particular, the approximate location and color, are used to derive an automatic rule to select small seed regions, likely to correspond to samples of skin and the lesion of interest. The seed regions are used as initial training samples, and the lesion segmentation problem is treated as binary classification problem. An iterative hybrid classification strategy, based on a weighted combination of estimated posteriors of a linear and quadratic classifier, is used to update both the automatically selected training samples and the segmentation, increasing reliability and final accuracy, especially for those challenging images, where the contrast between the background skin and lesion is low.

  3. Comparison research on iot oriented image classification algorithms

    Directory of Open Access Journals (Sweden)

    Du Ke


    Full Text Available Image classification belongs to the machine learning and computer vision fields, it aims to recognize and classify objects in the image contents. How to apply image classification algorithms to large-scale data in the IoT framework is the focus of current research. Based on Anaconda, this article implement sk-NN, SVM, Softmax and Neural Network algorithms by Python, performs data normalization, random search, HOG and colour histogram feature extraction to enhance the algorithms, experiments on them in CIFAR-10 datasets, then conducts comparison from three aspects of training time, test time and classification accuracy. The experimental results show that: the vectorized implementation of the algorithms is more efficient than the loop implementation; The training time of k-NN is the shortest, SVM and Softmax spend more time, and the training time of Neural Network is the longest; The test time of SVM, Softmax and Neural Network are much shorter than of k-NN; Neural Network gets the highest classification accuracy, SVM and Softmax get lower and approximate accuracies, and k-NN gets the lowest accuracy. The effects of three algorithm improvement methods are obvious.

  4. New Adaptive Image Quality Assessment Based on Distortion Classification

    Directory of Open Access Journals (Sweden)

    Xin JIN


    Full Text Available This paper proposes a new adaptive image quality assessment (AIQA method, which is based on distortion classifying. AIQA contains two parts, distortion classification and image quality assessment. Firstly, we analysis characteristics of the original and distorted images, including the distribution of wavelet coefficient, the ratio of edge energy and inner energy of the differential image block, we divide distorted images into White Noise distortion, JPEG compression distortion and fuzzy distortion. To evaluate the quality of first two type distortion images, we use pixel based structure similarity metric and DCT based structural similarity metric respectively. For those blurriness pictures, we present a new wavelet-based structure similarity algorithm. According to the experimental results, AIQA takes the advantages of different structural similarity metrics, and it’s able to simulate the human visual perception effectively.

  5. Topology-preserving tissue classification of magnetic resonance brain images. (United States)

    Bazin, Pierre-Louis; Pham, Dzung L


    This paper presents a new framework for multiple object segmentation in medical images that respects the topological properties and relationships of structures as given by a template. The technique, known as topology-preserving, anatomy-driven segmentation (TOADS), combines advantages of statistical tissue classification, topology-preserving fast marching methods, and image registration to enforce object-level relationships with little constraint over the geometry. When applied to the problem of brain segmentation, it directly provides a cortical surface with spherical topology while segmenting the main cerebral structures. Validation on simulated and real images characterises the performance of the algorithm with regard to noise, inhomogeneities, and anatomical variations.

  6. Supervised graph hashing for histopathology image retrieval and classification. (United States)

    Shi, Xiaoshuang; Xing, Fuyong; Xu, KaiDi; Xie, Yuanpu; Su, Hai; Yang, Lin


    In pathology image analysis, morphological characteristics of cells are critical to grade many diseases. With the development of cell detection and segmentation techniques, it is possible to extract cell-level information for further analysis in pathology images. However, it is challenging to conduct efficient analysis of cell-level information on a large-scale image dataset because each image usually contains hundreds or thousands of cells. In this paper, we propose a novel image retrieval based framework for large-scale pathology image analysis. For each image, we encode each cell into binary codes to generate image representation using a novel graph based hashing model and then conduct image retrieval by applying a group-to-group matching method to similarity measurement. In order to improve both computational efficiency and memory requirement, we further introduce matrix factorization into the hashing model for scalable image retrieval. The proposed framework is extensively validated with thousands of lung cancer images, and it achieves 97.98% classification accuracy and 97.50% retrieval precision with all cells of each query image used. Copyright © 2017 Elsevier B.V. All rights reserved.

  7. Deep Transfer Learning for Modality Classification of Medical Images

    Directory of Open Access Journals (Sweden)

    Yuhai Yu


    Full Text Available Medical images are valuable for clinical diagnosis and decision making. Image modality is an important primary step, as it is capable of aiding clinicians to access required medical image in retrieval systems. Traditional methods of modality classification are dependent on the choice of hand-crafted features and demand a clear awareness of prior domain knowledge. The feature learning approach may detect efficiently visual characteristics of different modalities, but it is limited to the number of training datasets. To overcome the absence of labeled data, on the one hand, we take deep convolutional neural networks (VGGNet, ResNet with different depths pre-trained on ImageNet, fix most of the earlier layers to reserve generic features of natural images, and only train their higher-level portion on ImageCLEF to learn domain-specific features of medical figures. Then, we train from scratch deep CNNs with only six weight layers to capture more domain-specific features. On the other hand, we employ two data augmentation methods to help CNNs to give the full scope to their potential characterizing image modality features. The final prediction is given by our voting system based on the outputs of three CNNs. After evaluating our proposed model on the subfigure classification task in ImageCLEF2015 and ImageCLEF2016, we obtain new, state-of-the-art results—76.87% in ImageCLEF2015 and 87.37% in ImageCLEF2016—which imply that CNNs, based on our proposed transfer learning methods and data augmentation skills, can identify more efficiently modalities of medical images.

  8. Scene classification of infrared images based on texture feature (United States)

    Zhang, Xiao; Bai, Tingzhu; Shang, Fei


    Scene Classification refers to as assigning a physical scene into one of a set of predefined categories. Utilizing the method texture feature is good for providing the approach to classify scenes. Texture can be considered to be repeating patterns of local variation of pixel intensities. And texture analysis is important in many applications of computer image analysis for classification or segmentation of images based on local spatial variations of intensity. Texture describes the structural information of images, so it provides another data to classify comparing to the spectrum. Now, infrared thermal imagers are used in different kinds of fields. Since infrared images of the objects reflect their own thermal radiation, there are some shortcomings of infrared images: the poor contrast between the objectives and background, the effects of blurs edges, much noise and so on. Because of these shortcomings, it is difficult to extract to the texture feature of infrared images. In this paper we have developed an infrared image texture feature-based algorithm to classify scenes of infrared images. This paper researches texture extraction using Gabor wavelet transform. The transformation of Gabor has excellent capability in analysis the frequency and direction of the partial district. Gabor wavelets is chosen for its biological relevance and technical properties In the first place, after introducing the Gabor wavelet transform and the texture analysis methods, the infrared images are extracted texture feature by Gabor wavelet transform. It is utilized the multi-scale property of Gabor filter. In the second place, we take multi-dimensional means and standard deviation with different scales and directions as texture parameters. The last stage is classification of scene texture parameters with least squares support vector machine (LS-SVM) algorithm. SVM is based on the principle of structural risk minimization (SRM). Compared with SVM, LS-SVM has overcome the shortcoming of

  9. On classification of sea surface oil films using TerraSAR-X satellite polarization data (United States)

    Ivonin, D. V.; Ivanov, A. Yu.


    The paper presents the results of applying a new polarization method proposed in [28] to identify the type of surface pollution and differentiate between mineral oil films (crude oil and its emulsion and petroleum products) and films of other origin in sea surface radar images. The method is based on calculation of the quantitative characteristics for the ratios of suppression or intensification of scattered radio signals of different physical nature, viz., caused by capillary ripples several centimeters long, or wave breaking. TerraSAR-X satellite coaxial-polarized (VV/HH) SAR images are used. The data for analysis have been collected in areas where spots and slicks of known origin regularly occur, such as oil spills and natural oil seeps in the Gulf of Mexico and the Caspian Sea, and biogenic films in the Caspian Sea. The results of analyzing radar images from the TerraSAR-X satellite with controlled experimental oil emulsion spills in the North Sea are used for comparison. Based on the analysis of ten TerraSAR-X radar polarization images with surface sensing angles greater than 30°, it is shown that this method makes it possible to distinguish between oil spills and slicks formed by natural oil seeps and biogenic films with an accuracy higher than 80% regardless of the observation area.

  10. Segmentation and Classification of Remotely Sensed Images: Object-Based Image Analysis (United States)

    Syed, Abdul Haleem

    Land-use-and-land-cover (LULC) mapping is crucial in precision agriculture, environmental monitoring, disaster response, and military applications. The demand for improved and more accurate LULC maps has led to the emergence of a key methodology known as Geographic Object-Based Image Analysis (GEOBIA). The core idea of the GEOBIA for an object-based classification system (OBC) is to change the unit of analysis from single-pixels to groups-of-pixels called `objects' through segmentation. While this new paradigm solved problems and improved global accuracy, it also raised new challenges such as the loss of accuracy in categories that are less abundant, but potentially important. Although this trade-off may be acceptable in some domains, the consequences of such an accuracy loss could be potentially fatal in others (for instance, landmine detection). This thesis proposes a method to improve OBC performance by eliminating such accuracy losses. Specifically, we examine the two key players of an OBC system: Hierarchical Segmentation and Supervised Classification. Further, we propose a model to understand the source of accuracy errors in minority categories and provide a method called Scale Fusion to eliminate those errors. This proposed fusion method involves two stages. First, the characteristic scale for each category is estimated through a combination of segmentation and supervised classification. Next, these estimated scales (segmentation maps) are fused into one combined-object-map. Classification performance is evaluated by comparing results of the multi-cut-and-fuse approach (proposed) to the traditional single-cut (SC) scale selection strategy. Testing on four different data sets revealed that our proposed algorithm improves accuracy on minority classes while performing just as well on abundant categories. Another active obstacle, presented by today's remotely sensed images, is the volume of information produced by our modern sensors with high spatial and

  11. G0-WISHART Distribution Based Classification from Polarimetric SAR Images (United States)

    Hu, G. C.; Zhao, Q. H.


    Enormous scientific and technical developments have been carried out to further improve the remote sensing for decades, particularly Polarimetric Synthetic Aperture Radar(PolSAR) technique, so classification method based on PolSAR images has getted much more attention from scholars and related department around the world. The multilook polarmetric G0-Wishart model is a more flexible model which describe homogeneous, heterogeneous and extremely heterogeneous regions in the image. Moreover, the polarmetric G0-Wishart distribution dose not include the modified Bessel function of the second kind. It is a kind of simple statistical distribution model with less parameter. To prove its feasibility, a process of classification has been tested with the full-polarized Synthetic Aperture Radar (SAR) image by the method. First, apply multilook polarimetric SAR data process and speckle filter to reduce speckle influence for classification result. Initially classify the image into sixteen classes by H/A/α decomposition. Using the ICM algorithm to classify feature based on the G0-Wshart distance. Qualitative and quantitative results show that the proposed method can classify polaimetric SAR data effectively and efficiently.

  12. Semi-Supervised Feature Transformation for Tissue Image Classification.

    Directory of Open Access Journals (Sweden)

    Kenji Watanabe

    Full Text Available Various systems have been proposed to support biological image analysis, with the intent of decreasing false annotations and reducing the heavy burden on biologists. These systems generally comprise a feature extraction method and a classification method. Task-oriented methods for feature extraction leverage characteristic images for each problem, and they are very effective at improving the classification accuracy. However, it is difficult to utilize such feature extraction methods for versatile task in practice, because few biologists specialize in Computer Vision and/or Pattern Recognition to design the task-oriented methods. Thus, in order to improve the usability of these supporting systems, it will be useful to develop a method that can automatically transform the image features of general propose into the effective form toward the task of their interest. In this paper, we propose a semi-supervised feature transformation method, which is formulated as a natural coupling of principal component analysis (PCA and linear discriminant analysis (LDA in the framework of graph-embedding. Compared with other feature transformation methods, our method showed favorable classification performance in biological image analysis.

  13. Real time deforestation detection using ann and satellite images the Amazon rainforest study case

    CERN Document Server

    Nunes Kehl, Thiago; Roberto Veronez, Maurício; Cesar Cazella, Silvio


    The foremost aim of the present study was the development of a tool to detect daily deforestation in the Amazon rainforest, using satellite images from the MODIS/TERRA sensor and Artificial Neural Networks. The developed tool provides parameterization of the configuration for the neural network training to enable us to select the best neural architecture to address the problem. The tool makes use of confusion matrices to determine the degree of success of the network. A spectrum-temporal analysis of the study area was done on 57 images from May 20 to July 15, 2003 using the trained neural network. The analysis enabled verification of quality of the implemented neural network classification and also aided in understanding the dynamics of deforestation in the Amazon rainforest, thereby highlighting the vast potential of neural networks for image classification. However, the complex task of detection of predatory actions at the beginning, i.e., generation of consistent alarms, instead of false alarms has not bee...

  14. Chagas disease study using satellite image processing: A Bolivian case (United States)

    Vargas-Cuentas, Natalia I.; Roman-Gonzalez, Avid; Mantari, Alicia Alva; Muñoz, Luis AnthonyAucapuma


    Remote sensing is the technology that has enabled us to obtain information about the Earth's surface without directly contacting it. For this reason, currently, the Bolivian state has considered a list of interesting applications of remote sensing in the country, including the following: biodiversity and environment monitoring, mining and geology, epidemiology, agriculture, water resources and land use planning. The use of satellite images has become a great tool for epidemiology because with this technological advance we can determine the environment in which transmission occurs, the distribution of the disease and its evolution over time. In that context, one of the important diseases related to public health in Bolivia is Chagas disease, also known as South American Trypanosomiasis. Chagas is caused by a blood-sucking bug or Vinchuca, which causes serious intestinal and heart long term problems and affects 33.4% of the Bolivian population. This disease affects mostly humble people, so the Bolivian state invests millions of dollars to acquire medicine and distribute it for free. Due to the above reasons, the present research aims to analyze some areas of Bolivia using satellite images for developing an epidemiology study. The primary objective is to understand the environment in which the transmission of the disease happens, and the climatic conditions under which occurs, observe the behavior of the blood-sucking bug, identify in which months occur higher outbreaks, in which months the bug leaves its eggs, and under which weather conditions this happens. All this information would be contrasted with information extracted from the satellite images and data from the Ministry of Health, and the Institute of Meteorology in Bolivia. All this data will allow us to have a more integrated understanding of this disease and promote new possibilities to prevent and control it.

  15. Classification of Korla fragrant pears using NIR hyperspectral imaging analysis (United States)

    Rao, Xiuqin; Yang, Chun-Chieh; Ying, Yibin; Kim, Moon S.; Chao, Kuanglin


    Korla fragrant pears are small oval pears characterized by light green skin, crisp texture, and a pleasant perfume for which they are named. Anatomically, the calyx of a fragrant pear may be either persistent or deciduous; the deciduouscalyx fruits are considered more desirable due to taste and texture attributes. Chinese packaging standards require that packed cases of fragrant pears contain 5% or less of the persistent-calyx type. Near-infrared hyperspectral imaging was investigated as a potential means for automated sorting of pears according to calyx type. Hyperspectral images spanning the 992-1681 nm region were acquired using an EMCCD-based laboratory line-scan imaging system. Analysis of the hyperspectral images was performed to select wavebands useful for identifying persistent-calyx fruits and for identifying deciduous-calyx fruits. Based on the selected wavebands, an image-processing algorithm was developed that targets automated classification of Korla fragrant pears into the two categories for packaging purposes.

  16. Atmosphere-based image classification through luminance and hue (United States)

    Xu, Feng; Zhang, Yujin


    In this paper a novel image classification system is proposed. Atmosphere serves an important role in generating the scene"s topic or in conveying the message behind the scene"s story, which belongs to abstract attribute level in semantic levels. At first, five atmosphere semantic categories are defined according to rules of photo and film grammar, followed by global luminance and hue features. Then the hierarchical SVM classifiers are applied. In each classification stage, corresponding features are extracted and the trained linear SVM is implemented, resulting in two classes. After three stages of classification, five atmosphere categories are obtained. At last, the text annotation of the atmosphere semantics and the corresponding features by Extensible Markup Language (XML) in MPEG-7 is defined, which can be integrated into more multimedia applications (such as searching, indexing and accessing of multimedia content). The experiment is performed on Corel images and film frames. The classification results prove the effectiveness of the definition of atmosphere semantic classes and the corresponding features.

  17. Texture-based classification for characterizing regions on remote sensing images (United States)

    Borne, Frédéric; Viennois, Gaëlle


    Remote sensing classification methods mostly use only the physical properties of pixels or complex texture indexes but do not lead to recommendation for practical applications. Our objective was to design a texture-based method, called the Paysages A PRIori method (PAPRI), which works both at pixel and neighborhood level and which can handle different spatial scales of analysis. The aim was to stay close to the logic of a human expert and to deal with co-occurrences in a more efficient way than other methods. The PAPRI method is pixelwise and based on a comparison of statistical and spatial reference properties provided by the expert with local properties computed in varying size windows centered on the pixel. A specific distance is computed for different windows around the pixel and a local minimum leads to choosing the class in which the pixel is to be placed. The PAPRI method brings a significant improvement in classification quality for different kinds of images, including aerial, lidar, high-resolution satellite images as well as texture images from the Brodatz and Vistex databases. This work shows the importance of texture analysis in understanding remote sensing images and for future developments.

  18. Material classification based on multi-band polarimetric images fusion (United States)

    Zhao, Yongqiang; Pan, Quan; Zhang, Hongcai


    Polarization imparted by surface reflections contains unique and discriminatory signatures which may augment spectral target-detection techniques. With the development of multi-band polarization imaging technology, it is becoming more and more important on how to integrate polarimetric, spatial and spectral information to improve target discrimination. In this study, investigations were performed on combining multi-band polarimetric images through false color mapping and wavelet integrated image fusion method. The objective of this effort was to extend the investigation of the use of polarized light to target detection and material classification. As there is great variation in polarization in and between each of the bandpasses, and this variation is comparable to the magnitude of the variation intensity. At the same time, the contrast in polarization is greater than for intensity, and that polarization contrast increases as intensity contrast decreases. It is also pointed out that chromaticity can be used to make targets stand out more clearly against background, and material can be divided into conductor and nonconductor through polarization information. So, through false color mapping, the difference part of polarimetric information between each of the bandpasses and common part of polarimetric information in each of the bandpasses are combined, in the resulting image the conductor and nonconductor are assigned different color. Then panchromatic polarimetric images are fused with resulting image through wavelet decomposition, the final fused image have more detail information and more easy identification. This study demonstrated, using digital image data collected by imaging spectropolarimeter, multi-band imaging polarimetry is likely to provide an advantage in target detection and material classification.

  19. Multiple Classifier System for Remote Sensing Image Classification: A Review

    Directory of Open Access Journals (Sweden)

    Yi Liu


    Full Text Available Over the last two decades, multiple classifier system (MCS or classifier ensemble has shown great potential to improve the accuracy and reliability of remote sensing image classification. Although there are lots of literatures covering the MCS approaches, there is a lack of a comprehensive literature review which presents an overall architecture of the basic principles and trends behind the design of remote sensing classifier ensemble. Therefore, in order to give a reference point for MCS approaches, this paper attempts to explicitly review the remote sensing implementations of MCS and proposes some modified approaches. The effectiveness of existing and improved algorithms are analyzed and evaluated by multi-source remotely sensed images, including high spatial resolution image (QuickBird, hyperspectral image (OMISII and multi-spectral image (Landsat ETM+.Experimental results demonstrate that MCS can effectively improve the accuracy and stability of remote sensing image classification, and diversity measures play an active role for the combination of multiple classifiers. Furthermore, this survey provides a roadmap to guide future research, algorithm enhancement and facilitate knowledge accumulation of MCS in remote sensing community.

  20. Evaluating the Effects of Shadow Detection on QuickBird Image Classification and Spectroradiometric Restoration

    Directory of Open Access Journals (Sweden)

    Marvin E. Bauer


    Full Text Available Shadows in high resolution imagery create significant problems for urban land cover classification and environmental application. We first investigated whether shadows were intrinsically different and hypothetically possible to separate from each other with ground spectral measurements. Both pixel-based and object-oriented methods were used to evaluate the effects of shadow detection on QuickBird image classification and spectroradiometric restoration. In each method, shadows were detected and separated either with or without histogram thresholding, and subsequently corrected with a k-nearest neighbor algorithm and a linear correlation correction. The results showed that shadows had distinct spectroradiometric characteristics, thus, could be detected with an optimal brightness threshold and further differentiated with a scene-based near infrared ratio. The pixel-based methods generally recognized more shadow areas and with statistically higher accuracy than the object-oriented methods. The effects of the prior shadow thresholding were not statistically significant. The accuracy of the final land cover classification, after accounting for the shadow detection and separation, was significantly higher for the pixel-based methods than for the object-oriented methods, although both achieved similar accuracy for the non-shadow classes. Both radiometric restoration algorithms significantly reduced shadow areas in the original satellite images.

  1. Landsat TM and ETM+ 2002-2003 Kansas Satellite Image Database (KSID) (United States)

    Kansas Data Access and Support Center — The Kansas Satellite Image Database (KSID):2002-2003 consists of image data gathered by three sensors. The first image data are terrain-corrected, precision...

  2. Multicriteria classification method for dimensionality reduction adapted to hyperspectral images (United States)

    Khoder, Mahdi; Kashana, Serge; Khoder, Jihan; Younes, Rafic


    Due to the incredible growth of high dimensional datasets, we address the problem of unsupervised methods sensitive to undergoing different variations, such as noise degradation, and to preserving rare information. Therefore, researchers nowadays are forced to develop techniques to meet the needed requirements. In this work, we introduce a dimensionality reduction method that focuses on the multiobjectives of multiple images taken from multiple frequency bands, which form a hyperspectral image. The multicriteria classification algorithm technique compares and classifies these images based on multiple similarity criteria, which allows the selection of particular images from the whole set of images. The selected images are the ones chosen to represent the original set of data while respecting certain quality thresholds. Knowing that the number of images in a hyperspectral image signifies its dimension, choosing a smaller number of images to represent the data leads to dimensionality reduction. Also, results of tests of the developed algorithm on multiple hyperspectral image samples are shown. A comparative study later on will show the advantages of this technique compared to other common methods used in the field of dimensionality reduction.

  3. Portable EDITOR (PEDITOR): A portable image processing system. [satellite images (United States)

    Angelici, G.; Slye, R.; Ozga, M.; Ritter, P.


    The PEDITOR image processing system was created to be readily transferable from one type of computer system to another. While nearly identical in function and operation to its predecessor, EDITOR, PEDITOR employs additional techniques which greatly enhance its portability. These cover system structure and processing. In order to confirm the portability of the software system, two different types of computer systems running greatly differing operating systems were used as target machines. A DEC-20 computer running the TOPS-20 operating system and using a Pascal Compiler was utilized for initial code development. The remaining programmers used a Motorola Corporation 68000-based Forward Technology FT-3000 supermicrocomputer running the UNIX-based XENIX operating system and using the Silicon Valley Software Pascal compiler and the XENIX C compiler for their initial code development.

  4. High-dimensional multispectral image fusion: classification by neural network (United States)

    He, Mingyi; Xia, Jiantao


    Advances in sensor technology for Earth observation make it possible to collect multispectral data in much higher dimensionality. Such high dimensional data will it possible to classify more classes. However, it will also have several impacts on processing technology. First, because of its huge data, more processing power will be needed to process such high dimensional data. Second, because of its high dimensionality and the limited training samples, it is very difficult for Bayes method to estimate the parameters accurately. So the classification accuracy cannot be high enough. Neural Network is an intelligent signal processing method. MLFNN (Multi-Layer Feedforward Neural Network) directly learn from training samples and the probability model needs not to be estimated, the classification may be conducted through neural network fusion of multispectral images. The latent information about different classes can be extracted from training samples by MLFNN. However, because of the huge data and high dimensionality, MLFNN will face some serious difficulties: (1) There are many local minimal points in the error surface of MLFNN; (2) Over-fitting phenomena. These two difficulties depress the classification accuracy and generalization performance of MLFNN. In order to overcome these difficulties, the author proposed DPFNN (Double Parallel Feedforward Neural Networks) used to classify the high dimensional multispectral images. The model and learning algorithm of DPFNN with strong generalization performance are proposed, with emphases on the regularization of output weights and improvement of the generalization performance of DPFNN. As DPFNN is composed of MLFNN and SLFNN (Single-Layer Feedforward Neural Network), it has the advantages of MLFNN and SLFNN: (1) Good nonlinear mapping capability; (2) High learning speed for linear-like problem. Experimental results with generated data, 64-band practical multispectral images and 220-band multispectral images show that the new

  5. Automated classification of Pap smear images to detect cervical dysplasia. (United States)

    Bora, Kangkana; Chowdhury, Manish; Mahanta, Lipi B; Kundu, Malay Kumar; Das, Anup Kumar


    The present study proposes an intelligent system for automatic categorization of Pap smear images to detect cervical dysplasia, which has been an open problem ongoing for last five decades. The classification technique is based on shape, texture and color features. It classifies the cervical dysplasia into two-level (normal and abnormal) and three-level (Negative for Intraepithelial Lesion or Malignancy, Low-grade Squamous Intraepithelial Lesion and High-grade Squamous Intraepithelial Lesion) classes reflecting the established Bethesda system of classification used for diagnosis of cancerous or precancerous lesion of cervix. The system is evaluated on two generated databases obtained from two diagnostic centers, one containing 1610 single cervical cells and the other 1320 complete smear level images. The main objective of this database generation is to categorize the images according to the Bethesda system of classification both of which require lots of training and expertise. The system is also trained and tested on the benchmark Herlev University database which is publicly available. In this contribution a new segmentation technique has also been proposed for extracting shape features. Ripplet Type I transform, Histogram first order statistics and Gray Level Co-occurrence Matrix have been used for color and texture features respectively. To improve classification results, ensemble method is used, which integrates the decision of three classifiers. Assessments are performed using 5 fold cross validation. Extended experiments reveal that the proposed system can successfully classify Pap smear images performing significantly better when compared with other existing methods. This type of automated cancer classifier will be of particular help in early detection of cancer. Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.

  6. A statistical approach to material classification using image patch exemplars. (United States)

    Varma, Manik; Zisserman, Andrew


    In this paper, we investigate material classification from single images obtained under unknown viewpoint and illumination. It is demonstrated that materials can be classified using the joint distribution of intensity values over extremely compact neighborhoods (starting from as small as 3 \\times 3 pixels square) and that this can outperform classification using filter banks with large support. It is also shown that the performance of filter banks is inferior to that of image patches with equivalent neighborhoods. We develop novel texton-based representations which are suited to modeling this joint neighborhood distribution for Markov random fields. The representations are learned from training images and then used to classify novel images (with unknown viewpoint and lighting) into texture classes. Three such representations are proposed and their performance is assessed and compared to that of filter banks. The power of the method is demonstrated by classifying 2,806 images of all 61 materials present in the Columbia-Utrecht database. The classification performance surpasses that of recent state-of-the-art filter bank-based classifiers such as Leung and Malik (IJCV 01), Cula and Dana (IJCV 04), and Varma and Zisserman (IJCV 05). We also benchmark performance by classifying all of the textures present in the UIUC, Microsoft Textile, and San Francisco outdoor data sets. We conclude with discussions on why features based on compact neighborhoods can correctly discriminate between textures with large global structure and why the performance of filter banks is not superior to that of the source image patches from which they were derived.

  7. Detection of urban environments using advanced land observing satellite phased array type L-band synthetic aperture radar data through different classification techniques (United States)

    Pradhan, Biswajeet; Abdullahi, Saleh; Seddighi, Younes


    Urban environments are very dynamic phenomena, and it is essential to update urban-related information for various applications. In this regard, remotely sensed data have been utilized widely to extract and monitor urban land use and land cover changes. Particularly, synthetic aperture radar (SAR) data, due to several advantages of this technology in comparison to passive sensors, provides better performance especially in tropical regions. However, the methodological approaches for extraction of information from SAR images are another important task that needs to be considered appropriately. This paper attempts to investigate and compare the performance of different image classification techniques for extracting urban areas using advanced land observing satellite phased array type L-band synthetic aperture radar imagery. Several object- [such as rule based (RB), support vector machine (SVM) and K-nearest neighbor (K-NN)] and pixel-based [decision tree (DT)] classification techniques were implemented, and their results were compared in detail. The overall results indicated RB classification performed better than other techniques. Furthermore, DT method, due to its predefined rules, distinguished the land cover classes better than SVM and K-NN, which were based on training datasets. Nevertheless, this study confirms the potential of SAR data and object-based classification techniques in urban detection and land cover mapping.

  8. Object-oriented classification using quasi-synchronous multispectral images (optical and radar) over agricultural surface (United States)

    Marais Sicre, Claire; Baup, Frederic; Fieuzal, Remy


    In the context of climate change (with consequences on temperature and precipitation patterns), persons involved in agricultural management have the imperative to combine: sufficient productivity (as a response of the increment of the necessary foods) and durability of the resources (in order to restrain waste of water, fertilizer or environmental damages). To this end, a detailed knowledge of land use will improve the management of food and water, while preserving the ecosystems. Among the wide range of available monitoring tools, numerous studies demonstrated the interest of satellite images for agricultural mapping. Recently, the launch of several radar and optical sensors offer new perspectives for the multi-wavelength crop monitoring (Terrasar-X, Radarsat-2, Sentinel-1, Landsat-8…) allowing surface survey whatever the cloud conditions. Previous studies have demonstrated the interest of using multi-temporal approaches for crop classification, requiring several images for suitable classification results. Unfortunately, these approaches are limited (due to the satellite orbit cycle) and require waiting several days, week or month before offering an accurate land use map. The objective of this study is to compare the accuracy of object-oriented classification (random forest algorithm combined with vector layer coming from segmentation) to map winter crop (barley, rapeseed, grasslands and wheat) and soil states (bare soils with different surface roughness) using quasi-synchronous images. Satellite data are composed of multi-frequency and multi-polarization (HH, VV, HV and VH) images acquired near the 14th of April, 2010, over a studied area (90km²) located close to Toulouse in France. This is a region of alluvial plains and hills, which are mostly mixed farming and governed by a temperate climate. Remote sensing images are provided by Formosat-2 (04/18), Radarsat-2 (C-band, 04/15), Terrasar-X (X-band, 04/14) and ALOS (L-band, 04/14). Ground data are collected

  9. Classification of ADHD children through multimodal magnetic resonance imaging. (United States)

    Dai, Dai; Wang, Jieqiong; Hua, Jing; He, Huiguang


    Attention deficit/hyperactivity disorder (ADHD) is one of the most common diseases in school-age children. To date, the diagnosis of ADHD is mainly subjective and studies of objective diagnostic method are of great importance. Although many efforts have been made recently to investigate the use of structural and functional brain images for the diagnosis purpose, few of them are related to ADHD. In this paper, we introduce an automatic classification framework based on brain imaging features of ADHD patients and present in detail the feature extraction, feature selection, and classifier training methods. The effects of using different features are compared against each other. In addition, we integrate multimodal image features using multi-kernel learning (MKL). The performance of our framework has been validated in the ADHD-200 Global Competition, which is a world-wide classification contest on the ADHD-200 datasets. In this competition, our classification framework using features of resting-state functional connectivity (FC) was ranked the 6th out of 21 participants under the competition scoring policy and performed the best in terms of sensitivity and J-statistic.

  10. Classification of ADHD children through multimodal Magnetic Resonance Imaging

    Directory of Open Access Journals (Sweden)

    Dai eDai


    Full Text Available Attention deficit/hyperactivity disorder (ADHD is one of the most common diseases in school-age children. To date, the diagnosis of ADHD is mainly subjective and studies of objective diagnostic method are of great importance. Although many efforts have been made recently to investigate the use of structural and functional brain images for the diagnosis purpose, few of them are related to ADHD. In this paper, we introduce an automatic classification framework based on brain imaging features of ADHD patients, and present in detail the feature extraction, feature selection and classifier training methods. The effects of using different features are compared against each other. In addition, we integrate multimodal image features using multi-kernel learning (MKL. The performance of our framework has been validated in the ADHD-200 Global Competition, which is a world-wide classification contest on the ADHD-200 datasets. In this competition, our classification framework using features of resting-state functional connectivity was ranked the 6th out of 21 participants under the competition scoring policy, and performed the best in terms of sensitivity and J-statistic.

  11. Multiview Discriminative Geometry Preserving Projection for Image Classification

    Directory of Open Access Journals (Sweden)

    Ziqiang Wang


    Full Text Available In many image classification applications, it is common to extract multiple visual features from different views to describe an image. Since different visual features have their own specific statistical properties and discriminative powers for image classification, the conventional solution for multiple view data is to concatenate these feature vectors as a new feature vector. However, this simple concatenation strategy not only ignores the complementary nature of different views, but also ends up with “curse of dimensionality.” To address this problem, we propose a novel multiview subspace learning algorithm in this paper, named multiview discriminative geometry preserving projection (MDGPP for feature extraction and classification. MDGPP can not only preserve the intraclass geometry and interclass discrimination information under a single view, but also explore the complementary property of different views to obtain a low-dimensional optimal consensus embedding by using an alternating-optimization-based iterative algorithm. Experimental results on face recognition and facial expression recognition demonstrate the effectiveness of the proposed algorithm.

  12. Arctic Ecological Classifications Derived from Vegetation Community and Satellite Spectral Data

    Directory of Open Access Journals (Sweden)

    David M. Atkinson


    Full Text Available As a result of the warming observed at high latitudes, there is significant potential for the balance of ecosystem processes to change, i.e., the balance between carbon sequestration and respiration may be altered, giving rise to the release of soil carbon through elevated ecosystem respiration. Gross ecosystem productivity and ecosystem respiration vary in relation to the pattern of vegetation community type and associated biophysical traits (e.g., percent cover, biomass, chlorophyll concentration, etc.. In an arctic environment where vegetation is highly variable across the landscape, the use of high spatial resolution imagery can assist in discerning complex patterns of vegetation and biophysical variables. The research presented here examines the relationship between ecological and spectral variables in order to generate an ecologically meaningful vegetation classification from high spatial resolution remote sensing data. Our methodology integrates ordination and image classifications techniques for two non-overlapping Arctic sites across a 5° latitudinal gradient (approximately 70° to 75°N. Ordination techniques were applied to determine the arrangement of sample sites, in relation to environmental variables, followed by cluster analysis to create ecological classes. The derived classes were then used to classify high spatial resolution IKONOS multispectral data. The results demonstrate moderate levels of success. Classifications had overall accuracies between 69%–79% and Kappa values of 0.54–0.69. Vegetation classes were generally distinct at each site with the exception of sedge wetlands. Based on the results presented here, the combination of ecological and remote sensing techniques can produce classifications that have ecological meaning and are spectrally separable in an arctic environment. These classification schemes are critical for modeling ecosystem processes.

  13. Instrument calibration architecture of Radar Imaging Satellite (RISAT-1) (United States)

    Misra, T.; Bhan, R.; Putrevu, D.; Mehrotra, P.; Nandy, P. S.; Shukla, S. D.; Rao, C. V. N.; Dave, D. B.; Desai, N. M.


    Radar Imaging Satellite (RISAT-1) payload system is configured to perform self-calibration of transmit and receive paths before and after imaging sessions through a special instrument calibration technique. Instrument calibration architecture of RISAT-1 supported ground verification and validation of payload including active array antenna. During on-ground validation of 126 beams of active array antenna which needed precise calibration of boresight pointing, a unique method called "collimation coefficient error estimation" was utilized. This method of antenna calibration was supported by special hardware and software calibration architecture of RISAT-1. This paper concentrates on RISAT-1 hardware and software architecture which supports in-orbit and on-ground instrument calibration. Efforts are also put here to highlight use of special calibration scheme of RISAT-1 instrument to evaluate system response during ground verification and validation.

  14. Advanced DTM Generation from Very High Resolution Satellite Stereo Images (United States)

    Perko, R.; Raggam, H.; Gutjahr, K. H.; Schardt, M.


    This work proposes a simple filtering approach that can be applied to digital surface models in order to extract digital terrain models. The method focusses on robustness and computational efficiency and is in particular tailored to filter DSMs that are extracted from satellite stereo images. It represents an evolution of an existing DTM generation method and includes distinct advancement through the integration of multi-directional processing as well as slope dependent filtering, thus denoted "MSD filtering". The DTM generation workflow is fully automatic and requires no user interaction. Exemplary results are presented for a DSM generated from a Pléiades tri-stereo image data set. Qualitative and quantitative evaluations with respect to highly accurate reference LiDAR data confirm the effectiveness of the proposed algorithm.

  15. Study on classification of pork quality using hyperspectral imaging technique (United States)

    Zeng, Shan; Bai, Jun; Wang, Haibin


    The relative problems' research of chilled meat, thawed meat and spoiled meat discrimination by hyperspectral image technique were proposed, such the section of feature wavelengths, et al. First, based on 400 ~ 1000nm range hyperspectral image data of testing pork samples, by K-medoids clustering algorithm based on manifold distance, we select 30 important wavelengths from 753 wavelengths, and thus select 8 feature wavelengths (454.4, 477.5, 529.3, 546.8, 568.4, 580.3, 589.9 and 781.2nm) based on the discrimination value. Then 8 texture features of each image under 8 feature wavelengths were respectively extracted by two-dimensional Gabor wavelets transform as pork quality feature. Finally, we build a pork quality classification model using the fuzzy C-mean clustering algorithm. Through the experiment of extracting feature wavelengths, we found that although the hyperspectral images between adjacent bands have a strong linear correlation, they show a significant non-linear manifold relationship from the entire band. K-medoids clustering algorithm based on manifold distance used in this paper for selecting the characteristic wavelengths, which is more reasonable than traditional principal component analysis (PCA). Through the classification result, we conclude that hyperspectral imaging technology can distinguish among chilled meat, thawed meat and spoiled meat accurately.

  16. A Dataset for Breast Cancer Histopathological Image Classification. (United States)

    Spanhol, Fabio A; Oliveira, Luiz S; Petitjean, Caroline; Heutte, Laurent


    Today, medical image analysis papers require solid experiments to prove the usefulness of proposed methods. However, experiments are often performed on data selected by the researchers, which may come from different institutions, scanners, and populations. Different evaluation measures may be used, making it difficult to compare the methods. In this paper, we introduce a dataset of 7909 breast cancer histopathology images acquired on 82 patients, which is now publicly available from The dataset includes both benign and malignant images. The task associated with this dataset is the automated classification of these images in two classes, which would be a valuable computer-aided diagnosis tool for the clinician. In order to assess the difficulty of this task, we show some preliminary results obtained with state-of-the-art image classification systems. The accuracy ranges from 80% to 85%, showing room for improvement is left. By providing this dataset and a standardized evaluation protocol to the scientific community, we hope to gather researchers in both the medical and the machine learning field to advance toward this clinical application.

  17. Use of satellite images for the monitoring of water systems (United States)

    Hillebrand, Gudrun; Winterscheid, Axel; Baschek, Björn; Wolf, Thomas


    Satellite images are a proven source of information for monitoring ecological indicators in coastal waters and inland river systems. This potential of remote sensing products was demonstrated by recent research projects (e.g. EU-funded project Freshmon - and other activities by national institutions. Among indicators for water quality, a particular focus was set on the temporal and spatial dynamics of suspended particulate matter (SPM) and Chlorophyll-a (Chl-a). The German Federal Institute of Hydrology (BfG) was using the Weser and Elbe estuaries as test cases to compare in-situ measurements with results obtained from a temporal series of automatically generated maps of SPM distributions based on remote sensing data. Maps of SPM and Chl-a distributions in European inland rivers and alpine lakes were generated by the Freshmon Project. Earth observation based products are a valuable source for additional data that can well supplement in-situ monitoring. For 2015, the BfG and the Institute for Lake Research of the State Institute for the Environment, Measurements and Nature Conservation of Baden-Wuerttemberg, Germany (LUBW) are in the process to start implementing an operational service for monitoring SPM and Chl-a based on satellite images (Landsat 7 & 8, Sentinel 2, and if required other systems with higher spatial resolution, e.g. Rapid Eye). In this 2-years project, which is part of the European Copernicus Programme, the operational service will be set up for - the inland rivers of Rhine and Elbe - the North Sea estuaries of Elbe, Weser and Ems. Furthermore - Lake Constance and other lakes located within the Federal State of Baden-Wuerttemberg. In future, the service can be implemented for other rivers and lakes as well. Key feature of the project is a data base that holds the stock of geo-referenced maps of SPM and Chl-a distributions. Via web-based portals (e.g. GGInA - geo-portal of the BfG; UIS - environmental information system of the


    Directory of Open Access Journals (Sweden)

    N. Ghasemian


    Full Text Available The goal of ensemble learning methods like Bagging and Boosting is to improve the classification results of some weak classifiers gradually. Usually, Boosting algorithms show better results than Bagging. In this article, we have examined the possibility of fusion of non-thermal and thermal bands of Landsat 8 satellite images for cloud detection by using the boosting method. We used SVM as a base learner and the performance of two kinds of Boosting methods including AdaBoost.M1 and σ Boost was compared on remote sensing images of Landsat 8 satellite. We first extracted the co-occurrence matrix features of non-thermal and thermal bands separately and then used PCA method for feature selection. In the next step AdaBoost.M1 and σ Boost algorithms were applied on non-thermal and thermal bands and finally, the classifiers were fused using majority voting. Also, we showed that by changing the regularization parameter (C the result of σ Boost algorithm can significantly change and achieve overall accuracy and cloud producer accuracy of 74%, and 0.53 kappa coefficient that shows better results in comparison to AdaBoost.M1.

  19. Fusion of Non-Thermal and Thermal Satellite Images by Boosted Svm Classifiers for Cloud Detection (United States)

    Ghasemian, N.; Akhoondzadeh, M.


    The goal of ensemble learning methods like Bagging and Boosting is to improve the classification results of some weak classifiers gradually. Usually, Boosting algorithms show better results than Bagging. In this article, we have examined the possibility of fusion of non-thermal and thermal bands of Landsat 8 satellite images for cloud detection by using the boosting method. We used SVM as a base learner and the performance of two kinds of Boosting methods including AdaBoost.M1 and σ Boost was compared on remote sensing images of Landsat 8 satellite. We first extracted the co-occurrence matrix features of non-thermal and thermal bands separately and then used PCA method for feature selection. In the next step AdaBoost.M1 and σ Boost algorithms were applied on non-thermal and thermal bands and finally, the classifiers were fused using majority voting. Also, we showed that by changing the regularization parameter (C) the result of σ Boost algorithm can significantly change and achieve overall accuracy and cloud producer accuracy of 74%, and 0.53 kappa coefficient that shows better results in comparison to AdaBoost.M1.

  20. Classification of multispectral or hyperspectral satellite imagery using clustering of sparse approximations on sparse representations in learned dictionaries obtained using efficient convolutional sparse coding

    Energy Technology Data Exchange (ETDEWEB)

    Moody, Daniela; Wohlberg, Brendt


    An approach for land cover classification, seasonal and yearly change detection and monitoring, and identification of changes in man-made features may use a clustering of sparse approximations (CoSA) on sparse representations in learned dictionaries. The learned dictionaries may be derived using efficient convolutional sparse coding to build multispectral or hyperspectral, multiresolution dictionaries that are adapted to regional satellite image data. Sparse image representations of images over the learned dictionaries may be used to perform unsupervised k-means clustering into land cover categories. The clustering process behaves as a classifier in detecting real variability. This approach may combine spectral and spatial textural characteristics to detect geologic, vegetative, hydrologic, and man-made features, as well as changes in these features over time.

  1. Active machine learning for rapid landslide inventory mapping with VHR satellite images (Invited) (United States)

    Stumpf, A.; Lachiche, N.; Malet, J.; Kerle, N.; Puissant, A.


    VHR satellite images have become a primary source for landslide inventory mapping after major triggering events such as earthquakes and heavy rainfalls. Visual image interpretation is still the prevailing standard method for operational purposes but is time-consuming and not well suited to fully exploit the increasingly better supply of remote sensing data. Recent studies have addressed the development of more automated image analysis workflows for landslide inventory mapping. In particular object-oriented approaches that account for spatial and textural image information have been demonstrated to be more adequate than pixel-based classification but manually elaborated rule-based classifiers are difficult to adapt under changing scene characteristics. Machine learning algorithm allow learning classification rules for complex image patterns from labelled examples and can be adapted straightforwardly with available training data. In order to reduce the amount of costly training data active learning (AL) has evolved as a key concept to guide the sampling for many applications. The underlying idea of AL is to initialize a machine learning model with a small training set, and to subsequently exploit the model state and data structure to iteratively select the most valuable samples that should be labelled by the user. With relatively few queries and labelled samples, an AL strategy yields higher accuracies than an equivalent classifier trained with many randomly selected samples. This study addressed the development of an AL method for landslide mapping from VHR remote sensing images with special consideration of the spatial distribution of the samples. Our approach [1] is based on the Random Forest algorithm and considers the classifier uncertainty as well as the variance of potential sampling regions to guide the user towards the most valuable sampling areas. The algorithm explicitly searches for compact regions and thereby avoids a spatially disperse sampling pattern

  2. Spatial, Temporal and Spectral Satellite Image Fusion via Sparse Representation (United States)

    Song, Huihui

    Remote sensing provides good measurements for monitoring and further analyzing the climate change, dynamics of ecosystem, and human activities in global or regional scales. Over the past two decades, the number of launched satellite sensors has been increasing with the development of aerospace technologies and the growing requirements on remote sensing data in a vast amount of application fields. However, a key technological challenge confronting these sensors is that they tradeoff between spatial resolution and other properties, including temporal resolution, spectral resolution, swath width, etc., due to the limitations of hardware technology and budget constraints. To increase the spatial resolution of data with other good properties, one possible cost-effective solution is to explore data integration methods that can fuse multi-resolution data from multiple sensors, thereby enhancing the application capabilities of available remote sensing data. In this thesis, we propose to fuse the spatial resolution with temporal resolution and spectral resolution, respectively, based on sparse representation theory. Taking the study case of Landsat ETM+ (with spatial resolution of 30m and temporal resolution of 16 days) and MODIS (with spatial resolution of 250m ~ 1km and daily temporal resolution) reflectance, we propose two spatial-temporal fusion methods to combine the fine spatial information of Landsat image and the daily temporal resolution of MODIS image. Motivated by that the images from these two sensors are comparable on corresponding bands, we propose to link their spatial information on available Landsat- MODIS image pair (captured on prior date) and then predict the Landsat image from the MODIS counterpart on prediction date. To well-learn the spatial details from the prior images, we use a redundant dictionary to extract the basic representation atoms for both Landsat and MODIS images based on sparse representation. Under the scenario of two prior Landsat

  3. Determination of rice canopy growth based on high resolution satellite images: a case study using RapidEye imagery in Korea

    Directory of Open Access Journals (Sweden)

    Mijeong Kim


    Full Text Available Processing to correct atmospheric effects and classify all constituent pixels in a remote sensing image is required before the image is used to monitor plant growth. The raw image contains artifacts due to atmospheric conditions at the time of acquisition. This study sought to distinguish the canopy growth of paddy rice using RapidEye (BlackBridge, Berlin, Germany satellite data and investigate practical image correction and classification methods. The RapidEye images were taken over experimental fields of paddy rice at Chonnam National University (CNU, Gwangju, and at TaeAn, Choongcheongnam-do, Korea. The CNU RapidEye images were used to evaluate the atmospheric correction methods. Atmospheric correction of the RapidEye images was performed using three different methods, QUick Atmospheric Correction (QUAC, Fast Line-of-sight Atmospheric Analysis of Spectral Hypercubes (FLAASH, and Atmospheric and Topographic Correction (ATCOR. To minimize errors in utilizing observed growth and yield estimation of paddy rice, the paddy fields were classified using a supervised classification method and normalized difference vegetation index (NDVI thresholds, using the NDVI time-series features of the paddy fields. The results of the atmospheric correction using ATCOR on the satellite images were favorable, which correspond to those from reference UAV images. Meanwhile, the classification method using the NDVI threshold accurately classified the same pixels from each of the time-series images. We have demonstrated that the image correction and classification methods investigated here should be applicable to high resolution satellite images used in monitoring other crop growth conditions.

  4. Assessment of geostatistical features for object-based image classification of contrasted landscape vegetation cover (United States)

    de Oliveira Silveira, Eduarda Martiniano; de Menezes, Michele Duarte; Acerbi Júnior, Fausto Weimar; Castro Nunes Santos Terra, Marcela; de Mello, José Márcio


    Accurate mapping and monitoring of savanna and semiarid woodland biomes are needed to support the selection of areas of conservation, to provide sustainable land use, and to improve the understanding of vegetation. The potential of geostatistical features, derived from medium spatial resolution satellite imagery, to characterize contrasted landscape vegetation cover and improve object-based image classification is studied. The study site in Brazil includes cerrado sensu stricto, deciduous forest, and palm swamp vegetation cover. Sentinel 2 and Landsat 8 images were acquired and divided into objects, for each of which a semivariogram was calculated using near-infrared (NIR) and normalized difference vegetation index (NDVI) to extract the set of geostatistical features. The features selected by principal component analysis were used as input data to train a random forest algorithm. Tests were conducted, combining spectral and geostatistical features. Change detection evaluation was performed using a confusion matrix and its accuracies. The semivariogram curves were efficient to characterize spatial heterogeneity, with similar results using NIR and NDVI from Sentinel 2 and Landsat 8. Accuracy was significantly greater when combining geostatistical features with spectral data, suggesting that this method can improve image classification results.

  5. Land cover classification in multispectral satellite imagery using sparse approximations on learned dictionaries (United States)

    Moody, Daniela I.; Brumby, Steven P.; Rowland, Joel C.; Altmann, Garrett L.


    Techniques for automated feature extraction, including neuroscience-inspired machine vision, are of great interest for landscape characterization and change detection in support of global climate change science and modeling. We present results from an ongoing effort to extend machine vision methodologies to the environmental sciences, using state-of-theart adaptive signal processing, combined with compressive sensing and machine learning techniques. We use a modified Hebbian learning rule to build spectral-textural dictionaries that are tailored for classification. We learn our dictionaries from millions of overlapping multispectral image patches and then use a pursuit search to generate classification features. Land cover labels are automatically generated using CoSA: unsupervised Clustering of Sparse Approximations. We demonstrate our method on multispectral WorldView-2 data from a coastal plain ecosystem in Barrow, Alaska (USA). Our goal is to develop a robust classification methodology that will allow for automated discretization of the landscape into distinct units based on attributes such as vegetation, surface hydrological properties (e.g., soil moisture and inundation), and topographic/geomorphic characteristics. In this paper, we explore learning from both raw multispectral imagery, as well as normalized band difference indexes. We explore a quantitative metric to evaluate the spectral properties of the clusters, in order to potentially aid in assigning land cover categories to the cluster labels.

  6. Texture-Based Automated Lithological Classification Using Aeromagenetic Anomaly Images (United States)

    Shankar, Vivek


    This report consists of a thesis submitted to the faculty of the Department of Electrical and Computer Engineering, in partial fulfillment of the requirements for the degree of Master of Science, Graduate College, The University of Arizona, 2004 Aeromagnetic anomaly images are geophysical prospecting tools frequently used in the exploration of metalliferous minerals and hydrocarbons. The amplitude and texture content of these images provide a wealth of information to geophysicists who attempt to delineate the nature of the Earth's upper crust. These images prove to be extremely useful in remote areas and locations where the minerals of interest are concealed by basin fill. Typically, geophysicists compile a suite of aeromagnetic anomaly images, derived from amplitude and texture measurement operations, in order to obtain a qualitative interpretation of the lithological (rock) structure. Texture measures have proven to be especially capable of capturing the magnetic anomaly signature of unique lithological units. We performed a quantitative study to explore the possibility of using texture measures as input to a machine vision system in order to achieve automated classification of lithological units. This work demonstrated a significant improvement in classification accuracy over random guessing based on a priori probabilities. Additionally, a quantitative comparison between the performances of five classes of texture measures in their ability to discriminate lithological units was achieved.

  7. Classification of breast cancer histology images using Convolutional Neural Networks.

    Directory of Open Access Journals (Sweden)

    Teresa Araújo

    Full Text Available Breast cancer is one of the main causes of cancer death worldwide. The diagnosis of biopsy tissue with hematoxylin and eosin stained images is non-trivial and specialists often disagree on the final diagnosis. Computer-aided Diagnosis systems contribute to reduce the cost and increase the efficiency of this process. Conventional classification approaches rely on feature extraction methods designed for a specific problem based on field-knowledge. To overcome the many difficulties of the feature-based approaches, deep learning methods are becoming important alternatives. A method for the classification of hematoxylin and eosin stained breast biopsy images using Convolutional Neural Networks (CNNs is proposed. Images are classified in four classes, normal tissue, benign lesion, in situ carcinoma and invasive carcinoma, and in two classes, carcinoma and non-carcinoma. The architecture of the network is designed to retrieve information at different scales, including both nuclei and overall tissue organization. This design allows the extension of the proposed system to whole-slide histology images. The features extracted by the CNN are also used for training a Support Vector Machine classifier. Accuracies of 77.8% for four class and 83.3% for carcinoma/non-carcinoma are achieved. The sensitivity of our method for cancer cases is 95.6%.

  8. Tongue Images Classification Based on Constrained High Dispersal Network

    Directory of Open Access Journals (Sweden)

    Dan Meng


    Full Text Available Computer aided tongue diagnosis has a great potential to play important roles in traditional Chinese medicine (TCM. However, the majority of the existing tongue image analyses and classification methods are based on the low-level features, which may not provide a holistic view of the tongue. Inspired by deep convolutional neural network (CNN, we propose a novel feature extraction framework called constrained high dispersal neural networks (CHDNet to extract unbiased features and reduce human labor for tongue diagnosis in TCM. Previous CNN models have mostly focused on learning convolutional filters and adapting weights between them, but these models have two major issues: redundancy and insufficient capability in handling unbalanced sample distribution. We introduce high dispersal and local response normalization operation to address the issue of redundancy. We also add multiscale feature analysis to avoid the problem of sensitivity to deformation. Our proposed CHDNet learns high-level features and provides more classification information during training time, which may result in higher accuracy when predicting testing samples. We tested the proposed method on a set of 267 gastritis patients and a control group of 48 healthy volunteers. Test results show that CHDNet is a promising method in tongue image classification for the TCM study.

  9. [A coarse-to-fine registration method for satellite infrared image and visual image]. (United States)

    Hu, Yong-Li; Wang, Liang; Liu, Rong; Zhang, Li; Duan, Fu-Qing


    In the present paper, in order to resolve the registration of the multi-mode satellite images with different signal properties and features, a two-phase coarse-to-fine registration method is presented and is applied to the registration of satellite infrared images and visual images. In the coarse registration phase of this method, the edge of infrared and visual images is firstly detected. Then the Fourier-Mellin transform is adopted to process the edge images. Finally, the affine transformation parameters of the registration are computed rapidly by the transformation relation between the registering images in frequency domain. In the fine registration phase of the proposed method, the feature points of infrared and visual images are firstly detected by Harris operator. Then the matched feature points of infrared and visual images are determined by the cross-correlation similarity of their local neighborhoods. The fine registration is finally realized according to the spatial correspondent relation of the matched feature points in infrared and visual images. The proposed coarse-to-fine registration method derives both the advantages of two methods, the high efficiency of Fourier-Mellin transform based registration method and the accuracy of Harris operator based registration method, which is considered the novelty and merit of the proposed method. To evaluate the performance of the proposed registration method, the coarse-to-fine registration method is implemented on the infrared and visual images captured by the FY-2D meteorological satellite. The experimental results show that the presented registration method is robust and has acceptable registration accuracy.

  10. Vegetation mapping from high-resolution satellite images in the heterogeneous arid environments of Socotra Island (Yemen) (United States)

    Malatesta, Luca; Attorre, Fabio; Altobelli, Alfredo; Adeeb, Ahmed; De Sanctis, Michele; Taleb, Nadim M.; Scholte, Paul T.; Vitale, Marcello


    Socotra Island (Yemen), a global biodiversity hotspot, is characterized by high geomorphological and biological diversity. In this study, we present a high-resolution vegetation map of the island based on combining vegetation analysis and classification with remote sensing. Two different image classification approaches were tested to assess the most accurate one in mapping the vegetation mosaic of Socotra. Spectral signatures of the vegetation classes were obtained through a Gaussian mixture distribution model, and a sequential maximum a posteriori (SMAP) classification was applied to account for the heterogeneity and the complex spatial pattern of the arid vegetation. This approach was compared to the traditional maximum likelihood (ML) classification. Satellite data were represented by a RapidEye image with 5 m pixel resolution and five spectral bands. Classified vegetation relevés were used to obtain the training and evaluation sets for the main plant communities. Postclassification sorting was performed to adjust the classification through various rule-based operations. Twenty-eight classes were mapped, and SMAP, with an accuracy of 87%, proved to be more effective than ML (accuracy: 66%). The resulting map will represent an important instrument for the elaboration of conservation strategies and the sustainable use of natural resources in the island.

  11. Textural features and neural network for image classification (United States)

    Haddadi, Souad; Fernandez, C.; Abdelnour, F.


    In this paper, we present a neural network approach for scene analysis: detection of human beings in images. To solve this problem, a precise classification system is required, with adaptation systems based on data processing. These systems must be largely parallel, which is why neural networks have been chosen. The first part of this text is a brief introduction to neural networks and their applications. The second part is a description of the image base composed for experiments and the low-level processing used, then we detail the method used to extract the texture feature of images. The third part describes the Bayesian method and its application to our problem. Part four shows the association of these texture processes with the neural network for identification of human beings. Finally, we conclude with the validity of the method and its future applications.

  12. Classification of hyperspectral images based on conditional random fields (United States)

    Hu, Yang; Saber, Eli; Monteiro, Sildomar T.; Cahill, Nathan D.; Messinger, David W.


    A significant increase in the availability of high resolution hyperspectral images has led to the need for developing pertinent techniques in image analysis, such as classification. Hyperspectral images that are correlated spatially and spectrally provide ample information across the bands to benefit this purpose. Conditional Random Fields (CRFs) are discriminative models that carry several advantages over conventional techniques: no requirement of the independence assumption for observations, flexibility in defining local and pairwise potentials, and an independence between the modules of feature selection and parameter leaning. In this paper we present a framework for classifying remotely sensed imagery based on CRFs. We apply a Support Vector Machine (SVM) classifier to raw remotely sensed imagery data in order to generate more meaningful feature potentials to the CRFs model. This approach produces promising results when tested with publicly available AVIRIS Indian Pine imagery.

  13. Palmer Classification and Magnetic Resonance Imaging Findings of Ulnocarpal Impingement. (United States)

    Ersoy, Hale; Pomeranz, Stephen J


    Ulnocarpal impaction (UCI) syndrome is a well-recognized and relatively frequent cause of ulnar-sided wrist pain and limitation of motion. In the setting of negative or questionable negative radiographs and a strong clinical suspicion for UCI, magnetic resonance imaging (MRI) is helpful in detecting occult disease. Current MRI technology is capable of providing high-spatial-resolution images on multiple planes while manipulating contrast to highlight different tissue types. However, imaging of the triangular fibrocartilage complex has been challenging because of the small and complex components of this structure. In this article, the stages of UCI are discussed with illustrations of the spectrum of MRI findings using Palmer classification as a guideline.

  14. Determination of Destructed and Infracted Forest Areas with Multi-temporal High Resolution Satellite Images (United States)

    Seker, D. Z.; Unal, A.; Kaya, S.; Alganci, U.


    Migration from rural areas to city centers and their surroundings is an important problem of not only our country but also the countries that under development stage. This uncontrolled and huge amount of migration brings out urbanization and socio - economic problems. The demand on settling the industrial areas and commercial activities nearby the city centers results with a negative change in natural land cover on cities. Negative impacts of human induced activities on natural resources and land cover has been continuously increasing for decades. The main human activities that resulted with destruction and infraction of forest areas can be defined as mining activities, agricultural activities, industrial / commercial activities and urbanization. Temporal monitoring of the changes in spatial distribution of forest areas is significantly important for effective management and planning progress. Changes can occur as spatially large destructions or small infractions. Therefore there is a need for reliable, fast and accurate data sources. At this point, satellite images proved to be a good data source for determination of the land use /cover changes with their capability of monitoring large areas with reasonable temporal resolutions. Spectral information derived from images provides discrimination of land use/cover types from each other. Developments in remote sensing technology in the last decade improved the spatial resolution of satellites and high resolution images were started to be used to detect even small changes in the land surface. As being the megacity of Turkey, Istanbul has been facing a huge migration for the last 20 years and effects of urbanization and other human based activities over forest areas are significant. Main focus of this study is to determine the destructions and infractions in forest areas of Istanbul, Turkey with 2.5m resolution SPOT 5 multi-temporal satellite imagery. Analysis was mainly constructed on threshold based classification of

  15. Identification and classification of structural soil conservation measures based on very high resolution stereo satellite data. (United States)

    Eckert, Sandra; Tesfay Ghebremicael, Selamawit; Hurni, Hans; Kohler, Thomas


    Land degradation affects large areas of land around the globe, with grave consequences for those living off the land. Major efforts are being made to implement soil and water conservation measures that counteract soil erosion and help secure vital ecosystem services. However, where and to what extent such measures have been implemented is often not well documented. Knowledge about this could help to identify areas where soil and water conservation measures are successfully supporting sustainable land management, as well as areas requiring urgent rehabilitation of conservation structures such as terraces and bunds. This study explores the potential of the latest satellite-based remote sensing technology for use in assessing and monitoring the extent of existing soil and water conservation structures. We used a set of very high resolution stereo Geoeye-1 satellite data, from which we derived a detailed digital surface model as well as a set of other spectral, terrain, texture, and filtered information layers. We developed and applied an object-based classification approach, working on two segmentation levels. On the coarser level, the aim was to delimit certain landscape zones. Information about these landscape zones is useful in distinguishing different types of soil and water conservation structures, as each zone contains certain specific types of structures. On the finer level, the goal was to extract and identify different types of linear soil and water conservation structures. The classification rules were based mainly on spectral, textural, shape, and topographic properties, and included object relationships. This approach enabled us to identify and separate from other classes the majority (78.5%) of terraces and bunds, as well as most hillside terraces (81.25%). Omission and commission errors are similar to those obtained by the few existing studies focusing on the same research objective but using different types of remotely sensed data. Based on our results

  16. Classification of bacterial contamination using image processing and distributed computing. (United States)

    Ahmed, W M; Bayraktar, B; Bhunia, A; Hirleman, E D; Robinson, J P; Rajwa, B


    Disease outbreaks due to contaminated food are a major concern not only for the food-processing industry but also for the public at large. Techniques for automated detection and classification of microorganisms can be a great help in preventing outbreaks and maintaining the safety of the nations food supply. Identification and classification of foodborne pathogens using colony scatter patterns is a promising new label-free technique that utilizes image-analysis and machine-learning tools. However, the feature-extraction tools employed for this approach are computationally complex, and choosing the right combination of scatter-related features requires extensive testing with different feature combinations. In the presented work we used computer clusters to speed up the feature-extraction process, which enables us to analyze the contribution of different scatter-based features to the overall classification accuracy. A set of 1000 scatter patterns representing ten different bacterial strains was used. Zernike and Chebyshev moments as well as Haralick texture features were computed from the available light-scatter patterns. The most promising features were first selected using Fishers discriminant analysis, and subsequently a support-vector-machine (SVM) classifier with a linear kernel was used. With extensive testing we were able to identify a small subset of features that produced the desired results in terms of classification accuracy and execution speed. The use of distributed computing for scatter-pattern analysis, feature extraction, and selection provides a feasible mechanism for large-scale deployment of a light scatter-based approach to bacterial classification.

  17. Magnetic resonance imaging texture analysis classification of primary breast cancer. (United States)

    Waugh, S A; Purdie, C A; Jordan, L B; Vinnicombe, S; Lerski, R A; Martin, P; Thompson, A M


    Patient-tailored treatments for breast cancer are based on histological and immunohistochemical (IHC) subtypes. Magnetic Resonance Imaging (MRI) texture analysis (TA) may be useful in non-invasive lesion subtype classification. Women with newly diagnosed primary breast cancer underwent pre-treatment dynamic contrast-enhanced breast MRI. TA was performed using co-occurrence matrix (COM) features, by creating a model on retrospective training data, then prospectively applying to a test set. Analyses were blinded to breast pathology. Subtype classifications were performed using a cross-validated k-nearest-neighbour (k = 3) technique, with accuracy relative to pathology assessed and receiver operator curve (AUROC) calculated. Mann-Whitney U and Kruskal-Wallis tests were used to assess raw entropy feature values. Histological subtype classifications were similar across training (n = 148 cancers) and test sets (n = 73 lesions) using all COM features (training: 75%, AUROC = 0.816; test: 72.5%, AUROC = 0.823). Entropy features were significantly different between lobular and ductal cancers (p cancers demonstrated significantly different entropy features. Entropy features alone were unable to create a robust classification model. Textural differences on contrast-enhanced MR images may reflect underlying lesion subtypes, which merits testing against treatment response. • MR-derived entropy features, representing heterogeneity, provide important information on tissue composition. • Entropy features can differentiate between histological and immunohistochemical subtypes of breast cancer. • Differing entropy features between breast cancer subtypes implies differences in lesion heterogeneity. • Texture analysis of breast cancer potentially provides added information for decision making.

  18. Heuristic Scheduling Algorithm Oriented Dynamic Tasks for Imaging Satellites

    Directory of Open Access Journals (Sweden)

    Maocai Wang


    Full Text Available Imaging satellite scheduling is an NP-hard problem with many complex constraints. This paper researches the scheduling problem for dynamic tasks oriented to some emergency cases. After the dynamic properties of satellite scheduling were analyzed, the optimization model is proposed in this paper. Based on the model, two heuristic algorithms are proposed to solve the problem. The first heuristic algorithm arranges new tasks by inserting or deleting them, then inserting them repeatedly according to the priority from low to high, which is named IDI algorithm. The second one called ISDR adopts four steps: insert directly, insert by shifting, insert by deleting, and reinsert the tasks deleted. Moreover, two heuristic factors, congestion degree of a time window and the overlapping degree of a task, are employed to improve the algorithm’s performance. Finally, a case is given to test the algorithms. The results show that the IDI algorithm is better than ISDR from the running time point of view while ISDR algorithm with heuristic factors is more effective with regard to algorithm performance. Moreover, the results also show that our method has good performance for the larger size of the dynamic tasks in comparison with the other two methods.

  19. Anholt offshore wind farm winds investigated from satellite images

    DEFF Research Database (Denmark)

    Hasager, Charlotte Bay; Badger, Merete; Volker, Patrick

    at this particular moment and the backscatter from the wind turbines is much higher than that from the sea. Therefore the wind turbines are contrasted clearly as yellow/orange dots at the Anholt wind farm. Along the Swedish coast several ships (red dots) are visible. The SAR-based wind speeds can be trusted...... at around 1 km distance from any coastline except in grid cells with wind turbines, ships and other hard targets. The grid resolution is 1 km by 1 km. The wind direction is from the south west. The satellite SAR analysis is based on ~1.000 SAR images from Envisat ASAR recorded from August 2002 to April 2012......, i.e. before the wind farm was constructed. Based on these data the wind resource is estimated. Concurrent Sentinel-1 SAR data and available SCADA and lidar data, kindly provided by DONG Energy and partners, for the period January 2013 to June 2015 account for ~70 images, while ~300 images...

  20. Galileo's first images of Jupiter and the Galilean satellites (United States)

    Belton, M.J.S.; Head, J. W.; Ingersoll, A.P.; Greeley, R.; McEwen, A.S.; Klaasen, K.P.; Senske, D.; Pappalardo, R.; Collins, G.; Vasavada, A.R.; Sullivan, R.; Simonelli, D.; Geissler, P.; Carr, M.H.; Davies, M.E.; Veverka, J.; Gierasch, P.J.; Banfield, D.; Bell, M.; Chapman, C.R.; Anger, C.; Greenberg, R.; Neukum, G.; Pilcher, C.B.; Beebe, R.F.; Burns, J.A.; Fanale, F.; Ip, W.; Johnson, T.V.; Morrison, D.; Moore, J.; Orton, G.S.; Thomas, P.; West, R.A.


    The first images of Jupiter, Io, Europa, and Ganymede from the Galileo spacecraft reveal new information about Jupiter's Great Red Spot (GRS) and the surfaces of the Galilean satellites. Features similar to clusters of thunderstorms were found in the GRS. Nearby wave structures suggest that the GRS may be a shallow atmospheric feature. Changes in surface color and plume distribution indicate differences in resurfacing processes near hot spots on lo. Patchy emissions were seen while Io was in eclipse by Jupiter. The outer margins of prominent linear markings (triple bands) on Europa are diffuse, suggesting that material has been vented from fractures. Numerous small circular craters indicate localized areas of relatively old surface. Pervasive brittle deformation of an ice layer appears to have formed grooves on Ganymede. Dark terrain unexpectedly shows distinctive albedo variations to the limit of resolution.

  1. Galileo's First Images of Jupiter and the Galilean Satellites (United States)

    Belton, M J S; Head, J W; Ingersoll, A P; Greeley, R; McEwen, A S; Klaasen, K P; Senske, D; Pappalardo, R; Collins, G; Vasavada, A R; Sullivan, R; Simonelli, D; Geissler, P; Carr, M H; Davies, M E; Veverka, J; Gierasch, P J; Banfield, D; Bell, M; Chapman, C R; Anger, C; Greenberg, R; Neukum, G; Pilcher, C B; Beebe, R F; Burns, J A; Fanale, F; Ip, W; Johnson, T V; Morrison, D; Moore, J; Orton, G S; Thomas, P; West, R A


    The first images of Jupiter, Io, Europa, and Ganymede from the Galileo spacecraft reveal new information about Jupiter's Great Red Spot (GRS) and the surfaces of the Galilean satellites. Features similar to clusters of thunderstorms were found in the GRS. Nearby wave structures suggest that the GRS may be a shallow atmospheric feature. Changes in surface color and plume distribution indicate differences in resurfacing processes near hot spots on Io. Patchy emissions were seen while Io was in eclipse by Jupiter. The outer margins of prominent linear markings (triple bands) on Europa are diffuse, suggesting that material has been vented from fractures. Numerous small circular craters indicate localized areas of relatively old surface. Pervasive brittle deformation of an ice layer appears to have formed grooves on Ganymede. Dark terrain unexpectedly shows distinctive albedo variations to the limit of resolution.

  2. Land cover and forest formation distributions for St. Kitts, Nevis, St. Eustatius, Grenada and Barbados from decision tree classification of cloud-cleared satellite imagery (United States)

    Helmer, E.H.; Kennaway, T.A.; Pedreros, D.H.; Clark, M.L.; Marcano-Vega, H.; Tieszen, L.L.; Ruzycki, T.R.; Schill, S.R.; Carrington, C.M.S.


    Satellite image-based mapping of tropical forests is vital to conservation planning. Standard methods for automated image classification, however, limit classification detail in complex tropical landscapes. In this study, we test an approach to Landsat image interpretation on four islands of the Lesser Antilles, including Grenada and St. Kitts, Nevis and St. Eustatius, testing a more detailed classification than earlier work in the latter three islands. Secondly, we estimate the extents of land cover and protected forest by formation for five islands and ask how land cover has changed over the second half of the 20th century. The image interpretation approach combines image mosaics and ancillary geographic data, classifying the resulting set of raster data with decision tree software. Cloud-free image mosaics for one or two seasons were created by applying regression tree normalization to scene dates that could fill cloudy areas in a base scene. Such mosaics are also known as cloud-filled, cloud-minimized or cloud-cleared imagery, mosaics, or composites. The approach accurately distinguished several classes that more standard methods would confuse; the seamless mosaics aided reference data collection; and the multiseason imagery allowed us to separate drought deciduous forests and woodlands from semi-deciduous ones. Cultivated land areas declined 60 to 100 percent from about 1945 to 2000 on several islands. Meanwhile, forest cover has increased 50 to 950%. This trend will likely continue where sugar cane cultivation has dominated. Like the island of Puerto Rico, most higher-elevation forest formations are protected in formal or informal reserves. Also similarly, lowland forests, which are drier forest types on these islands, are not well represented in reserves. Former cultivated lands in lowland areas could provide lands for new reserves of drier forest types. The land-use history of these islands may provide insight for planners in countries currently considering


    Directory of Open Access Journals (Sweden)

    J Carlos Moreno


    Full Text Available This paper presents a novel strategy for building a high-dimensional feature space to represent histopathology image contents. Histogram features, related to colors, textures and edges, are combined together in a unique image representation space using kernel functions. This feature space is further enhanced by the application of Latent Semantic Analysis, to model hidden relationships among visual patterns. All that information is included in the new image representation space. Then, Support Vector Machine classifiers are used to assign semantic labels to images. Processing and classification algorithms operate on top of kernel functions, so that, the structure of the feature space is completely controlled using similarity measures and a dual representation. The proposed approach has shown a successful performance in a classification task using a dataset with 1,502 real histopathology images in 18 different classes. The results show that our approach for histological image classification obtains an improved average performance of 20.6% when compared to a conventional classification approach based on SVM directly applied to the original kernel.


    Directory of Open Access Journals (Sweden)

    Moreno J Carlos


    Full Text Available This paper presents a novel strategy for building a high-dimensional feature space to represent histopathology image contents. Histogram features, related to colors, textures and edges, are combined together in a unique image representation space using kernel functions. This feature space is further enhanced by the application of Latent Semantic Analysis, to model hidden relationships among visual patterns. All that information is included in the new image representation space. Then, Support Vector Machine classifiers are used to assign semantic labels to images. Processing and classification algorithms operate on top of kernel functions, so that, the structure of the feature space is completely controlled using similarity measures and a dual representation. The proposed approach has shown a successful performance in a classification task using a dataset with 1,502 real histopathology images in 18 different classes. The results show that our approach for histological image classification obtains an improved average performance of 20.6% when compared to a conventional classification approach based on SVM directly applied to the original kernel.

  5. Satellite image analysis for surveillance, vegetation and climate change

    Energy Technology Data Exchange (ETDEWEB)

    Cai, D Michael [Los Alamos National Laboratory


    Recently, many studies have provided abundant evidence to show the trend of tree mortality is increasing in many regions, and the cause of tree mortality is associated with drought, insect outbreak, or fire. Unfortunately, there is no current capability available to monitor vegetation changes, and correlate and predict tree mortality with CO{sub 2} change, and climate change on the global scale. Different survey platforms (methods) have been used for forest management. Typical ground-based forest surveys measure tree stem diameter, species, and alive or dead. The measurements are low-tech and time consuming, but the sample sizes are large, running into millions of trees, covering large areas, and spanning many years. These field surveys provide powerful ground validation for other survey methods such as photo survey, helicopter GPS survey, and aerial overview survey. The satellite imagery has much larger coverage. It is easier to tile the different images together, and more important, the spatial resolution has been improved such that close to or even higher than aerial survey platforms. Today, the remote sensing satellite data have reached sub-meter spatial resolution for panchromatic channels (IKONOS 2: 1 m; Quickbird-2: 0.61 m; Worldview-2: 0.5 m) and meter spatial resolution for multi-spectral channels (IKONOS 2: 4 meter; Quickbird-2: 2.44 m; Worldview-2: 2 m). Therefore, high resolution satellite imagery can allow foresters to discern individual trees. This vital information should allow us to quantify physiological states of trees, e.g. healthy or dead, shape and size of tree crowns, as well as species and functional compositions of trees. This is a powerful data resource, however, due to the vast amount of the data collected daily, it is impossible for human analysts to review the imagery in detail to identify the vital biodiversity information. Thus, in this talk, we will discuss the opportunities and challenges to use high resolution satellite imagery and

  6. Brain tumor classification of microscopy images using deep residual learning (United States)

    Ishikawa, Yota; Washiya, Kiyotada; Aoki, Kota; Nagahashi, Hiroshi


    The crisis rate of brain tumor is about one point four in ten thousands. In general, cytotechnologists take charge of cytologic diagnosis. However, the number of cytotechnologists who can diagnose brain tumors is not sufficient, because of the necessity of highly specialized skill. Computer-Aided Diagnosis by computational image analysis may dissolve the shortage of experts and support objective pathological examinations. Our purpose is to support a diagnosis from a microscopy image of brain cortex and to identify brain tumor by medical image processing. In this study, we analyze Astrocytes that is a type of glia cell of central nerve system. It is not easy for an expert to discriminate brain tumor correctly since the difference between astrocytes and low grade astrocytoma (tumors formed from Astrocyte) is very slight. In this study, we present a novel method to segment cell regions robustly using BING objectness estimation and to classify brain tumors using deep convolutional neural networks (CNNs) constructed by deep residual learning. BING is a fast object detection method and we use pretrained BING model to detect brain cells. After that, we apply a sequence of post-processing like Voronoi diagram, binarization, watershed transform to obtain fine segmentation. For classification using CNNs, a usual way of data argumentation is applied to brain cells database. Experimental results showed 98.5% accuracy of classification and 98.2% accuracy of segmentation.

  7. Accessory cardiac bronchus: Proposed imaging classification on multidetector CT

    Energy Technology Data Exchange (ETDEWEB)

    Kim, Kang Min; Kim, Young Tong; Han, Jong Kyu; Jou, Sung Shick [Dept. of Radiology, Soonchunhyang University College of Medicine, Cheonan Hospital, Cheonan (Korea, Republic of)


    To propose the classification of accessory cardiac bronchus (ACB) based on imaging using multidetector computed tomography (MDCT), and evaluate follow-up changes of ACB. This study included 58 patients diagnosed as ACB since 9 years, using MDCT. We analyzed the types, division locations and division directions of ACB, and also evaluated changes on follow-up. We identified two main types of ACB: blind-end (51.7%) and lobule (48.3%). The blind-end ACB was further classified into three subtypes: blunt (70%), pointy (23.3%) and saccular (6.7%). The lobule ACB was also further classified into three subtypes: complete (46.4%), incomplete (28.6%) and rudimentary (25%). Division location to the upper half bronchus intermedius (79.3%) and medial direction (60.3%) were the most common in all patients. The difference in division direction was statistically significant between the blind-end and lobule types (p = 0.019). Peribronchial soft tissue was found in five cases. One calcification case was identified in the lobule type. During follow-up, ACB had disappeared in two cases of the blind-end type and in one case of the rudimentary subtype. The proposed classification of ACB based on imaging, and the follow-up CT, helped us to understand the various imaging features of ACB.

  8. A Novel Approach to Developing a Supervised Spatial Decision Support System for Image Classification: A Study of Paddy Rice Investigation

    Directory of Open Access Journals (Sweden)

    Shih-Hsun Chang


    Full Text Available Paddy rice area estimation via remote sensing techniques has been well established in recent years. Texture information and vegetation indicators are widely used to improve the classification accuracy of satellite images. Accordingly, this study employs texture information and vegetation indicators as ancillary information for classifying paddy rice through remote sensing images. In the first stage, the images are attained using a remote sensing technique and ancillary information is employed to increase the accuracy of classification. In the second stage, we decide to construct an efficient supervised classifier, which is used to evaluate the ancillary information. In the third stage, linear discriminant analysis (LDA is introduced. LDA is a well-known method for classifying images to various categories. Also, the particle swarm optimization (PSO algorithm is employed to optimize the LDA classification outcomes and increase classification performance. In the fourth stage, we discuss the strategy of selecting different window sizes and analyze particle numbers and iteration numbers with corresponding accuracy. Accordingly, a rational strategy for the combination of ancillary information is introduced. Afterwards, the PSO algorithm improves the accuracy rate from 82.26% to 89.31%. The improved accuracy results in a much lower salt-and-pepper effect in the thematic map.

  9. Land Covering Classifications of Boreas Modeling Grid Using AIRSAR Images (United States)

    Saatchi, Sasan S.; Rignot, Eric


    Mapping forest types in the boreal ecosystem in an integrated part of any modeling excercise of biogeophysical processes characterizing the interaction of forest with the atmosphere. In this paper, we report the results of the land cover classification of the SAR data acquired during the BOREAS (BOReal Ecosystem Atmospheric Study) intensive field campaigns over the modeling sub-grid of the southern study area in Saskatchewan , Canada. A Bayesian-maximum-a-posteriori classifier has been applied on the NASA/JPL AIRSAR images covering the region during the peak of the growing season in July, 1994.

  10. Applying Support Vector Machine in classifying satellite images for the assessment of urban sprawl (United States)

    murgante, Beniamino; Nolè, Gabriele; Lasaponara, Rosa; Lanorte, Antonio; Calamita, Giuseppe


    In last decades the spreading of new buildings, road infrastructures and a scattered proliferation of houses in zones outside urban areas, produced a countryside urbanization with no rules, consuming soils and impoverishing the landscape. Such a phenomenon generated a huge environmental impact, diseconomies and a decrease in life quality. This study analyzes processes concerning land use change, paying particular attention to urban sprawl phenomenon. The application is based on the integration of Geographic Information Systems and Remote Sensing adopting open source technologies. The objective is to understand size distribution and dynamic expansion of urban areas in order to define a methodology useful to both identify and monitor the phenomenon. In order to classify "urban" pixels, over time monitoring of settlements spread, understanding trends of artificial territories, classifications of satellite images at different dates have been realized. In order to obtain these classifications, supervised classification algorithms have been adopted. More particularly, Support Vector Machine (SVM) learning algorithm has been applied to multispectral remote data. One of the more interesting features in SVM is the possibility to obtain good results also adopting few classification pixels of training areas. SVM has several interesting features, such as the capacity to obtain good results also adopting few classification pixels of training areas, a high possibility of configuration parameters and the ability to discriminate pixels with similar spectral responses. Multi-temporal ASTER satellite data at medium resolution have been adopted because are very suitable in evaluating such phenomena. The application is based on the integration of Geographic Information Systems and Remote Sensing technologies by means of open source software. Tools adopted in managing and processing data are GRASS GIS, Quantum GIS and R statistical project. The area of interest is located south of Bari

  11. Adaptive Optics for Satellite Imaging and Space Debris Ranging (United States)

    Bennet, F.; D'Orgeville, C.; Price, I.; Rigaut, F.; Ritchie, I.; Smith, C.

    Earth's space environment is becoming crowded and at risk of a Kessler syndrome, and will require careful management for the future. Modern low noise high speed detectors allow for wavefront sensing and adaptive optics (AO) in extreme circumstances such as imaging small orbiting bodies in Low Earth Orbit (LEO). The Research School of Astronomy and Astrophysics (RSAA) at the Australian National University have been developing AO systems for telescopes between 1 and 2.5m diameter to image and range orbiting satellites and space debris. Strehl ratios in excess of 30% can be achieved for targets in LEO with an AO loop running at 2kHz, allowing the resolution of small features (system developed at RSAA consists of a high speed EMCCD Shack-Hartmann wavefront sensor, a deformable mirror (DM), and realtime computer (RTC), and an imaging camera. The system works best as a laser guide star system but will also function as a natural guide star AO system, with the target itself being the guide star. In both circumstances tip-tilt is provided by the target on the imaging camera. The fast tip-tilt modes are not corrected optically, and are instead removed by taking images at a moderate speed (>30Hz) and using a shift and add algorithm. This algorithm can also incorporate lucky imaging to further improve the final image quality. A similar AO system for space debris ranging is also in development in collaboration with Electro Optic Systems (EOS) and the Space Environment Management Cooperative Research Centre (SERC), at the Mount Stromlo Observatory in Canberra, Australia. The system is designed for an AO corrected upward propagated 1064nm pulsed laser beam, from which time of flight information is used to precisely range the target. A 1.8m telescope is used for both propagation and collection of laser light. A laser guide star, Shack-Hartmann wavefront sensor, and DM are used for high order correction, and tip-tilt correction provided by reflected sunlight from the target. The

  12. Large margin distribution machine for hyperspectral image classification (United States)

    Zhan, Kun; Wang, Haibo; Huang, He; Xie, Yuange


    Support vector machine (SVM) classifiers are widely applied to hyperspectral image (HSI) classification and provide significant advantages in terms of accuracy, simplicity, and robustness. SVM is a well-known learning algorithm that maximizes the minimum margin. However, recent theoretical results pointed out that maximizing the minimum margin leads to a lower generalization performance than optimizing the margin distribution, and proved that the margin distribution is more important. In this paper, a large margin distribution machine (LDM) is applied to HSI classification, and optimizing the margin distribution achieves a better generalization performance than SVM. Since the raw HSI feature space is not the most effective space for representing HSI, we adopt factor analysis to learn an effective HSI feature and the learned features are further filtered by a structure-preserved filter to fully exploit the spatial structure information of HSI. The spatial structure information is integrated in the feature learning process to obtain a better HSI feature. Then we propose a multiclass LDM to classify the filtered HSI feature. Experimental results show that the proposed LDM with feature learning method achieves the classification performance of the state-of-the-art methods in terms of visual quality and three quantitative evaluations and indicates that LDM has a high generalization performance.

  13. Hyperspectral image filtering with adaptive manifold for classification (United States)

    Xie, Weiying; Li, Yunsong; Zhou, Weiping


    Hyperspectral image (HSI) is a three-dimensional data cube containing two spatial information dimensions and one spectral information dimension. The spectral vectors of different classes may have similar tendency and value that may bring about negative influences on classification. It is, therefore, important to introduce signal preprocessing techniques in the spatial domain to improve classification accuracy of HSIs. Assuming that local pixels in HSI have some correlations with each other, this paper proposes a spatial filtering model based on adaptive manifold (AM) for HSI. The AM for spatial filtering emphasizes the similar neighboring pixels and is robust to resist the noisy points with fast speed. The rich information in the filtered data is effective for improving the performance of the subsequent classification. The filtered data are classified by an extreme learning machine (ELM). The experimental results indicate that the framework built based on AM and ELM provides competitive performance. Specifically, by classifying the filtered data, the average accuracy of ELM can be improved as high as 30.54%, while performing tens to hundreds times faster than those state-of-the-art classifiers.

  14. Classification of left and right eye retinal images (United States)

    Tan, Ngan Meng; Liu, Jiang; Wong, Damon W. K.; Zhang, Zhuo; Lu, Shijian; Lim, Joo Hwee; Li, Huiqi; Wong, Tien Yin


    Retinal image analysis is used by clinicians to diagnose and identify, if any, pathologies present in a patient's eye. The developments and applications of computer-aided diagnosis (CAD) systems in medical imaging have been rapidly increasing over the years. In this paper, we propose a system to classify left and right eye retinal images automatically. This paper describes our two-pronged approach to classify left and right retinal images by using the position of the central retinal vessel within the optic disc, and by the location of the macula with respect to the optic nerve head. We present a framework to automatically identify the locations of the key anatomical structures of the eye- macula, optic disc, central retinal vessels within the optic disc and the ISNT regions. A SVM model for left and right eye retinal image classification is trained based on the features from the detection and segmentation. An advantage of this is that other image processing algorithms can be focused on regions where diseases or pathologies and more likely to occur, thereby increasing the efficiency and accuracy of the retinal CAD system/pathology detection. We have tested our system on 102 retinal images, consisting of 51 left and right images each and achieved and accuracy of 94.1176%. The high experimental accuracy and robustness of this system demonstrates that there is potential for this system to be integrated and applied with other retinal CAD system, such as ARGALI, for a priori information in automatic mass screening and diagnosis of retinal diseases.

  15. Superpixel-based classification of gastric chromoendoscopy images (United States)

    Boschetto, Davide; Grisan, Enrico


    Chromoendoscopy (CH) is a gastroenterology imaging modality that involves the staining of tissues with methylene blue, which reacts with the internal walls of the gastrointestinal tract, improving the visual contrast in mucosal surfaces and thus enhancing a doctor's ability to screen precancerous lesions or early cancer. This technique helps identify areas that can be targeted for biopsy or treatment and in this work we will focus on gastric cancer detection. Gastric chromoendoscopy for cancer detection has several taxonomies available, one of which classifies CH images into three classes (normal, metaplasia, dysplasia) based on color, shape and regularity of pit patterns. Computer-assisted diagnosis is desirable to help us improve the reliability of the tissue classification and abnormalities detection. However, traditional computer vision methodologies, mainly segmentation, do not translate well to the specific visual characteristics of a gastroenterology imaging scenario. We propose the exploitation of a first unsupervised segmentation via superpixel, which groups pixels into perceptually meaningful atomic regions, used to replace the rigid structure of the pixel grid. For each superpixel, a set of features is extracted and then fed to a random forest based classifier, which computes a model used to predict the class of each superpixel. The average general accuracy of our model is 92.05% in the pixel domain (86.62% in the superpixel domain), while detection accuracies on the normal and abnormal class are respectively 85.71% and 95%. Eventually, the whole image class can be predicted image through a majority vote on each superpixel's predicted class.

  16. An approach for combining multiple descriptors for image classification (United States)

    Tran, Duc Toan; Jansen, Bart; Deklerck, Rudi; Debeir, Olivier


    Recently, efficient image descriptors have shown promise for image classification tasks. Moreover, methods based on the combination of multiple image features provide better performance compared to methods based on a single feature. This work presents a simple and efficient approach for combining multiple image descriptors. We first employ a Naive-Bayes Nearest-Neighbor scheme to evaluate four widely used descriptors. For all features, "Image-to-Class" distances are directly computed without descriptor quantization. Since distances measured by different metrics can be of different nature and they may not be on the same numerical scale, a normalization step is essential to transform these distances into a common domain prior to combining them. Our experiments conducted on a challenging database indicate that z-score normalization followed by a simple sum of distances fusion technique can significantly improve the performance compared to applications in which individual features are used. It was also observed that our experimental results on the Caltech 101 dataset outperform other previous results.

  17. Super pixel-level dictionary learning for hyperspectral image classification (United States)

    Zhao, Wei; Zhu, Wen; Liao, Bo; Fu, Xiangzheng


    This paper presents a superpixel-level dictionary learning model for hyperspectral data. The idea is to divide the hyperspectral image into a number of super-pixels by means of the super-pixel segmentation method. Each super-pixel is a spatial neighborhood called contextual group. That is, each pixel is represented using a linear combination of a few dictionary items learned from the train data, but since pixels inside a super-pixel are often consisting of the same materials, their linear combinations are constrained to use common items from the dictionary. To this end, the sparse coefficients of the context group have a common sparse pattern by using the joint sparse regularizer for dictionary learning. The sparse coefficients are then used for classification using linear support vector machines. The validity of the proposed method is experimentally verified on a real hyperspectral images.

  18. Objective color classification of ecstasy tablets by hyperspectral imaging. (United States)

    Edelman, Gerda; Lopatka, Martin; Aalders, Maurice


    The general procedure followed in the examination of ecstasy tablets for profiling purposes includes a color description, which depends highly on the observers' perception. This study aims to provide objective quantitative color information using visible hyperspectral imaging. Both self-manufactured and illicit tablets, created with different amounts of known colorants were analyzed. We derived reflectance spectra from hyperspectral images of these tablets, and successfully determined the most likely colorant used in the production of all self-manufactured tablets and four of five illicit tablets studied. Upon classification, the concentration of the colorant was estimated using a photon propagation model and a single reference measurement of a tablet of known concentration. The estimated concentrations showed a high correlation with the actual values (R(2) = 0.9374). The achieved color information, combined with other physical and chemical characteristics, can provide a powerful tool for the comparison of tablet seizures, which may reveal their origin. © 2013 American Academy of Forensic Sciences.

  19. Skimming Digits: Neuromorphic Classification of Spike-Encoded Images

    Directory of Open Access Journals (Sweden)

    Gregory Kevin Cohen


    Full Text Available The growing demands placed upon the field of computer vision has renewed the focus on alternative visual scene representations and processing paradigms. Silicon retinea provide an alternative means of imaging the visual environment, and produce frame-free spatio-temporal data. This paper presents an investigation into event-based digit classification using N-MNIST,a neuromorphic dataset created with a silicon retina, and the Synaptic Kernel Inverse Method (SKIM, a learning method based on principles of dendritic computation. As this work represents the first large-scale and multi-class classification task performed using the SKIM network, it explores different training patterns and output determination methods necessary to extend the original SKIM method to support multi-class problems. Making use of SKIM networks applied to real-world datasets, implementing the largest hidden layer sizes and simultaneously training the largest number of output neurons, the classification system achieved a best-case accuracy of 92.87% for a network containing 10,000 hidden layer neurons. These results represent the highest accuracies achieved against the dataset to date and serves to validate the application of the SKIM method to event-based visual classification tasks. Additionally, the study found that using a square pulse as the supervisory training signal produced the highest accuracy for most output determination methods, but the results also demonstrate that an exponential pattern is better suited to hardware implementations as it makes use of the simplest output determination method based on the maximum value.

  20. A Novel Classification Technique of Landsat-8 OLI Image-Based Data Visualization: The Application of Andrews’ Plots and Fuzzy Evidential Reasoning

    Directory of Open Access Journals (Sweden)

    Sornkitja Boonprong


    Full Text Available Andrews first proposed an equation to visualize the structures within data in 1972. Since then, this equation has been used for data transformation and visualization in a wide variety of fields. However, it has yet to be applied to satellite image data. The effect of unwanted, or impure, pixels occurring in these data varies with their distribution in the image; the effect is greater if impurity pixels are included in a classifier’s training set. Andrews’ curves enable the interpreter to select outlier or impurity data that can be grouped into a new category for classification. This study overcomes the above-mentioned problem and illustrates the novelty of applying Andrews’ plots to satellite image data, and proposes a robust method for classifying the plots that combines Dempster-Shafer theory with fuzzy set theory. In addition, we present an example, obtained from real satellite images, to demonstrate the application of the proposed classification method. The accuracy and robustness of the proposed method are investigated for different training set sizes and crop types, and are compared with the results of two traditional classification methods. We find that outlier data are easily eliminated by examining Andrews’ curves and that the proposed method significantly outperforms traditional methods when considering the classification accuracy.

  1. Satellite Image Time Series Decomposition Based on EEMD

    Directory of Open Access Journals (Sweden)

    Yun-long Kong


    Full Text Available Satellite Image Time Series (SITS have recently been of great interest due to the emerging remote sensing capabilities for Earth observation. Trend and seasonal components are two crucial elements of SITS. In this paper, a novel framework of SITS decomposition based on Ensemble Empirical Mode Decomposition (EEMD is proposed. EEMD is achieved by sifting an ensemble of adaptive orthogonal components called Intrinsic Mode Functions (IMFs. EEMD is noise-assisted and overcomes the drawback of mode mixing in conventional Empirical Mode Decomposition (EMD. Inspired by these advantages, the aim of this work is to employ EEMD to decompose SITS into IMFs and to choose relevant IMFs for the separation of seasonal and trend components. In a series of simulations, IMFs extracted by EEMD achieved a clear representation with physical meaning. The experimental results of 16-day compositions of Moderate Resolution Imaging Spectroradiometer (MODIS, Normalized Difference Vegetation Index (NDVI, and Global Environment Monitoring Index (GEMI time series with disturbance illustrated the effectiveness and stability of the proposed approach to monitoring tasks, such as applications for the detection of abrupt changes.

  2. The Advanced X-ray Imaging Satellite (AXIS) (United States)

    Reynolds, Christopher S.; Mushotzky, Richard


    The Advanced X-ray Imaging Satellite (AXIS) will follow in the footsteps of the spectacularly successful Chandra X-ray Observatory with similar or higher angular resolution and an order of magnitude more collecting area in the 0.3-10keV band. These capabilities will enable major advances in many of the most active areas of astrophysics, including (i) mapping event horizon scale structure in AGN accretion disks and the determination of supermassive black hole (SMBH) spins through monitoring of gravitationally-microlensed quasars; (ii) dramatically deepening our understanding of AGN feedback in galaxies and galaxy clusters out to high-z through the direct imaging of AGN winds and the interaction of jets with the hot interstellar/intracluster medium; (iii) understanding the fueling of AGN by probing hot flows inside of the SMBH sphere of influence; (iv) obtaining geometric distance measurements using dust scattering halos. With a nominal 2028 launch, AXIS will be enormously synergistic with LSST, ALMA, WFIRST and ATHENA, and will be a valuable precursor to Lynx. AXIS is enabled by breakthroughs in the construction of light-weight X-ray optics from mono-crystalline silicon blocks, building on recent developments in the semiconductor industry. Here, we describe the straw-man concept for AXIS, some of the high profile science that this observatory will address, and how you can become involved.

  3. Evaluation of the Chinese Fine Spatial Resolution Hyperspectral Satellite TianGong-1 in Urban Land-Cover Classification

    Directory of Open Access Journals (Sweden)

    Xueke Li


    Full Text Available The successful launch of the Chinese high spatial resolution hyperspectral satellite TianGong-1 (TG-1 opens up new possibilities for applications of remotely-sensed satellite imagery. One of the main goals of the TG-1 mission is to provide observations of surface attributes at local and landscape spatial scales to map urban land cover accurately using the hyperspectral technique. This study attempted to evaluate the TG-1 datasets for urban feature analysis, using existing data over Beijing, China, by comparing the TG-1 (with a spatial resolution of 10 m to EO-1 Hyperion (with a spatial resolution of 30 m. The spectral feature of TG-1 was first analyzed and, thus, finding out optimal hyperspectral wavebands useful for the discrimination of urban areas. Based on this, the pixel-based maximum likelihood classifier (PMLC, pixel-based support vector machine (PSVM, hybrid maximum likelihood classifier (HMLC, and hybrid support vector machine (HSVM were implemented, as well as compared in the application of mapping urban land cover types. The hybrid classifier approach, which integrates the pixel-based classifier and the object-based segmentation approach, was demonstrated as an effective alternative to the conventional pixel-based classifiers for processing the satellite hyperspectral data, especially the fine spatial resolution data. For TG-1 imagery, the pixel-based urban classification was obtained with an average overall accuracy of 89.1%, whereas the hybrid urban classification was obtained with an average overall accuracy of 91.8%. For Hyperion imagery, the pixel-based urban classification was obtained with an average overall accuracy of 85.9%, whereas the hybrid urban classification was obtained with an average overall accuracy of 86.7%. Overall, it can be concluded that the fine spatial resolution satellite hyperspectral data TG-1 is promising in delineating complex urban scenes, especially when using an appropriate classifier, such as the

  4. Classification of rainfall radar images using the scattering transform (United States)

    Lagrange, Mathieu; Andrieu, Hervé; Emmanuel, Isabelle; Busquets, Gerard; Loubrié, Stéphane


    The classification of rainfall fields has mainly focused on the split between convective and stratiform rainfall fields. In the present case study, the wavelet-based scattering transform is used to classify rainfall events observed by a weather radar. This very recent method has, to the best of the authors' knowledge, not yet been applied for such a purpose. This method considers the spatial properties of rainfall radar images. This case study regroups 34 rainfall periods recorded over the Nantes region (western France) during 23 days in both 2009 and 2012. These periods display different characteristics in terms of duration and type of rainfall field. A reference configuration of the scattering transform has been evaluated and compared to various configurations in order to approximate the application conditions most appropriate to this case study. This evaluation is performed by a leave-one-out cross validation. A global accuracy of 93.5% of well classified images is obtained in the reference conditions which is an encouraging result. The temporal sampling of the rainfall fields is an important aspect of the classification process.

  5. Automated classification of colon polyps in endoscopic image data (United States)

    Gross, Sebastian; Palm, Stephan; Tischendorf, Jens J. W.; Behrens, Alexander; Trautwein, Christian; Aach, Til


    Colon cancer is the third most commonly diagnosed type of cancer in the US. In recent years, however, early diagnosis and treatment have caused a significant rise in the five year survival rate. Preventive screening is often performed by colonoscopy (endoscopic inspection of the colon mucosa). Narrow Band Imaging (NBI) is a novel diagnostic approach highlighting blood vessel structures on polyps which are an indicator for future cancer risk. In this paper, we review our automated inter- and intra-observer independent system for the automated classification of polyps into hyperplasias and adenomas based on vessel structures to further improve the classification performance. To surpass the performance limitations we derive a novel vessel segmentation approach, extract 22 features to describe complex vessel topologies, and apply three feature selection strategies. Tests are conducted on 286 NBI images with diagnostically important and challenging polyps (10mm or smaller) taken from our representative polyp database. Evaluations are based on ground truth data determined by histopathological analysis. Feature selection by Simulated Annealing yields the best result with a prediction accuracy of 96.2% (sensitivity: 97.6%, specificity: 94.2%) using eight features. Future development aims at implementing a demonstrator platform to begin clinical trials at University Hospital Aachen.

  6. Low-Rank Sparse Coding for Image Classification

    KAUST Repository

    Zhang, Tianzhu


    In this paper, we propose a low-rank sparse coding (LRSC) method that exploits local structure information among features in an image for the purpose of image-level classification. LRSC represents densely sampled SIFT descriptors, in a spatial neighborhood, collectively as low-rank, sparse linear combinations of code words. As such, it casts the feature coding problem as a low-rank matrix learning problem, which is different from previous methods that encode features independently. This LRSC has a number of attractive properties. (1) It encourages sparsity in feature codes, locality in codebook construction, and low-rankness for spatial consistency. (2) LRSC encodes local features jointly by considering their low-rank structure information, and is computationally attractive. We evaluate the LRSC by comparing its performance on a set of challenging benchmarks with that of 7 popular coding and other state-of-the-art methods. Our experiments show that by representing local features jointly, LRSC not only outperforms the state-of-the-art in classification accuracy but also improves the time complexity of methods that use a similar sparse linear representation model for feature coding.

  7. Bayesian Information Criterion Based Feature Filtering for the Fusion of Multiple Features in High-Spatial-Resolution Satellite Scene Classification

    Directory of Open Access Journals (Sweden)

    Da Lin


    Full Text Available This paper presents a novel classification method for high-spatial-resolution satellite scene classification introducing Bayesian information criterion (BIC-based feature filtering process to further eliminate opaque and redundant information between multiple features. Firstly, two diverse and complementary feature descriptors are extracted to characterize the satellite scene. Then, sparse canonical correlation analysis (SCCA with penalty function is employed to fuse the extracted feature descriptors and remove the ambiguities and redundancies between them simultaneously. After that, a two-phase Bayesian information criterion (BIC-based feature filtering process is designed to further filter out redundant information. In the first phase, we gradually impose a constraint via an iterative process to set a constraint on the loadings for averting sparse correlation descending below to a lower confidence limit of the approximated canonical correlation. In the second phase, Bayesian information criterion (BIC is utilized to conduct the feature filtering which sets the smallest loading in absolute value to zero in each iteration for all features. Lastly, a support vector machine with pyramid match kernel is applied to obtain the final result. Experimental results on high-spatial-resolution satellite scenes demonstrate that the suggested approach achieves satisfactory performance in classification accuracy.

  8. Colour space influence for vegetation image classification application to Caribbean forest and agriculture (United States)

    Abadi, M.; Grandchamp, E.


    This paper deals with a comparison of different colour space in order to improve high resolution images classification. The background of this study is the measure of the agriculture impact on the environment in islander context. Biodiversity is particularly sensitive and relevant in such areas and the follow-up of the forest front is a way to ensure its preservation. Very high resolution satellite images are used such as QuickBird and IKONOS scenes. In order to segment the images into forest and agriculture areas, we characterize both ground covers with colour and texture features. A classical unsupervised classifier is then used to obtain labelled areas. As features are computed on coloured images, we can wonder if the colour space choice is relevant. This study has been made considering more than fourteen colour spaces (RGB, YUV, Lab, YIQ, YCrCs, XYZ, CMY, LMS, HSL, KLT, IHS, I1I2I3, HSV, HSI, etc.) and shows the visual and quantitative superiority of IHS on all others. For conciseness reasons, results only show RGB, I1I2I3 and IHS colour spaces.

  9. Post-earthquake road damage assessment using region-based algorithms from high-resolution satellite images (United States)

    Haghighattalab, A.; Mohammadzadeh, A.; Valadan Zoej, M. J.; Taleai, M.


    Receiving accurate and comprehensive knowledge about the conditions of roads after earthquake strike are crucial in finding optimal paths and coordinating rescue missions. Continuous coverage of the disaster region and rapid access of high-resolution satellite images make this technology as a useful and powerful resource for post-earthquake damage assessment and the evaluation process. Along with this improved technology, object-oriented classification has become a promising alternative for classifying high-resolution remote sensing imagery, such as QuickBird, Ikonos. Thus, in this study, a novel approach is proposed for the automatic detection and assessment of damaged roads in urban areas based on object based classification techniques using post-event satellite image and vector map. The most challenging phase of the proposed region-based algorithm is the segmentation procedure. The extracted regions are then classified using nearest neighbor classifier making use of textural parameters. Then, an appropriate fuzzy inference system (FIS) is proposed for road damage assessment. Finally, the roads are correctly labeled as 'Blocked road' or 'Unblocked road' in the road damage assessment step. The proposed method was tested on QuickBird pan-sharpened image of Bam, Iran, concerning the devastating earthquake that occurred in December 2003. The visual investigation of the obtained results demonstrates the efficiency of the proposed approach.

  10. Comparison of Oil Spill Classifications Using Fully and Compact Polarimetric SAR Images

    Directory of Open Access Journals (Sweden)

    Yuanzhi Zhang


    Full Text Available In this paper, we present a comparison between several algorithms for oil spill classifications using fully and compact polarimetric SAR images. Oil spill is considered as one of the most significant sources of marine pollution. As a major difficulty of SAR-based oil spill detection algorithms is the classification between mineral and biogenic oil, we focus on quantitatively analyzing and comparing fully and compact polarimetric satellite synthetic aperture radar (SAR modes to detect hydrocarbon slicks over the sea surface, discriminating them from weak-damping surfactants, such as biogenic slicks. The experiment was conducted on quad-pol SAR data acquired during the Norwegian oil-on-water experiment in 2011. A universal procedure was used to extract the features from quad-, dual- and compact polarimetric SAR modes to rank different polarimetric SAR modes and common supervised classifiers. Among all the dual- and compact polarimetric SAR modes, the π/2 mode has the best performance. The best supervised classifiers vary and depended on whether sufficient polarimetric information can be obtained in each polarimetric mode. We also analyzed the influence of the number of polarimetric parameters considered as inputs for the supervised classifiers, onto the detection/discrimination performance. We discovered that a feature set with four features is sufficient for most polarimetric feature-based oil spill classifications. Moreover, dimension reduction algorithms, including principle component analysis (PCA and the local linear embedding (LLE algorithm, were employed to learn low dimensional and distinctive information from quad-polarimetric SAR features. The performance of the new feature sets has comparable performance in oil spill classification.

  11. Classification of quantitative light-induced fluorescence images using convolutional neural network

    NARCIS (Netherlands)

    Imangaliyev, S.; van der Veen, M.H.; Volgenant, C.M.C.; Loos, B.G.; Keijser, B.J.F.; Crielaard, W.; Levin, E.; Lintas, A.; Rovetta, S.; Verschure, P.F.M.J.; Villa, A.E.P.


    Images are an important data source for diagnosis of oral diseases. The manual classification of images may lead to suboptimal treatment procedures due to subjective errors. In this paper an image classification algorithm based on Deep Learning framework is applied to Quantitative Light-induced

  12. Imaging modalities for the classification of gout: systematic literature review and meta-analysis

    NARCIS (Netherlands)

    Ogdie, A.; Taylor, W.J.; Weatherall, M.; Fransen, J.; Jansen, T.L.; Neogi, T.; Schumacher, H.R.; Dalbeth, N.


    BACKGROUND: Although there has been major progress in gout imaging, no gout classification criteria currently include advanced imaging techniques. OBJECTIVE: To examine the usefulness of imaging modalities in the classification of gout when compared to monosodium urate (MSU) crystal confirmation as

  13. Estimate Landslide Volume with Genetic Algorithms and Image Similarity Method from Single Satellite Image (United States)

    Yu, Ting-To


    It is important to acquire the volume of landslide in short period of time. For hazard mitigation and also emergency response purpose, the traditional method takes much longer time than expected. Due to the weather limit, traffic accessibility and many regulations of law, it take months to handle these process before the actual carry out of filed work. Remote sensing imagery can get the data as long as the visibility allowed, which happened only few day after the event. While traditional photometry requires a stereo pairs images to produce the post event DEM for calculating the change of volume. Usually have to wait weeks or even months for gathering such data, LiDAR or ground GPS measurement might take even longer period of time with much higher cost. In this study we use one post event satellite image and pre-event DTM to compare the similarity between these by alter the DTM with genetic algorithms. The outcome of smartest guess from GAs shall remove or add exact values of height at each location, which been converted into shadow relief viewgraph to compare with satellite image. Once the similarity threshold been make then the guessing work stop. It takes only few hours to finish the entire task, the computed accuracy is around 70% by comparing to the high resolution LiDAR survey at a landslide, southern Taiwan. With extra GCPs, the estimate accuracy can improve to 85% and also within few hours after the receiving of satellite image. Data of this demonstration case is a 5 m DTM at 2005, 2M resolution FormoSat optical image at 2009 and 5M LiDAR at 2010. The GAs and image similarity code is developed on Matlab at windows PC.

  14. Image segmentation and particles classification using texture analysis method

    Directory of Open Access Journals (Sweden)

    Mayar Aly Atteya

    Full Text Available Introduction: Ingredients of oily fish include a large amount of polyunsaturated fatty acids, which are important elements in various metabolic processes of humans, and have also been used to prevent diseases. However, in an attempt to reduce cost, recent developments are starting a replace the ingredients of fish oil with products of microalgae, that also produce polyunsaturated fatty acids. To do so, it is important to closely monitor morphological changes in algae cells and monitor their age in order to achieve the best results. This paper aims to describe an advanced vision-based system to automatically detect, classify, and track the organic cells using a recently developed SOPAT-System (Smart On-line Particle Analysis Technology, a photo-optical image acquisition device combined with innovative image analysis software. Methods The proposed method includes image de-noising, binarization and Enhancement, as well as object recognition, localization and classification based on the analysis of particles’ size and texture. Results The methods allowed for correctly computing cell’s size for each particle separately. By computing an area histogram for the input images (1h, 18h, and 42h, the variation could be observed showing a clear increase in cell. Conclusion The proposed method allows for algae particles to be correctly identified with accuracies up to 99% and classified correctly with accuracies up to 100%.

  15. Classification of white maize defects with multispectral imaging. (United States)

    Sendin, Kate; Manley, Marena; Williams, Paul J


    Multispectral imaging with object-wise multivariate image analysis was evaluated for its potential to grade whole white maize kernels. The types of defective materials regarded in grading legislation were divided into 13 classes, and were imaged with a multispectral imaging instrument spanning the UV, visible and NIR regions (19 wavelengths ranging from 375 to 970nm). Object-wise partial least squares discriminant analysis (PLS-DA) models were developed and validated with an independent data set. Results demonstrated good performance in distinguishing between sound maize and undesirable materials, with cross-validated coefficients of determination (Q2) and classification accuracies ranging from 0.35 to 0.99 and 83 to 100%, respectively. Wavelengths related to absorbance of green, yellow and orange colour indicated the presence of lycopene and anthocyanin (505, 525, 570 and 590 nm). NIR wavelengths 890, 940 nm (associated with fat) and 970 nm (associated with water) were generally identified as important features throughout the study. Copyright © 2017 Elsevier Ltd. All rights reserved.

  16. Modelling the angular effects on satellite retrieved LST at global scale using a land surface classification (United States)

    Ermida, Sofia; DaCamara, Carlos C.; Trigo, Isabel F.; Pires, Ana C.; Ghent, Darren


    Land Surface Temperature (LST) is a key climatological variable and a diagnostic parameter of land surface conditions. Remote sensing constitutes the most effective method to observe LST over large areas and on a regular basis. Although LST estimation from remote sensing instruments operating in the Infrared (IR) is widely used and has been performed for nearly 3 decades, there is still a list of open issues. One of these is the LST dependence on viewing and illumination geometry. This effect introduces significant discrepancies among LST estimations from different sensors, overlapping in space and time, that are not related to uncertainties in the methodologies or input data used. Furthermore, these directional effects deviate LST products from an ideally defined LST, which should represent to the ensemble of directional radiometric temperature of all surface elements within the FOV. Angular effects on LST are here conveniently estimated by means of a kernel model of the surface thermal emission, which describes the angular dependence of LST as a function of viewing and illumination geometry. The model is calibrated using LST data as provided by a wide range of sensors to optimize spatial coverage, namely: 1) a LEO sensor - the Moderate Resolution Imaging Spectroradiometer (MODIS) on-board NASA's TERRA and AQUA; and 2) 3 GEO sensors - the Spinning Enhanced Visible and Infrared Imager (SEVIRI) on-board EUMETSAT's Meteosat Second Generation (MSG), the Japanese Meteorological Imager (JAMI) on-board the Japanese Meteorological Association (JMA) Multifunction Transport SATellite (MTSAT-2), and NASA's Geostationary Operational Environmental Satellites (GOES). As shown in our previous feasibility studies the sampling of illumination and view angles has a high impact on the obtained model parameters. This impact may be mitigated when the sampling size is increased by aggregating pixels with similar surface conditions. Here we propose a methodology where land surface is

  17. [Classification and imaging diagnosis of Lisfranc joint injuries]. (United States)

    Xi, Y; Hu, D J; Yao, W W; Li, M


    To accelerate the detection rate and accuracy of diagnosis in damage imaging of Lisfranc joint through research on the information of X-ray, CT, and MR imaging of tarsometatarsus joint (also called Lisfranc joint) damage. A total of 153 cases of tarsometratisus damage or Lisfranc ligamentous injury patients were chosen during November 2012 to November 2015. Lisfranc injuries were classified according to the Myerson fracture displacements classification and Nunley-Vertullo low-grade injury classification. All the treatment data was performed using SPSS 17.0 software. For Myerson fracture displacements, there were 16 cases in Myerson Ⅰ type (homolateral complete), 100 cases in Myerson Ⅱ type (homolateral incomplete), and 5 cases in Myerson Ⅲ type (divergent). For the low-grade injury, there were 7 cases, 24 cases, and 1 case in Nunley-Vertullo Ⅰ, Ⅱ, Ⅲ type respectively. The probability was 14.9% (18/121) for patients that the initial survey found negative by X-ray imaging diagnosis and was confirmed by subsequent CT or MRI. It was found that the distance between the base of first (M1) and second (M2) metatarsus which was larger than 2 mm was 69.4%(84/121)from the X-ray imaging; there were small chip fractures between the base of M1 and M2 was 47.1% (57/121), and 71.2% (37/52)of small chip fractures in the inside of base of M2 from CT. On MRI, ligament disruption showed the discontinue or normal signal disappearing, and there were 15 cases in the complete disruption condition. It should be suggested to take a CT or MRI check for the patients who have highly suspicious Lisfranc injure and the X-ray imaging diagnosis was negative, since there is a certain rate of missed diagnosis for the Lisfranc injure using X-ray imaging. For children and teenagers, the sports injuries and joint strain are common style, such as the injuries caused by jump from higher platform, football/skateboarding injures, etc. If the distance between the base of M1 and M2 is larger than

  18. Classification and printability of EUV mask defects from SEM images (United States)

    Cho, Wonil; Price, Daniel; Morgan, Paul A.; Rost, Daniel; Satake, Masaki; Tolani, Vikram L.


    Classification and Printability of EUV Mask Defects from SEM images EUV lithography is starting to show more promise for patterning some critical layers at 5nm technology node and beyond. However, there still are many key technical obstacles to overcome before bringing EUV Lithography into high volume manufacturing (HVM). One of the greatest obstacles is manufacturing defect-free masks. For pattern defect inspections in the mask-shop, cutting-edge 193nm optical inspection tools have been used so far due to lacking any e-beam mask inspection (EBMI) or EUV actinic pattern inspection (API) tools. The main issue with current 193nm inspection tools is the limited resolution for mask dimensions targeted for EUV patterning. The theoretical resolution limit for 193nm mask inspection tools is about 60nm HP on masks, which means that main feature sizes on EUV masks will be well beyond the practical resolution of 193nm inspection tools. Nevertheless, 193nm inspection tools with various illumination conditions that maximize defect sensitivity and/or main-pattern modulation are being explored for initial EUV defect detection. Due to the generally low signal-to-noise in the 193nm inspection imaging at EUV patterning dimensions, these inspections often result in hundreds and thousands of defects which then need to be accurately reviewed and dispositioned. Manually reviewing each defect is difficult due to poor resolution. In addition, the lack of a reliable aerial dispositioning system makes it very challenging to disposition for printability. In this paper, we present the use of SEM images of EUV masks for higher resolution review and disposition of defects. In this approach, most of the defects detected by the 193nm inspection tools are first imaged on a mask SEM tool. These images together with the corresponding post-OPC design clips are provided to KLA-Tencor's Reticle Decision Center (RDC) platform which provides ADC (Automated Defect Classification) and S2A (SEM

  19. Spatio-temporal multi-modality ontology for indexing and retrieving satellite images


    MESSOUDI, Wassim; FARAH, Imed Riadh; SAHEB ETTABAA, Karim; Ben Ghezala, Henda; Solaiman, Basel


    International audience; This paper presents spatio-temporal multi-modality ontology for indexing and retrieving satellite images in the high level to improve the quality of the system retrieval and to perform semantic in the retrieval process.Our approach is based on three modules: (1) regions and features extraction, (2) ontological indexing and (3) semantic image retrieval. The first module allows extracting regions from the satellite image using the fuzzy c-means FCM) segmentation algorith...

  20. [Vascular tumours and malformations, classification, pathology and imaging]. (United States)

    Wassef, M; Vanwijck, R; Clapuyt, P; Boon, L; Magalon, G


    The understanding of vascular anomalies (vascular tumours and vascular malformations) was obscured, for a long time, by confusion and uncertainties in nosology and terminology. The International Society for the Study of Vascular Anomalies (ISSVA) recently adopted a classification scheme, clearly separating vascular tumours (hemangiomas of different types) which result from active cell proliferation, from vascular malformations, which are inborn defects in vascular morphogenesis. These two types of lesions have different clinical behaviour and require different diagnostic and therapeutic strategies. The most frequent vascular tumour is infantile hemangioma. Its clinical aspects and evolution are well-known. New data have been recently obtained concerning the phenotype of tumour cells and its histogenesis. Of the numerous new vascular tumours, which have been recently described, only the congenital hemangiomas, the vascular tumours associated with the Maffucci syndrome and the tumours that may be complicated by a profound thrombocytopenia (Kasabach and Merritt phenomenon) will be considered. Vascular malformations can be classified according to the vessel(s) types they are composed of. A classification table is presented, separating the malformations of vascular trunks from tissular malformations which are more intimately embedded in the surrounding tissues. The different syndromes associated with vascular anomalies take also place in this table. The clinical, imaging and histological aspects of the most frequent malformations (capillary, venous, lymphatic and arteriovenous) are presented. This classification intend to clarify the nosology and terminology of the complex field of vascular tumours and malformation and to offer a common language to the different physicians and specialists contributing, preferably with a interdisciplinary approach, to the diagnosis and treatment of these difficult lesions.

  1. Classification of CT brain images based on deep learning networks. (United States)

    Gao, Xiaohong W; Hui, Rui; Tian, Zengmin


    While computerised tomography (CT) may have been the first imaging tool to study human brain, it has not yet been implemented into clinical decision making process for diagnosis of Alzheimer's disease (AD). On the other hand, with the nature of being prevalent, inexpensive and non-invasive, CT does present diagnostic features of AD to a great extent. This study explores the significance and impact on the application of the burgeoning deep learning techniques to the task of classification of CT brain images, in particular utilising convolutional neural network (CNN), aiming at providing supplementary information for the early diagnosis of Alzheimer's disease. Towards this end, three categories of CT images (N = 285) are clustered into three groups, which are AD, lesion (e.g. tumour) and normal ageing. In addition, considering the characteristics of this collection with larger thickness along the direction of depth (z) (~3-5 mm), an advanced CNN architecture is established integrating both 2D and 3D CNN networks. The fusion of the two CNN networks is subsequently coordinated based on the average of Softmax scores obtained from both networks consolidating 2D images along spatial axial directions and 3D segmented blocks respectively. As a result, the classification accuracy rates rendered by this elaborated CNN architecture are 85.2%, 80% and 95.3% for classes of AD, lesion and normal respectively with an average of 87.6%. Additionally, this improved CNN network appears to outperform the others when in comparison with 2D version only of CNN network as well as a number of state of the art hand-crafted approaches. As a result, these approaches deliver accuracy rates in percentage of 86.3, 85.6 ± 1.10, 86.3 ± 1.04, 85.2 ± 1.60, 83.1 ± 0.35 for 2D CNN, 2D SIFT, 2D KAZE, 3D SIFT and 3D KAZE respectively. The two major contributions of the paper constitute a new 3-D approach while applying deep learning technique to extract signature information

  2. Satellite image atlas of glaciers of the world (United States)

    Williams, Richard S.; Ferrigno, Jane G.; Williams, Richard S., Jr.; Ferrigno, Jane G.


    U.S. Geological Survey Professional Paper 1386, Satellite Image Atlas of Glaciers of the World, contains 11 chapters designated by the letters A through K. Chapter A provides a comprehensive, yet concise, review of the "State of the Earth's Cryosphere at the Beginning of the 21st Century: Glaciers, Global Snow Cover, Floating Ice, and Permafrost and Periglacial Environments," and a "Map/Poster of the Earth's Dynamic Cryosphere," and a set of eight "Supplemental Cryosphere Notes" about the Earth's Dynamic Cryosphere and the Earth System. The next 10 chapters, B through K, are arranged geographically and present glaciological information from Landsat and other sources of historic and modern data on each of the geographic areas. Chapter B covers Antarctica; Chapter C, Greenland; Chapter D, Iceland; Chapter E, Continental Europe (except for the European part of the former Soviet Union), including the Alps, the Pyrenees, Norway, Sweden, Svalbard (Norway), and Jan Mayen (Norway); Chapter F, Asia, including the European part of the former Soviet Union, China, Afghanistan, Pakistan, India, Nepal, and Bhutan; Chapter G, Turkey, Iran, and Africa; Chapter H, Irian Jaya (Indonesia) and New Zealand; Chapter I, South America; Chapter J, North America (excluding Alaska); and Chapter K, Alaska. Chapters A–D each include map plates.

  3. Water extraction technique in mountainous areas from satellite images (United States)

    Kaplan, Gordana; Avdan, Ugur


    Water monitoring is an important part of water resource management and has become an essential aspect of remote sensing. A number of indices have been developed for water extraction using satellite images. Even though all indices can extract the extent of a water body, none can do so without including a noise component, such as topographic shadows, cloud shadows, snow, ice, and buildup areas, all of which have spectrally similar characteristics under certain circumstances. In order to select the best index for water body extraction, several water indices have been compared. This paper proposes a method for extracting water bodies called the water extraction surface temperature index (WESTI). This method uses normalized difference water index (NDWI) and land surface temperature to eliminate the noise components, especially in mountainous and cold areas where other indices have very low accuracy. The results have shown that WESTI improves the NDWI results by removing more than 80% of topographic shadows, with an overall accuracy of 99% in all cases.

  4. Spectral-Spatial Shared Linear Regression for Hyperspectral Image Classification. (United States)

    Haoliang Yuan; Yuan Yan Tang


    Classification of the pixels in hyperspectral image (HSI) is an important task and has been popularly applied in many practical applications. Its major challenge is the high-dimensional small-sized problem. To deal with this problem, lots of subspace learning (SL) methods are developed to reduce the dimension of the pixels while preserving the important discriminant information. Motivated by ridge linear regression (RLR) framework for SL, we propose a spectral-spatial shared linear regression method (SSSLR) for extracting the feature representation. Comparing with RLR, our proposed SSSLR has the following two advantages. First, we utilize a convex set to explore the spatial structure for computing the linear projection matrix. Second, we utilize a shared structure learning model, which is formed by original data space and a hidden feature space, to learn a more discriminant linear projection matrix for classification. To optimize our proposed method, an efficient iterative algorithm is proposed. Experimental results on two popular HSI data sets, i.e., Indian Pines and Salinas demonstrate that our proposed methods outperform many SL methods.

  5. Renal cell carcinoma: histological classification and correlation with imaging findings

    Directory of Open Access Journals (Sweden)

    Valdair F. Muglia


    Full Text Available Abstract Renal cell carcinoma (RCC is the seventh most common histological type of cancer in the Western world and has shown a sustained increase in its prevalence. The histological classification of RCCs is of utmost importance, considering the significant prognostic and therapeutic implications of its histological subtypes. Imaging methods play an outstanding role in the diagnosis, staging and follow-up of RCC. Clear cell, papillary and chromophobe are the most common histological subtypes of RCC, and their preoperative radiological characterization, either followed or not by confirmatory percutaneous biopsy, may be particularly useful in cases of poor surgical condition, metastatic disease, central mass in a solitary kidney, and in patients eligible for molecular targeted therapy. New strategies recently developed for treating renal cancer, such as cryo and radiofrequency ablation, molecularly targeted therapy and active surveillance also require appropriate preoperative characterization of renal masses. Less common histological types, although sharing nonspecific imaging features, may be suspected on the basis of clinical and epidemiological data. The present study is aimed at reviewing the main clinical and imaging findings of histological RCC subtypes.

  6. Renal cell carcinoma: histological classification and correlation with imaging findings

    Energy Technology Data Exchange (ETDEWEB)

    Muglia, Valdair F., E-mail: [Universidade de Sao Paulo (CCIFM/FMRP/USP), Ribeirao Preto, SP (Brazil). Centro de Ciencias das Imagens e Fisica Medica. Faculdade de Medicina; Prando, Adilson [Universidade Estadual de Campinas (UNICAMP), SP (Brazil); Hospital Vera Cruz, Campinas, SP (Brazil). Dept. de Imaginologia


    Renal cell carcinoma (RCC) is the seventh most common histological type of cancer in the Western world and has shown a sustained increase in its prevalence. The histological classification of RCCs is of utmost importance, considering the significant prognostic and therapeutic implications of its histological subtypes. Imaging methods play an outstanding role in the diagnosis, staging and follow-up of RCC. Clear cell, papillary and chromophobe are the most common histological subtypes of RCC, and their preoperative radiological characterization, either followed or not by confirmatory percutaneous biopsy, may be particularly useful in cases of poor surgical condition, metastatic disease, central mass in a solitary kidney, and in patients eligible for molecular targeted therapy. New strategies recently developed for treating renal cancer, such as cryo and radiofrequency ablation, molecularly targeted therapy and active surveillance also require appropriate preoperative characterization of renal masses. Less common histological types, although sharing nonspecific imaging features, may be suspected on the basis of clinical and epidemiological data. The present study is aimed at reviewing the main clinical and imaging findings of histological RCC subtypes. (author)

  7. Methodology for mammal classification in camera trap images (United States)

    Pulido Castelblanco, Luis; Isaza Narváez, Claudia; Díaz Pulido, Angélica


    Using camera traps in animal ecology studies has increased because it facilitates the work of biologists and allows them to obtain information that otherwise would be impossible. A large number of photographs are capturing with this wildlife photography technique making difficult their posterior analysis. This paper presents a method to automatically identify the images with at least one animal and to classify them between birds and mammals. In this work a fuzzy classifier and a matched filter were used to identify the image with animals and to segment the images. An artificial neural network was employed to classify the segments between birds and mammals. We obtained a classification accuracy of 73.1% validating the model over real camera trap sessions. The database includes several difficulties, as the constant changes in the scene by climatic factors or animals partially occluded by the environment. This method was implemented in a software that is currently using in the Alexander von Humboldt Biological Resources Research Institute for studies of biodiversity in Colombia.

  8. Super-Resolution Reconstruction of High-Resolution Satellite ZY-3 TLC Images. (United States)

    Li, Lin; Wang, Wei; Luo, Heng; Ying, Shen


    Super-resolution (SR) image reconstruction is a technique used to recover a high-resolution image using the cumulative information provided by several low-resolution images. With the help of SR techniques, satellite remotely sensed images can be combined to achieve a higher-resolution image, which is especially useful for a two- or three-line camera satellite, e.g., the ZY-3 high-resolution Three Line Camera (TLC) satellite. In this paper, we introduce the application of the SR reconstruction method, including motion estimation and the robust super-resolution technique, to ZY-3 TLC images. The results show that SR reconstruction can significantly improve both the resolution and image quality of ZY-3 TLC images.

  9. Involvement of Machine Learning for Breast Cancer Image Classification: A Survey

    Directory of Open Access Journals (Sweden)

    Abdullah-Al Nahid


    Full Text Available Breast cancer is one of the largest causes of women’s death in the world today. Advance engineering of natural image classification techniques and Artificial Intelligence methods has largely been used for the breast-image classification task. The involvement of digital image classification allows the doctor and the physicians a second opinion, and it saves the doctors’ and physicians’ time. Despite the various publications on breast image classification, very few review papers are available which provide a detailed description of breast cancer image classification techniques, feature extraction and selection procedures, classification measuring parameterizations, and image classification findings. We have put a special emphasis on the Convolutional Neural Network (CNN method for breast image classification. Along with the CNN method we have also described the involvement of the conventional Neural Network (NN, Logic Based classifiers such as the Random Forest (RF algorithm, Support Vector Machines (SVM, Bayesian methods, and a few of the semisupervised and unsupervised methods which have been used for breast image classification.

  10. Statistical methods for segmentation and classification of images

    DEFF Research Database (Denmark)

    Rosholm, Anders


    The central matter of the present thesis is Bayesian statistical inference applied to classification of images. An initial review of Markov Random Fields relates to the modeling aspect of the indicated main subject. In that connection, emphasis is put on the relatively unknown sub-class of Pickard...... Random Fields (PRF's). The properties of this type of random fields are given a specially thourough treatment, including an investigation of a previously unresolved general parameterization issue. Novel insight into the parameterization of discrete versions of these fields is presented. A visual...... evaluation of the properties of Pickard Random Fields has been enabled by simulations of both continuous and discrete fields. Simulations of a compared Potts model from the traditional MRF theory are also given. Variations of the surveyed Markov Random Fields are used as prior and observation models...

  11. Assessment of Off-shore Wind Energy Resource in China using QuikSCAT Satellite data and SAR Satellite Images

    DEFF Research Database (Denmark)

    Xiuzhi, Zhang; Yanbo, Shen; Jingwei, Xu


    From August 2008 to August 2009, the project ‘Off-Shore Wind Energy Resource Assessment and Feasibility Study of Off-Shore Wind Farm Development in China’ was carried out by China Meteorological Administration (CMA), which was funded by the EU-China Energy and Environment Programme (EEP). As one...... part of the project, off-shore wind energy resource in China was assessed with QuikSCAT Satellite data and SAR Satellite Images. In this paper, the results from these two ways were introduced....

  12. Satellite Images for Monitoring Mangrove Cover Changes in a Fast Growing Economic Region in Southern Peninsular Malaysia

    Directory of Open Access Journals (Sweden)

    Kasturi Devi Kanniah


    Full Text Available Effective monitoring is necessary to conserve mangroves from further loss in Malaysia. In this context, remote sensing is capable of providing information on mangrove status and changes over a large spatial extent and in a continuous manner. In this study we used Landsat satellite images to analyze the changes over a period of 25 years of mangrove areas in Iskandar Malaysia (IM, the fastest growing national special economic region located in southern Johor, Malaysia. We tested the use of two widely used digital classification techniques to classify mangrove areas. The Maximum Likelihood Classification (MLC technique provided significantly higher user, producer and overall accuracies and less “salt and pepper effects” compared to the Support Vector Machine (SVM technique. The classified satellite images using the MLC technique showed that IM lost 6740 ha of mangrove areas from 1989 to 2014. Nevertheless, a gain of 710 ha of mangroves was observed in this region, resulting in a net loss of 6030 ha or 33%. The loss of about 241 ha per year of mangroves was associated with a steady increase in urban land use (1225 ha per year from 1989 until 2014. Action is necessary to protect the existing mangrove cover from further loss. Gazetting of the remaining mangrove sites as protected areas or forest reserves and introducing tourism activities in mangrove areas can ensure the continued survival of mangroves in IM.

  13. An Analytical Framework for Assessing the Efficacy of Small Satellites in Performing Novel Imaging Missions (United States)

    Weaver, Oesa A.

    In the last two decades, small satellites have opened up the use of space to groups other than governments and large corporations, allowing for increased participation and experimentation. This democratization of space was primarily enabled by two factors: improved technology and reduced launch costs. Improved technology allowed the miniaturization of components and reduced overall cost meaning many of the capabilities of larger satellites could be replicated at a fraction of the cost. In addition, new launcher systems that could host many small satellites as ride-shares on manifested vehicles lowered launch costs and simplified the process of getting a satellite into orbit. The potential of these smaller satellites to replace or augment existing systems has led to a flood of potential satellite and mission concepts, often with little rigorous study of whether the proposed satellite or mission is achievable or necessary. This work proposes an analytical framework to aid system designers in evaluating the ability of an existing concept or small satellite to perform a particular imaging mission, either replacing or augmenting existing capabilities. This framework was developed and then refined by application to the problem of using small satellites to perform a wide area search mission -- a mission not possible with existing imaging satellites, but one that would add to current capabilities. Requirements for a wide area search mission were developed, along with a list of factors that would affect image quality and system performance. Two existing small satellite concepts were evaluated for use by examining image quality from the systems, selecting an algorithm to perform the search function automatically, and then assessing mission feasibility by applying the algorithm to simulated imagery. Finally, a notional constellation design was developed to assess the number of satellites required to perform the mission. It was found that a constellation of 480 Cube

  14. Automated outcome classification of emergency department computed tomography imaging reports. (United States)

    Yadav, Kabir; Sarioglu, Efsun; Smith, Meaghan; Choi, Hyeong-Ah


    Reliably abstracting outcomes from free-text electronic health records remains a challenge. While automated classification of free text has been a popular medical informatics topic, performance validation using real-world clinical data has been limited. The two main approaches are linguistic (natural language processing [NLP]) and statistical (machine learning). The authors have developed a hybrid system for abstracting computed tomography (CT) reports for specified outcomes. The objective was to measure performance of a hybrid NLP and machine learning system for automated outcome classification of emergency department (ED) CT imaging reports. The hypothesis was that such a system is comparable to medical personnel doing the data abstraction. A secondary analysis was performed on a prior diagnostic imaging study on 3,710 blunt facial trauma victims. Staff radiologists dictated CT reports as free text, which were then deidentified. A trained data abstractor manually coded the reference standard outcome of acute orbital fracture, with a random subset double-coded for reliability. The data set was randomly split evenly into training and testing sets. Training patient reports were used as input to the Medical Language Extraction and Encoding (MedLEE) NLP tool to create structured output containing standardized medical terms and modifiers for certainty and temporal status. Findings were filtered for low certainty and past/future modifiers and then combined with the manual reference standard to generate decision tree classifiers using data mining tools Waikato Environment for Knowledge Analysis (WEKA) 3.7.5 and Salford Predictive Miner 6.6. Performance of decision tree classifiers was evaluated on the testing set with or without NLP processing. The performance of machine learning alone was comparable to prior NLP studies (sensitivity = 0.92, specificity = 0.93, precision = 0.95, recall = 0.93, f-score = 0.94), and the combined use of NLP and machine learning showed

  15. Scene Classification of Remote Sensing Image Based on Multi-scale Feature and Deep Neural Network

    Directory of Open Access Journals (Sweden)

    XU Suhui


    Full Text Available Aiming at low precision of remote sensing image scene classification owing to small sample sizes, a new classification approach is proposed based on multi-scale deep convolutional neural network (MS-DCNN, which is composed of nonsubsampled Contourlet transform (NSCT, deep convolutional neural network (DCNN, and multiple-kernel support vector machine (MKSVM. Firstly, remote sensing image multi-scale decomposition is conducted via NSCT. Secondly, the decomposing high frequency and low frequency subbands are trained by DCNN to obtain image features in different scales. Finally, MKSVM is adopted to integrate multi-scale image features and implement remote sensing image scene classification. The experiment results in the standard image classification data sets indicate that the proposed approach obtains great classification effect due to combining the recognition superiority to different scenes of low frequency and high frequency subbands.


    National Aeronautics and Space Administration — MULTI-TEMPORAL REMOTE SENSING IMAGE CLASSIFICATION - A MULTI-VIEW APPROACH VARUN CHANDOLA AND RANGA RAJU VATSAVAI Abstract. Multispectral remote sensing images have...


    Directory of Open Access Journals (Sweden)

    C. Bao


    Full Text Available As the increment of remote sensing data with multi-space resolution, multi-spectral resolution and multi-source, data fusion technologies have been widely used in geological fields. Synthetic Aperture Radar (SAR and optical camera are two most common sensors presently. The multi-spectral optical images express spectral features of ground objects, while SAR images express backscatter information. Accuracy of the image classification could be effectively improved fusing the two kinds of images. In this paper, Terra SAR-X images and ALOS multi-spectral images were fused for land use classification. After preprocess such as geometric rectification, radiometric rectification noise suppression and so on, the two kind images were fused, and then SVM model identification method was used for land use classification. Two different fusion methods were used, one is joining SAR image into multi-spectral images as one band, and the other is direct fusing the two kind images. The former one can raise the resolution and reserve the texture information, and the latter can reserve spectral feature information and improve capability of identifying different features. The experiment results showed that accuracy of classification using fused images is better than only using multi-spectral images. Accuracy of classification about roads, habitation and water bodies was significantly improved. Compared to traditional classification method, the method of this paper for fused images with SVM classifier could achieve better results in identifying complicated land use classes, especially for small pieces ground features.

  18. Assessing village authenticity with satellite images: a method to identify intact cultural landscapes in Europe. (United States)

    Angelstam, Per; Boresjö-Bronge, Laine; Mikusiński, Grzegorz; Sporrong, Ulf; Wästfelt, Anders


    The village with its characteristic zones of different land use from the center to the periphery is a basic unit of Europe's cultural landscapes. However, loss of the authentic pre-industrial village structure characterized by a fine-grained structure of arable land and wooded grasslands is a threat to both cultural heritage and biodiversity in many rural landscapes. Therefore, it is important that the extent and rate of change of such authentic villages in a landscape can be monitored. We studied to what extent loss of authenticity with increasing time after abandonment can be assessed by quantitative analysis and visual interpretation of satellite images. The study was carried out in the Bieszczady Mountains, SE Poland in 1999. Using Landsat Thematic Mapper data from 1998, both the grain size of landscape elements (size of fields) and land-cover composition (encroachment of shrub and forest) were quantitatively described 6 type villages representing different stages of deterioration of the authentic village structure. Historical maps were used to delineate the border of the villages and the former extension of forest and open land was measured. The present land use and the degree of abandonment expressed as grain size and forest encroachment were mapped using satellite data. Deterioration occurred along 2 transformation paths: abandonment and ultimately becoming forest, or intensified agriculture, respectively. To validate these results we classified 22 other villages in a 1000 km2 area by visual interpretation of the original satellite images into 1 of 4 types. We then collected historical data on human population changes over the past six decades. The classification of village authenticity was clearly related to the rate of human population decline. We address the importance of validating and applying this approach for rapid assessment of the authenticity of cultural landscapes in European regions being subject to ongoing as well as expected future change

  19. Creating a classification of image types in the medical literature for visual categorization (United States)

    Müller, Henning; Kalpathy-Cramer, Jayashree; Demner-Fushman, Dina; Antani, Sameer


    Content-based image retrieval (CBIR) from specialized collections has often been proposed for use in such areas as diagnostic aid, clinical decision support, and teaching. The visual retrieval from broad image collections such as teaching files, the medical literature or web images, by contrast, has not yet reached a high maturity level compared to textual information retrieval. Visual image classification into a relatively small number of classes (20-100) on the other hand, has shown to deliver good results in several benchmarks. It is, however, currently underused as a basic technology for retrieval tasks, for example, to limit the search space. Most classification schemes for medical images are focused on specific areas and consider mainly the medical image types (modalities), imaged anatomy, and view, and merge them into a single descriptor or classification hierarchy. Furthermore, they often ignore other important image types such as biological images, statistical figures, flowcharts, and diagrams that frequently occur in the biomedical literature. Most of the current classifications have also been created for radiology images, which are not the only types to be taken into account. With Open Access becoming increasingly widespread particularly in medicine, images from the biomedical literature are more easily available for use. Visual information from these images and knowledge that an image is of a specific type or medical modality could enrich retrieval. This enrichment is hampered by the lack of a commonly agreed image classification scheme. This paper presents a hierarchy for classification of biomedical illustrations with the goal of using it for visual classification and thus as a basis for retrieval. The proposed hierarchy is based on relevant parts of existing terminologies, such as the IRMA-code (Image Retrieval in Medical Applications), ad hoc classifications and hierarchies used in imageCLEF (Image retrieval task at the Cross-Language Evaluation

  20. Mapping species of submerged aquatic vegetation with multi-seasonal satellite images and considering life history information (United States)

    Luo, Juhua; Duan, Hongtao; Ma, Ronghua; Jin, Xiuliang; Li, Fei; Hu, Weiping; Shi, Kun; Huang, Wenjiang


    Spatial information of the dominant species of submerged aquatic vegetation (SAV) is essential for restoration projects in eutrophic lakes, especially eutrophic Taihu Lake, China. Mapping the distribution of SAV species is very challenging and difficult using only multispectral satellite remote sensing. In this study, we proposed an approach to map the distribution of seven dominant species of SAV in Taihu Lake. Our approach involved information on the life histories of the seven SAV species and eight distribution maps of SAV from February to October. The life history information of the dominant SAV species was summarized from the literature and field surveys. Eight distribution maps of the SAV were extracted from eight 30 m HJ-CCD images from February to October in 2013 based on the classification tree models, and the overall classification accuracies for the SAV were greater than 80%. Finally, the spatial distribution of the SAV species in Taihu in 2013 was mapped using multilayer erasing approach. Based on validation, the overall classification accuracy for the seven species was 68.4%, and kappa was 0.6306, which suggests that larger differences in life histories between species can produce higher identification accuracies. The classification results show that Potamogeton malaianus was the most widely distributed species in Taihu Lake, followed by Myriophyllum spicatum, Potamogeton maackianus, Potamogeton crispus, Elodea nuttallii, Ceratophyllum demersum and Vallisneria spiralis. The information is useful for planning shallow-water habitat restoration projects.

  1. Proceedings of the Second Annual Symposium on Mathematical Pattern Recognition and Image Analysis Program (United States)

    Guseman, L. F., Jr. (Principal Investigator)


    Several papers addressing image analysis and pattern recognition techniques for satellite imagery are presented. Texture classification, image rectification and registration, spatial parameter estimation, and surface fitting are discussed.

  2. Accuracy comparison of Pléiades satellite ortho-images using GPS ...

    African Journals Online (AJOL)

    Ivan Henrico

    2Hartebeesthoek Radio Astronomy Observatory. 3Airbus Defence and Space, Geo-Intelligence Abstract. Conducting single frame orthorectification on satellite images to create an ortho-image requires four basic components, namely an image, a geometric sensor model, elevation data ...

  3. Vegetation Cover Change in Yosemite National Park (California) Detected using Landsat Satellite Image Analysis (United States)

    Potter, Christopher


    Landsat image analysis over the past 20+ years showed that consistent increases in the satellite normalized difference vegetation index (NDVI) during relatively dry years were confined to large wildfire areas that burned in the late 1980s and 1990s.

  4. Image Positioning Accuracy Analysis for Super Low Altitude Remote Sensing Satellites

    Directory of Open Access Journals (Sweden)

    Ming Xu


    Full Text Available Super low altitude remote sensing satellites maintain lower flight altitudes by means of ion propulsion in order to improve image resolution and positioning accuracy. The use of engineering data in design for achieving image positioning accuracy is discussed in this paper based on the principles of the photogrammetry theory. The exact line-of-sight rebuilding of each detection element and this direction precisely intersecting with the Earth's elliptical when the camera on the satellite is imaging are both ensured by the combined design of key parameters. These parameters include: orbit determination accuracy, attitude determination accuracy, camera exposure time, accurately synchronizing the reception of ephemeris with attitude data, geometric calibration and precise orbit verification. Precise simulation calculations show that image positioning accuracy of super low altitude remote sensing satellites is not obviously improved. The attitude determination error of a satellite still restricts its positioning accuracy.

  5. Review of Medical Image Classification using the Adaptive Neuro-Fuzzy Inference System. (United States)

    Hosseini, Monireh Sheikh; Zekri, Maryam


    Image classification is an issue that utilizes image processing, pattern recognition and classification methods. Automatic medical image classification is a progressive area in image classification, and it is expected to be more developed in the future. Because of this fact, automatic diagnosis can assist pathologists by providing second opinions and reducing their workload. This paper reviews the application of the adaptive neuro-fuzzy inference system (ANFIS) as a classifier in medical image classification during the past 16 years. ANFIS is a fuzzy inference system (FIS) implemented in the framework of an adaptive fuzzy neural network. It combines the explicit knowledge representation of an FIS with the learning power of artificial neural networks. The objective of ANFIS is to integrate the best features of fuzzy systems and neural networks. A brief comparison with other classifiers, main advantages and drawbacks of this classifier are investigated.

  6. Geospatial mapping of Antarctic coastal oasis using geographic object-based image analysis and high resolution satellite imagery (United States)

    Jawak, Shridhar D.; Luis, Alvarinho J.


    An accurate spatial mapping and characterization of land cover features in cryospheric regions is an essential procedure for many geoscientific studies. A novel semi-automated method was devised by coupling spectral index ratios (SIRs) and geographic object-based image analysis (OBIA) to extract cryospheric geospatial information from very high resolution WorldView 2 (WV-2) satellite imagery. The present study addresses development of multiple rule sets for OBIA-based classification of WV-2 imagery to accurately extract land cover features in the Larsemann Hills, east Antarctica. Multilevel segmentation process was applied to WV-2 image to generate different sizes of geographic image objects corresponding to various land cover features with respect to scale parameter. Several SIRs were applied to geographic objects at different segmentation levels to classify land mass, man-made features, snow/ice, and water bodies. We focus on water body class to identify water areas at the image level, considering their uneven appearance on landmass and ice. The results illustrated that synergetic usage of SIRs and OBIA can provide accurate means to identify land cover classes with an overall classification accuracy of ≍97%. In conclusion, our results suggest that OBIA is a powerful tool for carrying out automatic and semiautomatic analysis for most cryospheric remote-sensing applications, and the synergetic coupling with pixel-based SIRs is found to be a superior method for mining geospatial information.

  7. Geographic Object-based Image Analysis for Developing Cryospheric Surface Mapping Application using Remotely Sensed High-Resolution Satellite Imagery (United States)

    Jawak, S. D.; Luis, A. J.


    A novel semi-automated method was devised by coupling spectral index ratios (SIRs) and geographic object-based image analysis (GEOBIA) to extract cryospheric geoinformation from very high resolution WorldView 2 (WV-2) satellite imagery. The present study addresses development of multiple rule sets for GEOBIA-based classification of WV-2 imagery to accurately extract land cover features in the Larsemann Hills, Antarctica. Multi-level segmentation process was applied to WV-2 image to generate different sizes of geographic image objects corresponding to various land cover features w.r.t scale parameter. Several SIRs were applied to geographic objects at different segmentation levels to classify landmass, man-made features, snow/ice, and water bodies. A specific attention was paid to water body class to identify water areas at the image level, considering their uneven appearance on landmass and ice. The results illustrated that synergetic usage of SIRs and GEOBIA can provide accurate means to identify land cover classes with an overall classification accuracy of ≈97%. In conclusion, the results suggest that GEOBIA is a powerful tool for carrying out automatic and semiautomatic analysis for most cryospheric remote-sensing applications, and the synergetic coupling with pixel-based SIRs is found to be a superior method for mining geoinformation.

  8. Decomposition-based transfer distance metric learning for image classification. (United States)

    Luo, Yong; Liu, Tongliang; Tao, Dacheng; Xu, Chao


    Distance metric learning (DML) is a critical factor for image analysis and pattern recognition. To learn a robust distance metric for a target task, we need abundant side information (i.e., the similarity/dissimilarity pairwise constraints over the labeled data), which is usually unavailable in practice due to the high labeling cost. This paper considers the transfer learning setting by exploiting the large quantity of side information from certain related, but different source tasks to help with target metric learning (with only a little side information). The state-of-the-art metric learning algorithms usually fail in this setting because the data distributions of the source task and target task are often quite different. We address this problem by assuming that the target distance metric lies in the space spanned by the eigenvectors of the source metrics (or other randomly generated bases). The target metric is represented as a combination of the base metrics, which are computed using the decomposed components of the source metrics (or simply a set of random bases); we call the proposed method, decomposition-based transfer DML (DTDML). In particular, DTDML learns a sparse combination of the base metrics to construct the target metric by forcing the target metric to be close to an integration of the source metrics. The main advantage of the proposed method compared with existing transfer metric learning approaches is that we directly learn the base metric coefficients instead of the target metric. To this end, far fewer variables need to be learned. We therefore obtain more reliable solutions given the limited side information and the optimization tends to be faster. Experiments on the popular handwritten image (digit, letter) classification and challenge natural image annotation tasks demonstrate the effectiveness of the proposed method.

  9. Multi-view Multi-sparsity Kernel Reconstruction for Multi-class Image Classification

    KAUST Repository

    Zhu, Xiaofeng


    This paper addresses the problem of multi-class image classification by proposing a novel multi-view multi-sparsity kernel reconstruction (MMKR for short) model. Given images (including test images and training images) representing with multiple visual features, the MMKR first maps them into a high-dimensional space, e.g., a reproducing kernel Hilbert space (RKHS), where test images are then linearly reconstructed by some representative training images, rather than all of them. Furthermore a classification rule is proposed to classify test images. Experimental results on real datasets show the effectiveness of the proposed MMKR while comparing to state-of-the-art algorithms.

  10. Crowds for Clouds: Using an Internet Workforce to Interpret Satellite Images


    YU Ling; Ball, Sheryl; Christine E. Blinn; Moeltner, Klaus; Peery, Seth; Valerie A. Thomas; Randolph H. Wynne


    A chronologically ordered sequence of satellite images can be used to learn how natural features of the landscape change over time. For example, we can learn how forests react to human interventions or climate change. Before these satellite images can be used for this purpose, they need to be examined for clouds and cloud shadow that may hide important features of the landscape and would lead to misinterpretation of forest conditions. Once clouds and their shadow have been identified, researc...

  11. A Selective Ensemble Classification Method Combining Mammography Images with Ultrasound Images for Breast Cancer Diagnosis

    Directory of Open Access Journals (Sweden)

    Jinyu Cong


    Full Text Available Breast cancer has been one of the main diseases that threatens women’s life. Early detection and diagnosis of breast cancer play an important role in reducing mortality of breast cancer. In this paper, we propose a selective ensemble method integrated with the KNN, SVM, and Naive Bayes to diagnose the breast cancer combining ultrasound images with mammography images. Our experimental results have shown that the selective classification method with an accuracy of 88.73% and sensitivity of 97.06% is efficient for breast cancer diagnosis. And indicator R presents a new way to choose the base classifier for ensemble learning.

  12. Feature Extraction in Sequential Multimedia Images: with Applications in Satellite Images and On-line Videos (United States)

    Liang, Yu-Li

    Multimedia data is increasingly important in scientific discovery and people's daily lives. Content of massive multimedia is often diverse and noisy, and motion between frames is sometimes crucial in analyzing those data. Among all, still images and videos are commonly used formats. Images are compact in size but do not contain motion information. Videos record motion but are sometimes too big to be analyzed. Sequential images, which are a set of continuous images with low frame rate, stand out because they are smaller than videos and still maintain motion information. This thesis investigates features in different types of noisy sequential images, and the proposed solutions that intelligently combined multiple features to successfully retrieve visual information from on-line videos and cloudy satellite images. The first task is detecting supraglacial lakes above ice sheet in sequential satellite images. The dynamics of supraglacial lakes on the Greenland ice sheet deeply affect glacier movement, which is directly related to sea level rise and global environment change. Detecting lakes above ice is suffering from diverse image qualities and unexpected clouds. A new method is proposed to efficiently extract prominent lake candidates with irregular shapes, heterogeneous backgrounds, and in cloudy images. The proposed system fully automatize the procedure that track lakes with high accuracy. We further cooperated with geoscientists to examine the tracked lakes and found new scientific findings. The second one is detecting obscene content in on-line video chat services, such as Chatroulette, that randomly match pairs of users in video chat sessions. A big problem encountered in such systems is the presence of flashers and obscene content. Because of various obscene content and unstable qualities of videos capture by home web-camera, detecting misbehaving users is a highly challenging task. We propose SafeVchat, which is the first solution that achieves satisfactory

  13. NEPR World View 2 Satellite Mosaic - NOAA TIFF Image (United States)

    National Oceanic and Atmospheric Administration, Department of Commerce — This GeoTiff is a mosaic of World View 2 panchromatic satellite imagery of Northeast Puerto Rico that contains the shallow water area (0-35m deep) surrounding...

  14. NOAA Geostationary Operational Environmental Satellite (GOES) Imager Data (United States)

    National Oceanic and Atmospheric Administration, Department of Commerce — The NOAA Geostationary Operational Environmental Satellite (GOES) series provides continuous measurements of the atmosphere and surface over the Western Hemisphere....


    Directory of Open Access Journals (Sweden)

    T. Alipour Fard


    Full Text Available This study concerned with fusion of synthetic aperture radar and optical satellite imagery. Due to the difference in the underlying sensor technology, data from synthetic aperture radar (SAR and optical sensors refer to different properties of the observed scene and it is believed that when they are fused together, they complement each other to improve the performance of a particular application. In this paper, two category of features are generate and six classifier fusion operators implemented and evaluated. Implementation results show significant improvement in the classification accuracy.

  16. Medical image classification based on multi-scale non-negative sparse coding. (United States)

    Zhang, Ruijie; Shen, Jian; Wei, Fushan; Li, Xiong; Sangaiah, Arun Kumar


    With the rapid development of modern medical imaging technology, medical image classification has become more and more important in medical diagnosis and clinical practice. Conventional medical image classification algorithms usually neglect the semantic gap problem between low-level features and high-level image semantic, which will largely degrade the classification performance. To solve this problem, we propose a multi-scale non-negative sparse coding based medical image classification algorithm. Firstly, Medical images are decomposed into multiple scale layers, thus diverse visual details can be extracted from different scale layers. Secondly, for each scale layer, the non-negative sparse coding model with fisher discriminative analysis is constructed to obtain the discriminative sparse representation of medical images. Then, the obtained multi-scale non-negative sparse coding features are combined to form a multi-scale feature histogram as the final representation for a medical image. Finally, SVM classifier is combined to conduct medical image classification. The experimental results demonstrate that our proposed algorithm can effectively utilize multi-scale and contextual spatial information of medical images, reduce the semantic gap in a large degree and improve medical image classification performance. Copyright © 2017 Elsevier B.V. All rights reserved.

  17. Storm diagnostic/predictive images derived from a combination of lightning and satellite imagery (United States)

    Goodman, Steven J.; Buechler, Dennis E.; Meyer, Paul J.


    A technique is presented for generating trend or convective tendency images using a combination of GOES satellite imagery and cloud-to-ground lightning observations. The convective tendency images can be used for short term forecasting of storm development. A conceptual model of cloud electrical development and an example of the methodology used to generate lightning/satellite convective tendency imagery are given. Successive convective tendency images can be looped or animated to show the previous growth or decay of thunderstorms and their associated lighting activity. It is suggested that the convective tendency image may also be used to indicate potential microburst producing storms.

  18. Performance Evaluation of Frequency Transform Based Block Classification of Compound Image Segmentation Techniques (United States)

    Selwyn, Ebenezer Juliet; Florinabel, D. Jemi


    Compound image segmentation plays a vital role in the compression of computer screen images. Computer screen images are images which are mixed with textual, graphical, or pictorial contents. In this paper, we present a comparison of two transform based block classification of compound images based on metrics like speed of classification, precision and recall rate. Block based classification approaches normally divide the compound images into fixed size blocks of non-overlapping in nature. Then frequency transform like Discrete Cosine Transform (DCT) and Discrete Wavelet Transform (DWT) are applied over each block. Mean and standard deviation are computed for each 8 × 8 block and are used as features set to classify the compound images into text/graphics and picture/background block. The classification accuracy of block classification based segmentation techniques are measured by evaluation metrics like precision and recall rate. Compound images of smooth background and complex background images containing text of varying size, colour and orientation are considered for testing. Experimental evidence shows that the DWT based segmentation provides significant improvement in recall rate and precision rate approximately 2.3% than DCT based segmentation with an increase in block classification time for both smooth and complex background images.

  19. On the Implementation of a Land Cover Classification System for SAR Images Using Khoros (United States)

    Medina Revera, Edwin J.; Espinosa, Ramon Vasquez


    The Synthetic Aperture Radar (SAR) sensor is widely used to record data about the ground under all atmospheric conditions. The SAR acquired images have very good resolution which necessitates the development of a classification system that process the SAR images to extract useful information for different applications. In this work, a complete system for the land cover classification was designed and programmed using the Khoros, a data flow visual language environment, taking full advantages of the polymorphic data services that it provides. Image analysis was applied to SAR images to improve and automate the processes of recognition and classification of the different regions like mountains and lakes. Both unsupervised and supervised classification utilities were used. The unsupervised classification routines included the use of several Classification/Clustering algorithms like the K-means, ISO2, Weighted Minimum Distance, and the Localized Receptive Field (LRF) training/classifier. Different texture analysis approaches such as Invariant Moments, Fractal Dimension and Second Order statistics were implemented for supervised classification of the images. The results and conclusions for SAR image classification using the various unsupervised and supervised procedures are presented based on their accuracy and performance.

  20. Segmentation-Based PolSAR Image Classification Using Visual Features: RHLBP and Color Features

    Directory of Open Access Journals (Sweden)

    Jian Cheng


    Full Text Available A segmentation-based fully-polarimetric synthetic aperture radar (PolSAR image classification method that incorporates texture features and color features is designed and implemented. This method is based on the framework that conjunctively uses statistical region merging (SRM for segmentation and support vector machine (SVM for classification. In the segmentation step, we propose an improved local binary pattern (LBP operator named the regional homogeneity local binary pattern (RHLBP to guarantee the regional homogeneity in PolSAR images. In the classification step, the color features extracted from false color images are applied to improve the classification accuracy. The RHLBP operator and color features can provide discriminative information to separate those pixels and regions with similar polarimetric features, which are from different classes. Extensive experimental comparison results with conventional methods on L-band PolSAR data demonstrate the effectiveness of our proposed method for PolSAR image classification.

  1. Fast Low-Rank Shared Dictionary Learning for Image Classification (United States)

    Vu, Tiep Huu; Monga, Vishal


    Despite the fact that different objects possess distinct class-specific features, they also usually share common patterns. This observation has been exploited partially in a recently proposed dictionary learning framework by separating the particularity and the commonality (COPAR). Inspired by this, we propose a novel method to explicitly and simultaneously learn a set of common patterns as well as class-specific features for classification with more intuitive constraints. Our dictionary learning framework is hence characterized by both a shared dictionary and particular (class-specific) dictionaries. For the shared dictionary, we enforce a low-rank constraint, i.e. claim that its spanning subspace should have low dimension and the coefficients corresponding to this dictionary should be similar. For the particular dictionaries, we impose on them the well-known constraints stated in the Fisher discrimination dictionary learning (FDDL). Further, we develop new fast and accurate algorithms to solve the subproblems in the learning step, accelerating its convergence. The said algorithms could also be applied to FDDL and its extensions. The efficiencies of these algorithms are theoretically and experimentally verified by comparing their complexities and running time with those of other well-known dictionary learning methods. Experimental results on widely used image datasets establish the advantages of our method over state-of-the-art dictionary learning methods.

  2. Research On The Classification Of High Resolution Image Based On Object-oriented And Class Rule (United States)

    Li, C. K.; Fang, W.; Dong, X. J.


    With the development of remote sensing technology, the spatial resolution, spectral resolution and time resolution of remote sensing data is greatly improved. How to efficiently process and interpret the massive high resolution remote sensing image data for ground objects, which with spatial geometry and texture information, has become the focus and difficulty in the field of remote sensing research. An object oriented and rule of the classification method of remote sensing data has presents in this paper. Through the discovery and mining the rich knowledge of spectrum and spatial characteristics of high-resolution remote sensing image, establish a multi-level network image object segmentation and classification structure of remote sensing image to achieve accurate and fast ground targets classification and accuracy assessment. Based on worldview-2 image data in the Zangnan area as a study object, using the object-oriented image classification method and rules to verify the experiment which is combination of the mean variance method, the maximum area method and the accuracy comparison to analysis, selected three kinds of optimal segmentation scale and established a multi-level image object network hierarchy for image classification experiments. The results show that the objectoriented rules classification method to classify the high resolution images, enabling the high resolution image classification results similar to the visual interpretation of the results and has higher classification accuracy. The overall accuracy and Kappa coefficient of the object-oriented rules classification method were 97.38%, 0.9673; compared with object-oriented SVM method, respectively higher than 6.23%, 0.078; compared with object-oriented KNN method, respectively more than 7.96%, 0.0996. The extraction precision and user accuracy of the building compared with object-oriented SVM method, respectively higher than 18.39%, 3.98%, respectively better than the object-oriented KNN method 21

  3. New approach using Bayesian Network to improve content based image classification systems


    jayech, Khlifia; mahjoub, mohamed ali


    This paper proposes a new approach based on augmented naive Bayes for image classification. Initially, each image is cutting in a whole of blocks. For each block, we compute a vector of descriptors. Then, we propose to carry out a classification of the vectors of descriptors to build a vector of labels for each image. Finally, we propose three variants of Bayesian Networks such as Naive Bayesian Network (NB), Tree Augmented Naive Bayes (TAN) and Forest Augmented Naive Bayes (FAN) to classify ...

  4. Satellite Image Edge Detection for Population Distribution Pattern Identification using Levelset with Morphological Filtering Process (United States)

    Harsiti; Munandar, T. A.; Suhendar, A.; Abdullah, A. G.; Rohendi, D.


    Population distribution pattern is directly related with economic gap of a region. Analysis of population distribution pattern is usually performed by studying statistical data on population. This study aimed to analyze population distribution pattern using image analysis concept, i.e. using satellite images. Levelset and morphological image filtering methods were used to analyze images to see distribution pattern. The research result showed that Levelset and morphological image filtering could remove a lot of noises in analysis result images and form object edge contours very clearly. The detected object contours were used as references to recognize population distribution pattern based on satellite image analysis. The pattern made based on the research result didn’t show optimal result because Levelset performed image segmentation based on the contours of the analyzed objects. Other segmentation methods should be combined with it to produce clearer population distribution pattern.

  5. Planetary geodetic control using satellite imaging. [equations for determination of control points from surface television-imagery (United States)

    Duxbury, T. C.


    A new data type for planetary geodetic control using natural satellite imaging is presented. Spacecraft images of natural satellites against the planet give a direct tie between inertial space and surface features surrounding the satellite image. This technique is expected to offer a factor of 3-10 improvement in accuracy over present geodetic reduction for Mars. A specific example using Viking imaging of Phobos against Mars is given.

  6. Segmentation of Clinical Endoscopic Images Based on the Classification of Topological Vector Features

    Directory of Open Access Journals (Sweden)

    O. A. Dunaeva


    Full Text Available In this work, we describe a prototype of an automatic segmentation system and annotation of endoscopy images. The used algorithm is based on the classification of vectors of the topological features of the original image. We use the image processing scheme which includes image preprocessing, calculation of vector descriptors defined for every point of the source image and the subsequent classification of descriptors. Image preprocessing includes finding and selecting artifacts and equalizating the image brightness. In this work, we give the detailed algorithm of the construction of topological descriptors and the classifier creating procedure based on mutual sharing the AdaBoost scheme and a naive Bayes classifier. In the final section, we show the results of the classification of real endoscopic images.

  7. Dealing with missing data in remote sensing images within land and crop classification (United States)

    Skakun, Sergii; Kussul, Nataliia; Basarab, Ruslan

    of non-missing data to the subspace vectors in the map. Restoration of the missing values is performed in the following way. The multi-temporal pixel values (with gaps) are put to the neural network. A neuron-winner (or a best matching unit, BMU) in the SOM is selected based on the distance metric (for example, Euclidian). It should be noted that missing values are omitted from metric estimation when selecting BMU. When the BMU is selected, missing values are substituted by corresponding components of the BMU values. The efficiency of the proposed approach was tested on a time-series of Landsat-8 images over the JECAM test site in Ukraine and Sich-2 images over Crimea (Sich-2 is Ukrainian remote sensing satellite acquiring images at 8m spatial resolution). Landsat-8 images were first converted to the TOA reflectance, and then were atmospherically corrected so each pixel value represents a surface reflectance in the range from 0 to 1. The error of reconstruction (error of quantization) on training data was: band-2: 0.015; band-3: 0.020; band-4: 0.026; band-5: 0.070; band-6: 0.060; band-7: 0.055. The reconstructed images were also used for crop classification using a multi-layer perceptron (MLP). Overall accuracy was 85.98% and Cohen's kappa was 0.83. References. 1. Skakun, S., Kussul, N., Shelestov, A. and Kussul, O. “Flood Hazard and Flood Risk Assessment Using a Time Series of Satellite Images: A Case Study in Namibia,” Risk Analysis, 2013, doi: 10.1111/risa.12156. 2. Gallego, F.J., Kussul, N., Skakun, S., Kravchenko, O., Shelestov, A., Kussul, O. “Efficiency assessment of using satellite data for crop area estimation in Ukraine,” International Journal of Applied Earth Observation and Geoinformation, vol. 29, pp. 22-30, 2014. 3. Roy D.P., Ju, J., Lewis, P., Schaaf, C., Gao, F., Hansen, M., and Lindquist, E., “Multi-temporal MODIS-Landsat data fusion for relative radiometric normalization, gap filling, and prediction of Landsat data,” Remote Sensing of

  8. Autonomous Sub-Pixel Satellite Track Endpoint Determination for Space Based Images

    Energy Technology Data Exchange (ETDEWEB)

    Simms, L M


    An algorithm for determining satellite track endpoints with sub-pixel resolution in spaced-based images is presented. The algorithm allows for significant curvature in the imaged track due to rotation of the spacecraft capturing the image. The motivation behind the subpixel endpoint determination is first presented, followed by a description of the methodology used. Results from running the algorithm on real ground-based and simulated spaced-based images are shown to highlight its effectiveness.

  9. A Spectral Signature Shape-Based Algorithm for Landsat Image Classification

    Directory of Open Access Journals (Sweden)

    Yuanyuan Chen


    Full Text Available Land-cover datasets are crucial for earth system modeling and human-nature interaction research at local, regional and global scales. They can be obtained from remotely sensed data using image classification methods. However, in processes of image classification, spectral values have received considerable attention for most classification methods, while the spectral curve shape has seldom been used because it is difficult to be quantified. This study presents a classification method based on the observation that the spectral curve is composed of segments and certain extreme values. The presented classification method quantifies the spectral curve shape and takes full use of the spectral shape differences among land covers to classify remotely sensed images. Using this method, classification maps from TM (Thematic mapper data were obtained with an overall accuracy of 0.834 and 0.854 for two respective test areas. The approach presented in this paper, which differs from previous image classification methods that were mostly concerned with spectral “value” similarity characteristics, emphasizes the "shape" similarity characteristics of the spectral curve. Moreover, this study will be helpful for classification research on hyperspectral and multi-temporal images.

  10. Exploring Google Earth Engine platform for big data processing: classification of multi-temporal satellite imagery for crop mapping (United States)

    Shelestov, Andrii; Lavreniuk, Mykola; Kussul, Nataliia; Novikov, Alexei; Skakun, Sergii


    Many applied problems arising in agricultural monitoring and food security require reliable crop maps at national or global scale. Large scale crop mapping requires processing and management of large amount of heterogeneous satellite imagery acquired by various sensors that consequently leads to a “Big Data” problem. The main objective of this study is to explore efficiency of using the Google Earth Engine (GEE) platform when classifying multi-temporal satellite imagery with potential to apply the platform for a larger scale (e.g. country level) and multiple sensors (e.g. Landsat-8 and Sentinel-2). In particular, multiple state-of-the-art classifiers available in the GEE platform are compared to produce a high resolution (30 m) crop classification map for a large territory ( 28,100 km2 and 1.0 M ha of cropland). Though this study does not involve large volumes of data, it does address efficiency of the GEE platform to effectively execute complex workflows of satellite data processing required with large scale applications such as crop mapping. The study discusses strengths and weaknesses of classifiers, assesses accuracies that can be achieved with different classifiers for the Ukrainian landscape, and compares them to the benchmark classifier using a neural network approach that was developed in our previous studies. The study is carried out for the Joint Experiment of Crop Assessment and Monitoring (JECAM) test site in Ukraine covering the Kyiv region (North of Ukraine) in 2013. We found that Google Earth Engine (GEE) provides very good performance in terms of enabling access to the remote sensing products through the cloud platform and providing pre-processing; however, in terms of classification accuracy, the neural network based approach outperformed support vector machine (SVM), decision tree and random forest classifiers available in GEE.

  11. The EO-1 hyperion and advanced land imager sensors for use in tundra classification studies within the Upper Kuparuk River Basin, Alaska (United States)

    Hall-Brown, Mary

    The heterogeneity of Arctic vegetation can make land cover classification vey difficult when using medium to small resolution imagery (Schneider et al., 2009; Muller et al., 1999). Using high radiometric and spatial resolution imagery, such as the SPOT 5 and IKONOS satellites, have helped arctic land cover classification accuracies rise into the 80 and 90 percentiles (Allard, 2003; Stine et al., 2010; Muller et al., 1999). However, those increases usually come at a high price. High resolution imagery is very expensive and can often add tens of thousands of dollars onto the cost of the research. The EO-1 satellite launched in 2002 carries two sensors that have high specral and/or high spatial resolutions and can be an acceptable compromise between the resolution versus cost issues. The Hyperion is a hyperspectral sensor with the capability of collecting 242 spectral bands of information. The Advanced Land Imager (ALI) is an advanced multispectral sensor whose spatial resolution can be sharpened to 10 meters. This dissertation compares the accuracies of arctic land cover classifications produced by the Hyperion and ALI sensors to the classification accuracies produced by the Systeme Pour l' Observation de le Terre (SPOT), the Landsat Thematic Mapper (TM) and the Landsat Enhanced Thematic Mapper Plus (ETM+) sensors. Hyperion and ALI images from August 2004 were collected over the Upper Kuparuk River Basin, Alaska. Image processing included the stepwise discriminant analysis of pixels that were positively classified from coinciding ground control points, geometric and radiometric correction, and principle component analysis. Finally, stratified random sampling was used to perform accuracy assessments on satellite derived land cover classifications. Accuracy was estimated from an error matrix (confusion matrix) that provided the overall, producer's and user's accuracies. This research found that while the Hyperion sensor produced classfication accuracies that were

  12. Enhancement of Satellite Image Compression Using a Hybrid (DWT-DCT) Algorithm (United States)

    Shihab, Halah Saadoon; Shafie, Suhaidi; Ramli, Abdul Rahman; Ahmad, Fauzan


    Discrete Cosine Transform (DCT) and Discrete Wavelet Transform (DWT) image compression techniques have been utilized in most of the earth observation satellites launched during the last few decades. However, these techniques have some issues that should be addressed. The DWT method has proven to be more efficient than DCT for several reasons. Nevertheless, the DCT can be exploited to improve the high-resolution satellite image compression when combined with the DWT technique. Hence, a proposed hybrid (DWT-DCT) method was developed and implemented in the current work, simulating an image compression system on-board on a small remote sensing satellite, with the aim of achieving a higher compression ratio to decrease the onboard data storage and the downlink bandwidth, while avoiding further complex levels of DWT. This method also succeeded in maintaining the reconstructed satellite image quality through replacing the standard forward DWT thresholding and quantization processes with an alternative process that employed the zero-padding technique, which also helped to reduce the processing time of DWT compression. The DCT, DWT and the proposed hybrid methods were implemented individually, for comparison, on three LANDSAT 8 images, using the MATLAB software package. A comparison was also made between the proposed method and three other previously published hybrid methods. The evaluation of all the objective and subjective results indicated the feasibility of using the proposed hybrid (DWT-DCT) method to enhance the image compression process on-board satellites.

  13. Detecting aircrafts from satellite images using saliency and conical ...

    Indian Academy of Sciences (India)

    Parts from the salient regions are further processed using clustering and morphological processing to get the probable regions of isolated aircraft targets. Finally, a novel conical pyramid based framework for template representation of the target samples is proposed for matching. Experimental results shown on a few satellite ...

  14. Remote Sensing Place : Satellite Images as Visual Spatial Imaginaries

    NARCIS (Netherlands)

    Shim, David

    How do people come to know the world? How do they get a sense of place and space? Arguably, one of the ways in which they do this is through the practice of remote sensing, among which satellite imagery is one of the most widespread and potent tools of engaging, representing and constructing space.

  15. Wildfire monitoring using satellite images, ontologies and linked geospatial data

    NARCIS (Netherlands)

    K. Kyzirakos (Konstantinos); M. Karpathiotakis (Manos); G. Garbis (George); C. Nikolaou (Charalampos); K. Bereta (Konstantina); I. Papoutsis (Ioannis); T. Herekakis (Themistocles); D. Michail (Dimitrios); M. Koubarakis (Manolis); C. Kontoes (Charalampos)


    htmlabstractAdvances in remote sensing technologies have allowed us to send an ever-increasing number of satellites in orbit around Earth. As a result, Earth Observation data archives have been constantly increasing in size in the last few years, and have become a valuable source of data for many

  16. Remote sensing place : Satellite images as visual spatial imaginaries

    NARCIS (Netherlands)

    Shim, David

    How do people come to know the world? How do they get a sense of place and space? Arguably, one of the ways in which they do this is through the practice of remote sensing, among which satellite imagery is one of the most widespread and potent tools of engaging, representing and constructing space.

  17. Relative Orientation and Modified Piecewise Epipolar Resampling for High Resolution Satellite Images (United States)

    Gong, K.; Fritsch, D.


    High resolution, optical satellite sensors are boosted to a new era in the last few years, because satellite stereo images at half meter or even 30cm resolution are available. Nowadays, high resolution satellite image data have been commonly used for Digital Surface Model (DSM) generation and 3D reconstruction. It is common that the Rational Polynomial Coefficients (RPCs) provided by the vendors have rough precision and there is no ground control information available to refine the RPCs. Therefore, we present two relative orientation methods by using corresponding image points only: the first method will use quasi ground control information, which is generated from the corresponding points and rough RPCs, for the bias-compensation model; the second method will estimate the relative pointing errors on the matching image and remove this error by an affine model. Both methods do not need ground control information and are applied for the entire image. To get very dense point clouds, the Semi-Global Matching (SGM) method is an efficient tool. However, before accomplishing the matching process the epipolar constraints are required. In most conditions, satellite images have very large dimensions, contrary to the epipolar geometry generation and image resampling, which is usually carried out in small tiles. This paper also presents a modified piecewise epipolar resampling method for the entire image without tiling. The quality of the proposed relative orientation and epipolar resampling method are evaluated, and finally sub-pixel accuracy has been achieved in our work.

  18. Classification of large-scale fundus image data sets: a cloud-computing framework. (United States)

    Roychowdhury, Sohini


    Large medical image data sets with high dimensionality require substantial amount of computation time for data creation and data processing. This paper presents a novel generalized method that finds optimal image-based feature sets that reduce computational time complexity while maximizing overall classification accuracy for detection of diabetic retinopathy (DR). First, region-based and pixel-based features are extracted from fundus images for classification of DR lesions and vessel-like structures. Next, feature ranking strategies are used to distinguish the optimal classification feature sets. DR lesion and vessel classification accuracies are computed using the boosted decision tree and decision forest classifiers in the Microsoft Azure Machine Learning Studio platform, respectively. For images from the DIARETDB1 data set, 40 of its highest-ranked features are used to classify four DR lesion types with an average classification accuracy of 90.1% in 792 seconds. Also, for classification of red lesion regions and hemorrhages from microaneurysms, accuracies of 85% and 72% are observed, respectively. For images from STARE data set, 40 high-ranked features can classify minor blood vessels with an accuracy of 83.5% in 326 seconds. Such cloud-based fundus image analysis systems can significantly enhance the borderline classification performances in automated screening systems.

  19. A Spectral-Texture Kernel-Based Classification Method for Hyperspectral Images

    Directory of Open Access Journals (Sweden)

    Yi Wang


    Full Text Available Classification of hyperspectral images always suffers from high dimensionality and very limited labeled samples. Recently, the spectral-spatial classification has attracted considerable attention and can achieve higher classification accuracy and smoother classification maps. In this paper, a novel spectral-spatial classification method for hyperspectral images by using kernel methods is investigated. For a given hyperspectral image, the principle component analysis (PCA transform is first performed. Then, the first principle component of the input image is segmented into non-overlapping homogeneous regions by using the entropy rate superpixel (ERS algorithm. Next, the local spectral histogram model is applied to each homogeneous region to obtain the corresponding texture features. Because this step is performed within each homogenous region, instead of within a fixed-size image window, the obtained local texture features in the image are more accurate, which can effectively benefit the improvement of classification accuracy. In the following step, a contextual spectral-texture kernel is constructed by combining spectral information in the image and the extracted texture information using the linearity property of the kernel methods. Finally, the classification map is achieved by the support vector machines (SVM classifier using the proposed spectral-texture kernel. Experiments on two benchmark airborne hyperspectral datasets demonstrate that our method can effectively improve classification accuracies, even though only a very limited training sample is available. Specifically, our method can achieve from 8.26% to 15.1% higher in terms of overall accuracy than the traditional SVM classifier. The performance of our method was further compared to several state-of-the-art classification methods of hyperspectral images using objective quantitative measures and a visual qualitative evaluation.

  20. Testing the performances of different image representations for mass classification in digital mammograms


    Angelini, Enrico; Campanini, Renato; Iampieri, Emiro; Lanconelli, Nico; Masotti, Matteo; Roffilli, Matteo


    The classification of tumoral masses and normal breast tissue is targeted. A mass detection algorithm which does not refer explicitly to shape, border, size, contrast or texture of mammographic suspicious regions is evaluated. In the present approach, classification features are embodied by the image representation used to encode suspicious regions. Classification is performed by means of a support vector machine (SVM) classifier. To investigate whether improvements can be achieved with respe...

  1. Extraction of Wavelet Based Features for Classification of T2-Weighted MRI Brain Images


    Ms. Yogita K.Dubey; Mushrif, Milind M.


    Extraction of discriminate features is very important task in classification algorithms. This paper presents technique for extraction cosine modulated feature for classification of the T2-weighted MRI images of human brain. Better discrimination and low design implementation complexity of the cosine-modulated wavelets has been effectively utilized to give better features and more accurate classification results. The proposed technique consists of two stages, namely, feature extraction, ...

  2. A novel multi-manifold classification model via path-based clustering for image retrieval (United States)

    Zhu, Rong; Yuan, Zhijun; Xuan, Junying


    Nowadays, with digital cameras and mass storage devices becoming increasingly affordable, each day thousands of pictures are taken and images on the Internet are emerged at an astonishing rate. Image retrieval is a process of searching valuable information that user demanded from huge images. However, it is hard to find satisfied results due to the well known "semantic gap". Image classification plays an essential role in retrieval process. But traditional methods will encounter problems when dealing with high-dimensional and large-scale image sets in applications. Here, we propose a novel multi-manifold classification model for image retrieval. Firstly, we simplify the classification of images from high-dimensional space into the one on low-dimensional manifolds, largely reducing the complexity of classification process. Secondly, considering that traditional distance measures often fail to find correct visual semantics of manifolds, especially when dealing with the images having complex data distribution, we also define two new distance measures based on path-based clustering, and further applied to the construction of a multi-class image manifold. One experiment was conducted on 2890 Web images. The comparison results between three methods show that the proposed method achieves the highest classification accuracy.

  3. Classification (United States)

    Clary, Renee; Wandersee, James


    In this article, Renee Clary and James Wandersee describe the beginnings of "Classification," which lies at the very heart of science and depends upon pattern recognition. Clary and Wandersee approach patterns by first telling the story of the "Linnaean classification system," introduced by Carl Linnacus (1707-1778), who is…

  4. Improved land use classification from Landsat and Seasat satellite imagery registered to a common map base (United States)

    Clark, J.


    In the case of Landsat Multispectral Scanner System (MSS) data, ambiguities in spectral signature can arise in urban areas. A study was initiated in the belief that Seasat digital SAR could help provide the spectral separability needed for a more accurate urban land use classification. A description is presented of the results of land use classifications performed on Landsat and preprocessed Seasat imagery that were registered to a common map base. The process of registering imagery and training site boundary coordinates to a common map has been reported by Clark (1980). It is found that preprocessed Seasat imagery provides signatures for urban land uses which are spectrally separable from Landsat signatures. This development appears to significantly improve land use classifications in an urban setting for class 12 (Commercial and Services), class 13 (Industrial), and class 14 (Transportation, Communications, and Utilities).

  5. Monitoring urban growth by using segmentation-classification of multispectral Landsat images in Izmit, Turkey. (United States)

    Yildiz, Selin; Doker, Mehmet Fatih


    Assessing the spatial land use and land cover (LULC) information is essential for decision making and management of landscapes. In fact, LULC information has been changed dramatically in fast-growing cities. This results in wrong land use problems due to unplanned and uncontrolled urbanization. The planning and evaluating of limited natural resources under the pressure of a growing population can be possible when a precise land use management plan is established. Therefore, it is imperative to monitor continuous LULC changes for future planning. Remote sensing (RS) technique is used for determining changes in LULC in urban areas. In this study, we have focused on Izmit, which is one of a growing number of metropolitan cities where the impact of the spatial growing period on LULC has been assessed over the past 30 years by using RS data. We have utilized the segmentation process and supervised classification of Landsat satellite images for four different dates (1985, 1995, 2005, and 2015). The outcome of this research can be summarized by significant changes in the shares of urban areas and farmland LULC classes. The overall observed increase in urban area class is up to 2177 ha between 1985 and 2015 period and this dramatic change has resulted in the decline of 1211 ha of farmland. Another conclusion is that the new residential areas have been created to the north, south and east of Izmit during this period.

  6. Incorporating uncertanity into Markov random field classification with the combine use of optical and SAR images and aduptive fuzzy mean vector (United States)

    Welikanna, D. R.; Tamura, M.; Susaki, J.


    A Markov Random Field (MRF) model accounting for the classification uncertainty using multisource satellite images and an adaptive fuzzy class mean vector is proposed in this study. The work also highlights the initialization of the class values for an MRF based classification for synthetic aperture radar (SAR) images using optical data. The model uses the contextual information from the optical image pixels and the SAR pixel intensity with corresponding fuzzy grade of memberships respectively, in the classification mechanism. Sub pixel class fractions estimated using Singular Value Decomposition (SVD) from the optical image initializes the class arrangement for the MRF process. Pair-site interactions of the pixels are used to model the prior energy from the initial class arrangement. Fuzzy class mean vector from the SAR intensity pixels is calculated using Fuzzy C-means (FCM) partitioning. Conditional probability for each class was determined by a Gamma distribution for the SAR image. Simulated annealing (SA) to minimize the global energy was executed using a logarithmic and power-law combined annealing schedule. Proposed technique was tested using an Advanced Land Observation Satellite (ALOS) phased array type L-band SAR (PALSAR) and Advanced Visible and Near-Infrared Radiometer-2 (AVNIR-2) data set over a disaster effected urban region in Japan. Proposed method and the conventional MRF results were evaluated with neural network (NN) and support vector machine (SVM) based classifications. The results suggest the possible integration of an adaptive fuzzy class mean vector and multisource data is promising for imprecise class discrimination using a MRF based classification.

  7. Satellite remote sensing of isolated wetlands using object-oriented classification of LANDSAT-7 data (United States)

    There has been an increasing interest in characterizing and mapping isolated depressional wetlands due to a 2001 U.S. Supreme Court decision that effectively removed their protected status. Our objective was to determine the utility of satellite remote sensing to accurately map ...

  8. Cupping artifact correction and automated classification for high-resolution dedicated breast CT images (United States)

    Yang, Xiaofeng; Wu, Shengyong; Sechopoulos, Ioannis; Fei, Baowei


    Purpose: To develop and test an automated algorithm to classify the different tissues present in dedicated breast CT images. Methods: The original CT images are first corrected to overcome cupping artifacts, and then a multiscale bilateral filter is used to reduce noise while keeping edge information on the images. As skin and glandular tissues have similar CT values on breast CT images, morphologic processing is used to identify the skin mask based on its position information. A modified fuzzy C-means (FCM) classification method is then used to classify breast tissue as fat and glandular tissue. By combining the results of the skin mask with the FCM, the breast tissue is classified as skin, fat, and glandular tissue. To evaluate the authors’ classification method, the authors use Dice overlap ratios to compare the results of the automated classification to those obtained by manual segmentation on eight patient images. Results: The correction method was able to correct the cupping artifacts and improve the quality of the breast CT images. For glandular tissue, the overlap ratios between the authors’ automatic classification and manual segmentation were 91.6% ± 2.0%. Conclusions: A cupping artifact correction method and an automatic classification method were applied and evaluated for high-resolution dedicated breast CT images. Breast tissue classification can provide quantitative measurements regarding breast composition, density, and tissue distribution. PMID:23039675

  9. Nightfire method to track volcanic eruptions from multispectral satellite images (United States)

    Trifonov, Grigory; Zhizhin, Mikhail; Melnikov, Dmitry


    This work presents the first results of an application of the Nightfire hotspot algorithm towards volcano activity detection. Nightfire algorithm have been developed to play along with a Suomi-NPP polar satellite launched in 2011, which has a new generation multispectral VIIRS thermal sensor on board, to detect gas flares related to the upstream and downstream production of oil and natural gas. Simultaneously using of nighttime data in SWIR, MWIR, and LWIR sensor bands the algorithm is able to estimate the hotspot temperature, size and radiant heat. Four years of non-filtered observations have been accumulated in a spatio-temporal detection database, which currently totals 125 GB in size. The first part of this work presents results of retrospective cross-match of the detection database with the publicly available observed eruptions databases. The second part discusses how an approximate 3D shape of a lava lake could be modeled based on the apparent source size and satellite zenith angle. The third part presents the results of fusion Landsat-8 and Himawari-8 satellites data with the VIIRS Nightfire for several active volcanoes.

  10. Hyperspectral Image Classification Based on the Combination of Spatial-spectral Feature and Sparse Representation

    Directory of Open Access Journals (Sweden)

    YANG Zhaoxia


    Full Text Available In order to avoid the problem of being over-dependent on high-dimensional spectral feature in the traditional hyperspectral image classification, a novel approach based on the combination of spatial-spectral feature and sparse representation is proposed in this paper. Firstly, we extract the spatial-spectral feature by reorganizing the local image patch with the first d principal components(PCs into a vector representation, followed by a sorting scheme to make the vector invariant to local image rotation. Secondly, we learn the dictionary through a supervised method, and use it to code the features from test samples afterwards. Finally, we embed the resulting sparse feature coding into the support vector machine(SVM for hyperspectral image classification. Experiments using three hyperspectral data show that the proposed method can effectively improve the classification accuracy comparing with traditional classification methods.

  11. Classification

    DEFF Research Database (Denmark)

    Hjørland, Birger


    This article presents and discusses definitions of the term “classification” and the related concepts “Concept/conceptualization,”“categorization,” “ordering,” “taxonomy” and “typology.” It further presents and discusses theories of classification including the influences of Aristotle...... and Wittgenstein. It presents different views on forming classes, including logical division, numerical taxonomy, historical classification, hermeneutical and pragmatic/critical views. Finally, issues related to artificial versus natural classification and taxonomic monism versus taxonomic pluralism are briefly...

  12. Development Of Polarimetric Decomposition Techniques For Indian Forest Resource Assessment Using Radar Imaging Satellite (Risat-1) Images (United States)

    Sridhar, J.


    The focus of this work is to examine polarimetric decomposition techniques primarily focussed on Pauli decomposition and Sphere Di-Plane Helix (SDH) decomposition for forest resource assessment. The data processing methods adopted are Pre-processing (Geometric correction and Radiometric calibration), Speckle Reduction, Image Decomposition and Image Classification. Initially to classify forest regions, unsupervised classification was applied to determine different unknown classes. It was observed K-means clustering method gave better results in comparison with ISO Data method.Using the algorithm developed for Radar Tools, the code for decomposition and classification techniques were applied in Interactive Data Language (IDL) and was applied to RISAT-1 image of Mysore-Mandya region of Karnataka, India. This region is chosen for studying forest vegetation and consists of agricultural lands, water and hilly regions. Polarimetric SAR data possess a high potential for classification of earth surface.After applying the decomposition techniques, classification was done by selecting region of interests andpost-classification the over-all accuracy was observed to be higher in the SDH decomposed image, as it operates on individual pixels on a coherent basis and utilises the complete intrinsic coherent nature of polarimetric SAR data. Thereby, making SDH decomposition particularly suited for analysis of high-resolution SAR data. The Pauli Decomposition represents all the polarimetric information in a single SAR image however interpretation of the resulting image is difficult. The SDH decomposition technique seems to produce better results and interpretation as compared to Pauli Decomposition however more quantification and further analysis are being done in this area of research. The comparison of Polarimetric decomposition techniques and evolutionary classification techniques will be the scope of this work.

  13. Representation learning with deep extreme learning machines for efficient image set classification

    KAUST Repository

    Uzair, Muhammad


    Efficient and accurate representation of a collection of images, that belong to the same class, is a major research challenge for practical image set classification. Existing methods either make prior assumptions about the data structure, or perform heavy computations to learn structure from the data itself. In this paper, we propose an efficient image set representation that does not make any prior assumptions about the structure of the underlying data. We learn the nonlinear structure of image sets with deep extreme learning machines that are very efficient and generalize well even on a limited number of training samples. Extensive experiments on a broad range of public datasets for image set classification show that the proposed algorithm consistently outperforms state-of-the-art image set classification methods both in terms of speed and accuracy.

  14. An SVM-based distal lung image classification using texture descriptors. (United States)

    Désir, Chesner; Petitjean, Caroline; Heutte, Laurent; Thiberville, Luc; Salaün, Mathieu


    A novel imaging technique can now provide microscopic images of the distal lung in vivo, for which quantitative analysis tools need to be developed. In this paper, we present an image classification system that is able to discriminate between normal and pathological images. Different feature spaces for discrimination are investigated and evaluated using a support vector machine. Best classification rates reach up to 90% and 95% on non-smoker and smoker groups, respectively. A feature selection process is also implemented, that allows us to gain some insight about these images. Whereas further tests on extended databases are needed, these first results indicate that efficient computer based automated classification of normal vs. pathological images of the distal lung is feasible. Copyright © 2011 Elsevier Ltd. All rights reserved.

  15. A fuzzy system approach for the classification of underwater AUV color images (United States)

    Díaz, José A.; Torres, Raúl E.


    This paper presents a fuzzy system approach using texture and color to classify living coral cover in underwater color images acquired by an autonomous underwater vehicle (AUV). The proposed fuzzy system for classification consists in the assigning of fuzzy memberships to different image features such as the mean, the spatial variance, the Gabor filter response standard deviation, and the wavelet energy. These fuzzy sensors are applied to the different segments present in the images. The segmentation of the images is previously done using the Homogeneity Coefficient Segmentation Algorithm (LHC). The resulted classification of the regions is compared against ground truth maps of the images. A correct classification over 80% was achieved in two different 25 images sets of two different areas.

  16. Exploration of mineral resource deposits based on analysis of aerial and satellite image data employing artificial intelligence methods (United States)

    Osipov, Gennady


    We propose a solution to the problem of exploration of various mineral resource deposits, determination of their forms / classification of types (oil, gas, minerals, gold, etc.) with the help of satellite photography of the region of interest. Images received from satellite are processed and analyzed to reveal the presence of specific signs of deposits of various minerals. Course of data processing and making forecast can be divided into some stages: Pre-processing of images. Normalization of color and luminosity characteristics, determination of the necessary contrast level and integration of a great number of separate photos into a single map of the region are performed. Construction of semantic map image. Recognition of bitmapped image and allocation of objects and primitives known to system are realized. Intelligent analysis. At this stage acquired information is analyzed with the help of a knowledge base, which contain so-called "attention landscapes" of experts. Used methods of recognition and identification of images: a) combined method of image recognition, b)semantic analysis of posterized images, c) reconstruction of three-dimensional objects from bitmapped images, d)cognitive technology of processing and interpretation of images. This stage is fundamentally new and it distinguishes suggested technology from all others. Automatic registration of allocation of experts` attention - registration of so-called "attention landscape" of experts - is the base of the technology. Landscapes of attention are, essentially, highly effective filters that cut off unnecessary information and emphasize exactly the factors used by an expert for making a decision. The technology based on denoted principles involves the next stages, which are implemented in corresponding program agents. Training mode -> Creation of base of ophthalmologic images (OI) -> Processing and making generalized OI (GOI) -> Mode of recognition and interpretation of unknown images. Training mode

  17. Application of the Coastal and Marine Ecological Classification Standard (CMECS) Water Column Component (WC) to data derived by the Naval Research Lab (NRL) Automated Processing System (APS) modeling of Moderate Resolution Imaging Spectroradiometer (MODIS) Imagery from the Aqua Earth Orbiting Satellite (EOS) PM in the Northern Gulf of Mexico from 2005-01 to 2009-12 (NODC Accession 0094007) (United States)

    National Oceanic and Atmospheric Administration, Department of Commerce — Satellite-derived data for sea surface temperature, salinity, chlorophyll; euphotic depth; and modeled bottom to surface temperature differences were evaluated to...

  18. Satellite image resolution enhancement using discrete wavelet transform and new edge-directed interpolation (United States)

    Witwit, Wasnaa; Zhao, Yifan; Jenkins, Karl; Zhao, Yitian


    An image resolution enhancement approach based on discrete wavelet transform (DWT) and new edge-directed interpolation (NEDI) for degraded satellite images by geometric distortion to correct the errors in image geometry and recover the edge details of directional high-frequency subbands is proposed. The observed image is decomposed into four frequency subbands through DWT, and then the three high-frequency subbands and the observed image are processed with NEDI. To better preserve the edges and remove potential noise in the estimated high-frequency subbands, an adaptive threshold is applied to process the estimated wavelet coefficients. Finally, the enhanced image is reconstructed by applying inverse DWT. Four criteria are introduced, aiming to better assess the overall performance of the proposed approach for different types of satellite images. A public satellite images data set is selected for the validation purpose. The visual and quantitative results show the superiority of the proposed approach over the conventional and state-of-the-art image resolution enhancement techniques.

  19. A line rate calculation method for arbitrary directional imaging of an Earth observing satellite (United States)

    Jeon, Moon-Jin; Kim, Eunghyun; Lim, Seong-Bin; Choi, Seok-Weon


    For an earth observing satellite, a line rate is the number of lines which the CCD of push broom type camera scans in a second. It can be easily calculated by ground velocity divided by ground sample distance. Accurate calculation of line rate is necessary to obtain high quality image using TDI CCD. The earth observing satellite has four types of imaging missions which are strip imaging, stereo imaging, multi-point imaging, and arbitrary directional imaging. For the first three types of imaging, ground scanning direction is aligned with satellite velocity direction. Therefore, if the orbit propagation and spacecraft attitude information are available, the ground velocity and ground sample distance could be easily calculated. However, the calculation method might not be applicable to the arbitrary directional imaging. In the arbitrary directional imaging mode, the ground velocity is not fixed value which could be directly derived by orbit information. Furthermore, the ground sample distance might not be easily calculated by simple trigonometry which is possible for the other types of imaging. In this paper, we proposed a line rate calculation method for the arbitrary directional imaging. We applied spherical geometry to derive the equation of ground point which is the intersection between the line of sight vector of the camera and earth surface. The derivative of this equation for time is the ground velocity except the factor of earth rotation. By adding this equation and earth rotation factor, the true ground velocity vector could be derived. For the ground sample distance, we applied the equation of circle and ellipse for yaw angle difference. The equation of circle is used for the yaw angle representation on the plane which is orthogonal to the line of sight vector. The equation of ellipse is used for the yaw angle representation on the ground surface. We applied the proposed method to the KOMPSAT-3A (Korea Multi-Purpose Satellite 3A) mission which is the first

  20. Classification of MR brain images by combination of multi-CNNs for AD diagnosis (United States)

    Cheng, Danni; Liu, Manhua; Fu, Jianliang; Wang, Yaping


    Alzheimer's disease (AD) is an irreversible neurodegenerative disorder with progressive impairment of memory and cognitive functions. Its early diagnosis is crucial for development of future treatment. Magnetic resonance images (MRI) play important role to help understand the brain anatomical changes related to AD. Conventional methods extract the hand-crafted features such as gray matter volumes and cortical thickness and train a classifier to distinguish AD from other groups. Different from these methods, this paper proposes to construct multiple deep 3D convolutional neural networks (3D-CNNs) to learn the various features from local brain images which are combined to make the final classification for AD diagnosis. First, a number of local image patches are extracted from the whole brain image and a 3D-CNN is built upon each local patch to transform the local image into more compact high-level features. Then, the upper convolution and fully connected layers are fine-tuned to combine the multiple 3D-CNNs for image classification. The proposed method can automatically learn the generic features from imaging data for classification. Our method is evaluated using T1-weighted structural MR brain images on 428 subjects including 199 AD patients and 229 normal controls (NC) from Alzheimer's Disease Neuroimaging Initiative (ADNI) database. Experimental results show that the proposed method achieves an accuracy of 87.15% and an AUC (area under the ROC curve) of 92.26% for AD classification, demonstrating the promising classification performances.

  1. Mission planning optimization of video satellite for ground multi-object staring imaging (United States)

    Cui, Kaikai; Xiang, Junhua; Zhang, Yulin


    This study investigates the emergency scheduling problem of ground multi-object staring imaging for a single video satellite. In the proposed mission scenario, the ground objects require a specified duration of staring imaging by the video satellite. The planning horizon is not long, i.e., it is usually shorter than one orbit period. A binary decision variable and the imaging order are used as the design variables, and the total observation revenue combined with the influence of the total attitude maneuvering time is regarded as the optimization objective. Based on the constraints of the observation time windows, satellite attitude adjustment time, and satellite maneuverability, a constraint satisfaction mission planning model is established for ground object staring imaging by a single video satellite. Further, a modified ant colony optimization algorithm with tabu lists (Tabu-ACO) is designed to solve this problem. The proposed algorithm can fully exploit the intelligence and local search ability of ACO. Based on full consideration of the mission characteristics, the design of the tabu lists can reduce the search range of ACO and improve the algorithm efficiency significantly. The simulation results show that the proposed algorithm outperforms the conventional algorithm in terms of optimization performance, and it can obtain satisfactory scheduling results for the mission planning problem.

  2. Classification of Clouds and Deep Convection from GEOS-5 Using Satellite Observations (United States)

    Putman, William; Suarez, Max


    With the increased resolution of global atmospheric models and the push toward global cloud resolving models, the resemblance of model output to satellite observations has become strikingly similar. As we progress with our adaptation of the Goddard Earth Observing System Model, Version 5 (GEOS-5) as a high resolution cloud system resolving model, evaluation of cloud properties and deep convection require in-depth analysis beyond a visual comparison. Outgoing long-wave radiation (OLR) provides a sufficient comparison with infrared (IR) satellite imagery to isolate areas of deep convection. We have adopted a binning technique to generate a series of histograms for OLR which classify the presence and fraction of clear sky versus deep convection in the tropics that can be compared with a similar analyses of IR imagery from composite Geostationary Operational Environmental Satellite (GOES) observations. We will present initial results that have been used to evaluate the amount of deep convective parameterization required within the model as we move toward cloud system resolving resolutions of 10- to 1-km globally.

  3. Median Filter Noise Reduction of Image and Backpropagation Neural Network Model for Cervical Cancer Classification (United States)

    Wutsqa, D. U.; Marwah, M.


    In this paper, we consider spatial operation median filter to reduce the noise in the cervical images yielded by colposcopy tool. The backpropagation neural network (BPNN) model is applied to the colposcopy images to classify cervical cancer. The classification process requires an image extraction by using a gray level co-occurrence matrix (GLCM) method to obtain image features that are used as inputs of BPNN model. The advantage of noise reduction is evaluated by comparing the performances of BPNN models with and without spatial operation median filter. The experimental result shows that the spatial operation median filter can improve the accuracy of the BPNN model for cervical cancer classification.

  4. Research on adaptive segmentation and activity classification method of filamentous fungi image in microbe fermentation (United States)

    Cai, Xiaochun; Hu, Yihua; Wang, Peng; Sun, Dujuan; Hu, Guilan


    The paper presents an adaptive segmentation and activity classification method for filamentous fungi image. Firstly, an adaptive structuring element (SE) construction algorithm is proposed for image background suppression. Based on watershed transform method, the color labeled segmentation of fungi image is taken. Secondly, the fungi elements feature space is described and the feature set for fungi hyphae activity classification is extracted. The growth rate evaluation of fungi hyphae is achieved by using SVM classifier. Some experimental results demonstrate that the proposed method is effective for filamentous fungi image processing.

  5. Object based image analysis for the classification of the growth stages of Avocado crop, in Michoacán State, Mexico (United States)

    Gao, Yan; Marpu, Prashanth; Morales Manila, Luis M.


    This paper assesses the suitability of 8-band Worldview-2 (WV2) satellite data and object-based random forest algorithm for the classification of avocado growth stages in Mexico. We tested both pixel-based with minimum distance (MD) and maximum likelihood (MLC) and object-based with Random Forest (RF) algorithm for this task. Training samples and verification data were selected by visual interpreting the WV2 images for seven thematic classes: fully grown, middle stage, and early stage of avocado crops, bare land, two types of natural forests, and water body. To examine the contribution of the four new spectral bands of WV2 sensor, all the tested classifications were carried out with and without the four new spectral bands. Classification accuracy assessment results show that object-based classification with RF algorithm obtained higher overall higher accuracy (93.06%) than pixel-based MD (69.37%) and MLC (64.03%) method. For both pixel-based and object-based methods, the classifications with the four new spectral bands (overall accuracy obtained higher accuracy than those without: overall accuracy of object-based RF classification with vs without: 93.06% vs 83.59%, pixel-based MD: 69.37% vs 67.2%, pixel-based MLC: 64.03% vs 36.05%, suggesting that the four new spectral bands in WV2 sensor contributed to the increase of the classification accuracy.

  6. Image search engine with selective filtering and feature-element-based classification (United States)

    Li, Qing; Zhang, Yujin; Dai, Shengyang


    With the growth of Internet and storage capability in recent years, image has become a widespread information format in World Wide Web. However, it has become increasingly harder to search for images of interest, and effective image search engine for the WWW needs to be developed. We propose in this paper a selective filtering process and a novel approach for image classification based on feature element in the image search engine we developed for the WWW. First a selective filtering process is embedded in a general web crawler to filter out the meaningless images with GIF format. Two parameters that can be obtained easily are used in the filtering process. Our classification approach first extract feature elements from images instead of feature vectors. Compared with feature vectors, feature elements can better capture visual meanings of the image according to subjective perception of human beings. Different from traditional image classification method, our classification approach based on feature element doesn't calculate the distance between two vectors in the feature space, while trying to find associations between feature element and class attribute of the image. Experiments are presented to show the efficiency of the proposed approach.

  7. An attitude algorithm based on the band seamless splicing imaging for agile satellite (United States)

    Wang, Ya-min; Xu, Wei; Jin, Guang; Yang, Xiu-bin; Zhang, Zhao


    In order to realize fast maneuvering imaging of the target area with high resolution agile satellite, a new attitude matching algorithm is developed. A strict mosaic imaging model of ray trace and the velocity vector mapping are built according to the strip mosaic imaging principle and the relationship between imaging target and the camera focal plane. The three-axis attitude is deduced based on the principle of optimal tracking of the maneuvering path. Finally, the geometric scaling simulation is carried out through the time delayed and integration (TDI) charge coupled device (CCD) prototype system, satellite attitude control physical simulation platform and the LED earth target simulator. The experimental results show that the algorithm could realize the matching band seamless splicing imaging of the target very well, confirming the correctness of the algorithm.

  8. Classifications of Image Features: A Survey | Lichun | Discovery and ...

    African Journals Online (AJOL)

    An image feature is a descriptor of an image, which can avoid redundant data and reduce the effects of noise and variance. In computer imaging, feature selection is vital for researchers and processors. Feature extraction and image processing are based on the mathematical selection, computation and manipulation of ...

  9. Weighted Chebyshev distance classification method for hyperspectral imaging (United States)

    Demirci, S.; Erer, I.; Ersoy, O.


    The main objective of classification is to partition the surface materials into non-overlapping regions by using some decision rules. For supervised classification, the hyperspectral imagery (HSI) is compared with the reflectance spectra of the material containing similar spectral characteristic. As being a spectral similarity based classification method, prediction of different level of upper and lower spectral boundaries of all classes spectral signatures across spectral bands constitutes the basic principles of the Multi-Scale Vector Tunnel Algorithm (MS-VTA) classification algorithm. The vector tunnel (VT) scaling parameters obtained from means and standard deviations of the class references are used. In this study, MS-VT method is improved and a spectral similarity based technique referred to as Weighted Chebyshev Distance (WCD) method for the supervised classification of HSI is introduced. This is also shown to be equivalent to the use of the WCD in which the weights are chosen as an inverse power of the standard deviation per spectral band. The use of WCD measures in terms of the inverse power of standard deviations and optimization of power parameter constitute the most important side of the study. The algorithms are trained with the same kinds of training sets, and their performances are calculated for the power of the standard deviation. During these studies, various levels of the power parameters are evaluated based on the efficiency of the algorithms for choosing the best values of the weights.

  10. Legendrian satellites


    Etnyre, John; Vértesi, Vera


    In this paper we study Legendrian knots in the knot types of satellite knots. In particular, we classify Legendrian Whitehead patterns and learn a great deal about Legendrian braided patterns. We also show how the classification of Legendrian patterns can lead to a classification of the associated satellite knots if the companion knot is Legendrian simple and uniformly thick. This leads to new Legendrian and transverse classification results for knots in the 3-sphere with its standard contact...

  11. Modelling experimental image formation for likelihood-based classification of electron microscopy data (United States)

    Scheres, Sjors H. W.; Núñez-Ramírez, Rafael; Gómez-Llorente, Yacob; Martín, Carmen San; Eggermont, Paul P. B.; Carazo, José María


    The coexistence of multiple distinct structural states often obstructs the application of three-dimensional cryo-electron microscopy to large macromolecular complexes. Maximum likelihood approaches are emerging as robust tools for solving the image classification problems that are posed by such samples. Here, we propose a statistical data model that allows for a description of the experimental image formation within the formulation of 2D and 3D maximum likelihood refinement. The proposed approach comprises a formulation of the probability calculations in Fourier space, including a spatial frequency-dependent noise model and a description of defocus-dependent imaging effects. The Expectation-Maximization like algorithms presented are generally applicable to the alignment and classification of structurally heterogeneous projection data. Their effectiveness is demonstrated with various examples, including 2D classification of top views of the archaeal helicase MCM, and 3D classification of 70S E.coli ribosome and Simian Virus 40 large T-antigen projections. PMID:17937907

  12. A Locality-Constrained and Label Embedding Dictionary Learning Algorithm for Image Classification. (United States)

    Zhengming Li; Zhihui Lai; Yong Xu; Jian Yang; Zhang, David


    Locality and label information of training samples play an important role in image classification. However, previous dictionary learning algorithms do not take the locality and label information of atoms into account together in the learning process, and thus their performance is limited. In this paper, a discriminative dictionary learning algorithm, called the locality-constrained and label embedding dictionary learning (LCLE-DL) algorithm, was proposed for image classification. First, the locality information was preserved using the graph Laplacian matrix of the learned dictionary instead of the conventional one derived from the training samples. Then, the label embedding term was constructed using the label information of atoms instead of the classification error term, which contained discriminating information of the learned dictionary. The optimal coding coefficients derived by the locality-based and label-based reconstruction were effective for image classification. Experimental results demonstrated that the LCLE-DL algorithm can achieve better performance than some state-of-the-art algorithms.

  13. Tissue classification for laparoscopic image understanding based on multispectral texture analysis. (United States)

    Zhang, Yan; Wirkert, Sebastian J; Iszatt, Justin; Kenngott, Hannes; Wagner, Martin; Mayer, Benjamin; Stock, Christian; Clancy, Neil T; Elson, Daniel S; Maier-Hein, Lena


    Intraoperative tissue classification is one of the prerequisites for providing context-aware visualization in computer-assisted minimally invasive surgeries. As many anatomical structures are difficult to differentiate in conventional RGB medical images, we propose a classification method based on multispectral image patches. In a comprehensive ex vivo study through statistical analysis, we show that (1) multispectral imaging data are superior to RGB data for organ tissue classification when used in conjunction with widely applied feature descriptors and (2) combining the tissue texture with the reflectance spectrum improves the classification performance. The classifier reaches an accuracy of 98.4% on our dataset. Multispectral tissue analysis could thus evolve as a key enabling technique in computer-assisted laparoscopy.

  14. The Radon cumulative distribution transform and its application to image classification


    Kolouri, Soheil; Park, Se Rim; Rohde, Gustavo K.


    Invertible image representation methods (transforms) are routinely employed as low-level image processing operations based on which feature extraction and recognition algorithms are developed. Most transforms in current use (e.g. Fourier, Wavelet, etc.) are linear transforms, and, by themselves, are unable to substantially simplify the representation of image classes for classification. Here we describe a nonlinear, invertible, low-level image processing transform based on c...

  15. A Parallel Adaboost-Backpropagation Neural Network for Massive Image Dataset Classification (United States)

    Cao, Jianfang; Chen, Lichao; Wang, Min; Shi, Hao; Tian, Yun


    Image classification uses computers to simulate human understanding and cognition of images by automatically categorizing images. This study proposes a faster image classification approach that parallelizes the traditional Adaboost-Backpropagation (BP) neural network using the MapReduce parallel programming model. First, we construct a strong classifier by assembling the outputs of 15 BP neural networks (which are individually regarded as weak classifiers) based on the Adaboost algorithm. Second, we design Map and Reduce tasks for both the parallel Adaboost-BP neural network and the feature extraction algorithm. Finally, we establish an automated classification model by building a Hadoop cluster. We use the Pascal VOC2007 and Caltech256 datasets to train and test the classification model. The results are superior to those obtained using traditional Adaboost-BP neural network or parallel BP neural network approaches. Our approach increased the average classification accuracy rate by approximately 14.5% and 26.0% compared to the traditional Adaboost-BP neural network and parallel BP neural network, respectively. Furthermore, the proposed approach requires less computation time and scales very well as evaluated by speedup, sizeup and scaleup. The proposed approach may provide a foundation for automated large-scale image classification and demonstrates practical value.

  16. A Method of Spatial Mapping and Reclassification for High-Spatial-Resolution Remote Sensing Image Classification

    Directory of Open Access Journals (Sweden)

    Guizhou Wang


    Full Text Available This paper presents a new classification method for high-spatial-resolution remote sensing images based on a strategic mechanism of spatial mapping and reclassification. The proposed method includes four steps. First, the multispectral image is classified by a traditional pixel-based classification method (support vector machine. Second, the panchromatic image is subdivided by watershed segmentation. Third, the pixel-based multispectral image classification result is mapped to the panchromatic segmentation result based on a spatial mapping mechanism and the area dominant principle. During the mapping process, an area proportion threshold is set, and the regional property is defined as unclassified if the maximum area proportion does not surpass the threshold. Finally, unclassified regions are reclassified based on spectral information using the minimum distance to mean algorithm. Experimental results show that the classification method for high-spatial-resolution remote sensing images based on the spatial mapping mechanism and reclassification strategy can make use of both panchromatic and multispectral information, integrate the pixel- and object-based classification methods, and improve classification accuracy.

  17. Experimental comparison of support vector machines with random forests for hyperspectral image land cover classification (United States)

    Abe, B. T.; Olugbara, O. O.; Marwala, T.


    The performances of regular support vector machines and random forests are experimentally compared for hyperspectral imaging land cover classification. Special characteristics of hyperspectral imaging dataset present diverse processing problems to be resolved under robust mathematical formalisms such as image classification. As a result, pixel purity index algorithm is used to obtain endmember spectral responses from Indiana pine hyperspectral image dataset. The generalized reduced gradient optimization algorithm is thereafter executed on the research data to estimate fractional abundances in the hyperspectral image and thereby obtain the numeric values for land cover classification. The Waikato environment for knowledge analysis (WEKA) data mining framework is selected as a tool to carry out the classification process by using support vector machines and random forests classifiers. Results show that performance of support vector machines is comparable to that of random forests. This study makes a positive contribution to the problem of land cover classification by exploring generalized reduced gradient method, support vector machines, and random forests to improve producer accuracy and overall classification accuracy. The performance comparison of these classifiers is valuable for a decision maker to consider tradeoffs in method accuracy versus method complexity.

  18. Image Classification Using Biomimetic Pattern Recognition with Convolutional Neural Networks Features

    Directory of Open Access Journals (Sweden)

    Liangji Zhou


    Full Text Available As a typical deep-learning model, Convolutional Neural Networks (CNNs can be exploited to automatically extract features from images using the hierarchical structure inspired by mammalian visual system. For image classification tasks, traditional CNN models employ the softmax function for classification. However, owing to the limited capacity of the softmax function, there are some shortcomings of traditional CNN models in image classification. To deal with this problem, a new method combining Biomimetic Pattern Recognition (BPR with CNNs is proposed for image classification. BPR performs class recognition by a union of geometrical cover sets in a high-dimensional feature space and therefore can overcome some disadvantages of traditional pattern recognition. The proposed method is evaluated on three famous image classification benchmarks, that is, MNIST, AR, and CIFAR-10. The classification accuracies of the proposed method for the three datasets are 99.01%, 98.40%, and 87.11%, respectively, which are much higher in comparison with the other four methods in most cases.

  19. A Parallel Adaboost-Backpropagation Neural Network for Massive Image Dataset Classification (United States)

    Cao, Jianfang; Chen, Lichao; Wang, Min; Shi, Hao; Tian, Yun


    Image classification uses computers to simulate human understanding and cognition of images by automatically categorizing images. This study proposes a faster image classification approach that parallelizes the traditional Adaboost-Backpropagation (BP) neural network using the MapReduce parallel programming model. First, we construct a strong classifier by assembling the outputs of 15 BP neural networks (which are individually regarded as weak classifiers) based on the Adaboost algorithm. Second, we design Map and Reduce tasks for both the parallel Adaboost-BP neural network and the feature extraction algorithm. Finally, we establish an automated classification model by building a Hadoop cluster. We use the Pascal VOC2007 and Caltech256 datasets to train and test the classification model. The results are superior to those obtained using traditional Adaboost-BP neural network or parallel BP neural network approaches. Our approach increased the average classification accuracy rate by approximately 14.5% and 26.0% compared to the traditional Adaboost-BP neural network and parallel BP neural network, respectively. Furthermore, the proposed approach requires less computation time and scales very well as evaluated by speedup, sizeup and scaleup. The proposed approach may provide a foundation for automated large-scale image classification and demonstrates practical value. PMID:27905520

  20. A Method of Spatial Mapping and Reclassification for High-Spatial-Resolution Remote Sensing Image Classification (United States)

    Wang, Guizhou; Liu, Jianbo; He, Guojin


    This paper presents a new classification method for high-spatial-resolution remote sensing images based on a strategic mechanism of spatial mapping and reclassification. The proposed method includes four steps. First, the multispectral image is classified by a traditional pixel-based classification method (support vector machine). Second, the panchromatic image is subdivided by watershed segmentation. Third, the pixel-based multispectral image classification result is mapped to the panchromatic segmentation result based on a spatial mapping mechanism and the area dominant principle. During the mapping process, an area proportion threshold is set, and the regional property is defined as unclassified if the maximum area proportion does not surpass the threshold. Finally, unclassified regions are reclassified based on spectral information using the minimum distance to mean algorithm. Experimental results show that the classification method for high-spatial-resolution remote sensing images based on the spatial mapping mechanism and reclassification strategy can make use of both panchromatic and multispectral information, integrate the pixel- and object-based classification methods, and improve classification accuracy. PMID:24453808

  1. Image Classification Using Biomimetic Pattern Recognition with Convolutional Neural Networks Features (United States)

    Huo, Guanying


    As a typical deep-learning model, Convolutional Neural Networks (CNNs) can be exploited to automatically extract features from images using the hierarchical structure inspired by mammalian visual system. For image classification tasks, traditional CNN models employ the softmax function for classification. However, owing to the limited capacity of the softmax function, there are some shortcomings of traditional CNN models in image classification. To deal with this problem, a new method combining Biomimetic Pattern Recognition (BPR) with CNNs is proposed for image classification. BPR performs class recognition by a union of geometrical cover sets in a high-dimensional feature space and therefore can overcome some disadvantages of traditional pattern recognition. The proposed method is evaluated on three famous image classification benchmarks, that is, MNIST, AR, and CIFAR-10. The classification accuracies of the proposed method for the three datasets are 99.01%, 98.40%, and 87.11%, respectively, which are much higher in comparison with the other four methods in most cases. PMID:28316614

  2. Combining Global and Local Information for Knowledge-Assisted Image Analysis and Classification

    Directory of Open Access Journals (Sweden)

    Mezaris V


    Full Text Available A learning approach to knowledge-assisted image analysis and classification is proposed that combines global and local information with explicitly defined knowledge in the form of an ontology. The ontology specifies the domain of interest, its subdomains, the concepts related to each subdomain as well as contextual information. Support vector machines (SVMs are employed in order to provide image classification to the ontology subdomains based on global image descriptions. In parallel, a segmentation algorithm is applied to segment the image into regions and SVMs are again employed, this time for performing an initial mapping between region low-level visual features and the concepts in the ontology. Then, a decision function, that receives as input the computed region-concept associations together with contextual information in the form of concept frequency of appearance, realizes image classification based on local information. A fusion mechanism subsequently combines the intermediate classification results, provided by the local- and global-level information processing, to decide on the final image classification. Once the image subdomain is selected, final region-concept association is performed using again SVMs and a genetic algorithm (GA for optimizing the mapping between the image regions and the selected subdomain concepts taking into account contextual information in the form of spatial relations. Application of the proposed approach to images of the selected domain results in their classification (i.e., their assignment to one of the defined subdomains and the generation of a fine granularity semantic representation of them (i.e., a segmentation map with semantic concepts attached to each segment. Experiments with images from the personal collection domain, as well as comparative evaluation with other approaches of the literature, demonstrate the performance of the proposed approach.

  3. Super Resolution Reconstruction Based on Adaptive Detail Enhancement for ZY-3 Satellite Images (United States)

    Zhu, Hong; Song, Weidong; Tan, Hai; Wang, Jingxue; Jia, Di


    Super-resolution reconstruction of sequence remote sensing image is a technology which handles multiple low-resolution satellite remote sensing images with complementary information and obtains one or more high resolution images. The cores of the technology are high precision matching between images and high detail information extraction and fusion. In this paper puts forward a new image super resolution model frame which can adaptive multi-scale enhance the details of reconstructed image. First, the sequence images were decomposed into a detail layer containing the detail information and a smooth layer containing the large scale edge information by bilateral filter. Then, a texture detail enhancement function was constructed to promote the magnitude of the medium and small details. Next, the non-redundant information of the super reconstruction was obtained by differential processing of the detail layer, and the initial super resolution construction result was achieved by interpolating fusion of non-redundant information and the smooth layer. At last, the final reconstruction image was acquired by executing a local optimization model on the initial constructed image. Experiments on ZY-3 satellite images of same phase and different phase show that the proposed method can both improve the information entropy and the image details evaluation standard comparing with the interpolation method, traditional TV algorithm and MAP algorithm, which indicate that our method can obviously highlight image details and contains more ground texture information. A large number of experiment results reveal that the proposed method is robust and universal for different kinds of ZY-3 satellite images.

  4. Digital image processing for the earth resources technology satellite data. (United States)

    Will, P. M.; Bakis, R.; Wesley, M. A.


    This paper discusses the problems of digital processing of the large volumes of multispectral image data that are expected to be received from the ERTS program. Correction of geometric and radiometric distortions are discussed and a byte oriented implementation is proposed. CPU timing estimates are given for a System/360 Model 67, and show that a processing throughput of 1000 image sets per week is feasible.

  5. Effect of Satellite Formations and Imaging Modes on Global Albedo Estimation (United States)

    Nag, Sreeja; Gatebe, Charles K.; Miller, David W.; de Weck, Olivier L.


    We confirm the applicability of using small satellite formation flight for multi-angular earth observation to retrieve global, narrow band, narrow field-of-view albedo. The value of formation flight is assessed using a coupled systems engineering and science evaluation model, driven by Model Based Systems Engineering and Observing System Simulation Experiments. Albedo errors are calculated against bi-directional reflectance data obtained from NASA airborne campaigns made by the Cloud Absorption Radiometer for the seven major surface types, binned using MODIS' land cover map - water, forest, cropland, grassland, snow, desert and cities. A full tradespace of architectures with three to eight satellites, maintainable orbits and imaging modes (collective payload pointing strategies) are assessed. For an arbitrary 4-sat formation, changing the reference, nadir-pointing satellite dynamically reduces the average albedo error to 0.003, from 0.006 found in the static reference case. Tracking pre-selected waypoints with all the satellites reduces the average error further to 0.001, allows better polar imaging and continued operations even with a broken formation. An albedo error of 0.001 translates to 1.36 W/sq m or 0.4% in Earth's outgoing radiation error. Estimation errors are found to be independent of the satellites' altitude and inclination, if the nadir-looking is changed dynamically. The formation satellites are restricted to differ in only right ascension of planes and mean anomalies within slotted bounds. Three satellites in some specific formations show average albedo errors of less than 2% with respect to airborne, ground data and seven satellites in any slotted formation outperform the monolithic error of 3.6%. In fact, the maximum possible albedo error, purely based on angular sampling, of 12% for monoliths is outperformed by a five-satellite formation in any slotted arrangement and an eight satellite formation can bring that error down four fold to 3%. More

  6. Forested land cover classification on the Cumberland Plateau, Jackson County, Alabama: a comparison of Landsat ETM+ and SPOT5 images (United States)

    Yong Wang; Shanta Parajuli; Callie Schweitzer; Glendon Smalley; Dawn Lemke; Wubishet Tadesse; Xiongwen Chen


    Forest cover classifications focus on the overall growth form (physiognomy) of the community, dominant vegetation, and species composition of the existing forest. Accurately classifying the forest cover type is important for forest inventory and silviculture. We compared classification accuracy based on Landsat Enhanced Thematic Mapper Plus (Landsat ETM+) and Satellite...

  7. Large scale tissue histopathology image classification, segmentation, and visualization via deep convolutional activation features. (United States)

    Xu, Yan; Jia, Zhipeng; Wang, Liang-Bo; Ai, Yuqing; Zhang, Fang; Lai, Maode; Chang, Eric I-Chao


    Histopathology image analysis is a gold standard for cancer recognition and diagnosis. Automatic analysis of histopathology images can help pathologists diagnose tumor and cancer subtypes, alleviating the workload of pathologists. There are two basic types of tasks in digital histopathology image analysis: image classification and image segmentation. Typical problems with histopathology images that hamper automatic analysis include complex clinical representations, limited quantities of training images in a dataset, and the extremely large size of singular images (usually up to gigapixels). The property of extremely large size for a single image also makes a histopathology image dataset be considered large-scale, even if the number of images in the dataset is limited. In this paper, we propose leveraging deep convolutional neural network (CNN) activation features to perform classification, segmentation and visualization in large-scale tissue histopathology images. Our framework transfers features extracted from CNNs trained by a large natural image database, ImageNet, to histopathology images. We also explore the characteristics of CNN features by visualizing the response of individual neuron components in the last hidden layer. Some of these characteristics reveal biological insights that have been verified by pathologists. According to our experiments, the framework proposed has shown state-of-the-art performance on a brain tumor dataset from the MICCAI 2014 Brain Tumor Digital Pathology Challenge and a colon cancer histopathology image dataset. The framework proposed is a simple, efficient and effective system for histopathology image automatic analysis. We successfully transfer ImageNet knowledge as deep convolutional activation features to the classification and segmentation of histopathology images with little training data. CNN features are significantly more powerful than expert-designed features.

  8. Information analysis of hyperspectral images from the hyperion satellite (United States)

    Puzachenko, Yu. G.; Sandlersky, R. B.; Krenke, A. N.; Puzachenko, M. Yu.


    A new method of estimating the outgoing radiation spectra data obtained from the Hyperion EO-1 satellite is considered. In theoretical terms, this method is based on the nonequilibrium thermodynamics concept with corresponding estimates of the entropy and the Kullbak information. The obtained information estimates make it possible to assess the effective work of the landscape cover both in general and for its various types and to identify the spectrum ranges primarily responsible for the information increment and, accordingly, for the effective work. The information is measured in the frequency band intervals corresponding to the peaks of solar radiation absorption by different pigments, mesophyll, and water to evaluate the system operation by their synthesis and moisture accumulation. This method is assumed to be effective in investigation of ecosystem functioning by hyperspectral remote sensing.

  9. Classification of visualization exudates fundus images results using ...

    African Journals Online (AJOL)

    The kernel function settings; linear, polynomial, quadratic and RBF have an effect on the classification results. For SVM1, the best parameter in classifying pixels is linear kernel function. The visualization results using CAC and radar chart are classified using ts accuracy. It has proven to discriminated exudates and non ...

  10. Site scale wetness classification of tundra regions with C-band SAR satellite data

    DEFF Research Database (Denmark)

    Widhalm, Barbara; Bartsch, Annett; Siewert, Matthias Benjamin


    , especially C-band ASAR GM data (1-km resolution). A circumpolar wetness classification map has been introduced previously [1]. With heterogeneity being a major challenge in the Arctic, higher spatial resolution products than GM are essential. In this study we therefore investigate the potential...... of this approach at site scale using ENVISAT ASAR WS data (∼120 m resolution). These higher resolution ASAR WS maps have been produced for study sites representing different settings throughout the Arctic and compared to high resolution land cover maps and field survey data. It can be shown that a medium...

  11. A minimum spanning forest based classification method for dedicated breast CT images

    Energy Technology Data Exchange (ETDEWEB)

    Pike, Robert [Department of Radiology and Imaging Sciences, Emory University School of Medicine, Atlanta, Georgia 30329 (United States); Sechopoulos, Ioannis [Department of Radiology and Imaging Sciences, Emory University School of Medicine, Atlanta, Georgia 30329 and Winship Cancer Institute of Emory University, Atlanta, Georgia 30322 (United States); Fei, Baowei, E-mail: [Department of Radiology and Imaging Sciences, Emory University School of Medicine, Atlanta, Georgia 30329 (United States); Department of Biomedical Engineering, Emory University and Georgia Institute of Technology, Atlanta, Georgia 30322 (United States); Department of Mathematics and Computer Science, Emory University, Atlanta, Georgia 30322 (United States); Winship Cancer Institute of Emory University, Atlanta, Georgia 30322 (United States)


    Purpose: To develop and test an automated algorithm to classify different types of tissue in dedicated breast CT images. Methods: Images of a single breast of five different patients were acquired with a dedicated breast CT clinical prototype. The breast CT images were processed by a multiscale bilateral filter to reduce noise while keeping edge information and were corrected to overcome cupping artifacts. As skin and glandular tissue have similar CT values on breast CT images, morphologic processing is used to identify the skin based on its position information. A support vector machine (SVM) is trained and the resulting model used to create a pixelwise classification map of fat and glandular tissue. By combining the results of the skin mask with the SVM results, the breast tissue is classified as skin, fat, and glandular tissue. This map is then used to identify markers for a minimum spanning forest that is grown to segment the image using spatial and intensity information. To evaluate the authors’ classification method, they use DICE overlap ratios to compare the results of the automated classification to those obtained by manual segmentation on five patient images. Results: Comparison between the automatic and the manual segmentation shows that the minimum spanning forest based classification method was able to successfully classify dedicated breast CT image with average DICE ratios of 96.9%, 89.8%, and 89.5% for fat, glandular, and skin tissue, respectively. Conclusions: A 2D minimum spanning forest based classification method was proposed and evaluated for classifying the fat, skin, and glandular tissue in dedicated breast CT images. The classification method can be used for dense breast tissue quantification, radiation dose assessment, and other applications in breast imaging.

  12. Local feature representation based on linear filtering with feature pooling and divisive normalization for remote sensing image classification (United States)

    Wan, Lihong; Liu, Na; Guo, Yiyou; Huo, Hong; Fang, Tao


    We propose a local feature representation based on two types of linear filtering, feature pooling, and nonlinear divisive normalization for remote sensing image classification. First, images are decomposed using a bank of log-Gabor and Gaussian derivative filters to obtain filtering responses that are robust to changes in various lighting conditions. Second, the filtering responses computed using the same filter at nearby locations are pooled together to enhance position invariance and compact representation. Third, divisive normalization with channel-wise strategy, in which each pooled feature is divided by a common factor plus the sum of the neighboring features to reduce dependencies among nearby locations, is introduced to extract divisive normalization features (DNFs). Power-law transformation and principal component analysis are applied to make DNF significantly distinguishable, followed by feature fusion to enhance local description. Finally, feature encoding is used to aggregate DNFs into a global representation. Experiments on 21-class land use and 19-class satellite scene datasets demonstrate the effectiveness of the channel-wise divisive normalization compared with standard normalization across channels and the fusion of the two types of linear filtering in improving classification accuracy. The experiments also illustrate that the proposed method is competitive with state-of-the-art approaches.

  13. Mammographic quantitative image analysis and biologic image composition for breast lesion characterization and classification

    Energy Technology Data Exchange (ETDEWEB)

    Drukker, Karen, E-mail:; Giger, Maryellen L.; Li, Hui [Department of Radiology, University of Chicago, Chicago, Illinois 60637 (United States); Duewer, Fred; Malkov, Serghei; Joe, Bonnie; Kerlikowske, Karla; Shepherd, John A. [Radiology Department, University of California, San Francisco, California 94143 (United States); Flowers, Chris I. [Department of Radiology, University of South Florida, Tampa, Florida 33612 (United States); Drukteinis, Jennifer S. [Department of Radiology, H. Lee Moffitt Cancer Center and Research Institute, Tampa, Florida 33612 (United States)


    Purpose: To investigate whether biologic image composition of mammographic lesions can improve upon existing mammographic quantitative image analysis (QIA) in estimating the probability of malignancy. Methods: The study population consisted of 45 breast lesions imaged with dual-energy mammography prior to breast biopsy with final diagnosis resulting in 10 invasive ductal carcinomas, 5 ductal carcinomain situ, 11 fibroadenomas, and 19 other benign diagnoses. Analysis was threefold: (1) The raw low-energy mammographic images were analyzed with an established in-house QIA method, “QIA alone,” (2) the three-compartment breast (3CB) composition measure—derived from the dual-energy mammography—of water, lipid, and protein thickness were assessed, “3CB alone”, and (3) information from QIA and 3CB was combined, “QIA + 3CB.” Analysis was initiated from radiologist-indicated lesion centers and was otherwise fully automated. Steps of the QIA and 3CB methods were lesion segmentation, characterization, and subsequent classification for malignancy in leave-one-case-out cross-validation. Performance assessment included box plots, Bland–Altman plots, and Receiver Operating Characteristic (ROC) analysis. Results: The area under the ROC curve (AUC) for distinguishing between benign and malignant lesions (invasive and DCIS) was 0.81 (standard error 0.07) for the “QIA alone” method, 0.72 (0.07) for “3CB alone” method, and 0.86 (0.04) for “QIA+3CB” combined. The difference in AUC was 0.043 between “QIA + 3CB” and “QIA alone” but failed to reach statistical significance (95% confidence interval [–0.17 to + 0.26]). Conclusions: In this pilot study analyzing the new 3CB imaging modality, knowledge of the composition of breast lesions and their periphery appeared additive in combination with existing mammographic QIA methods for the distinction between different benign and malignant lesion types.

  14. Automated Classification of Lung Cancer Types from Cytological Images Using Deep Convolutional Neural Networks

    Directory of Open Access Journals (Sweden)

    Atsushi Teramoto


    Full Text Available Lung cancer is a leading cause of death worldwide. Currently, in differential diagnosis of lung cancer, accurate classification of cancer types (adenocarcinoma, squamous cell carcinoma, and small cell carcinoma is required. However, improving the accuracy and stability of diagnosis is challenging. In this study, we developed an automated classification scheme for lung cancers presented in microscopic images using a deep convolutional neural network (DCNN, which is a major deep learning technique. The DCNN used for classification consists of three convolutional layers, three pooling layers, and two fully connected layers. In evaluation experiments conducted, the DCNN was trained using our original database with a graphics processing unit. Microscopic images were first cropped and resampled to obtain images with resolution of 256 × 256 pixels and, to prevent overfitting, collected images were augmented via rotation, flipping, and filtering. The probabilities of three types of cancers were estimated using the developed scheme and its classification accuracy was evaluated using threefold cross validation. In the results obtained, approximately 71% of the images were classified correctly, which is on par with the accuracy of cytotechnologists and pathologists. Thus, the developed scheme is useful for classification of lung cancers from microscopic images.

  15. Ship Detection and Classification on Optical Remote Sensing Images Using Deep Learning

    Directory of Open Access Journals (Sweden)

    Liu Ying


    Full Text Available Ship detection and classification is critical for national maritime security and national defense. Although some SAR (Synthetic Aperture Radar image-based ship detection approaches have been proposed and used, they are not able to satisfy the requirement of real-world applications as the number of SAR sensors is limited, the resolution is low, and the revisit cycle is long. As massive optical remote sensing images of high resolution are available, ship detection and classification on theses images is becoming a promising technique, and has attracted great attention on applications including maritime security and traffic control. Some digital image processing methods have been proposed to detect ships in optical remote sensing images, but most of them face difficulty in terms of accuracy, performance and complexity. Recently, an autoencoder-based deep neural network with extreme learning machine was proposed, but it cannot meet the requirement of real-world applications as it only works with simple and small-scaled data sets. Therefore, in this paper, we propose a novel ship detection and classification approach which utilizes deep convolutional neural network (CNN as the ship classifier. The performance of our proposed ship detection and classification approach was evaluated on a set of images downloaded from Google Earth at the resolution 0.5m. 99% detection accuracy and 95% classification accuracy were achieved. In model training, 75× speedup is achieved on 1 Nvidia Titanx GPU.

  16. A fast and automatic mosaic method for high-resolution satellite images (United States)

    Chen, Hongshun; He, Hui; Xiao, Hongyu; Huang, Jing


    We proposed a fast and fully automatic mosaic method for high-resolution satellite images. First, the overlapped rectangle is computed according to geographical locations of the reference and mosaic images and feature points on both the reference and mosaic images are extracted by a scale-invariant feature transform (SIFT) algorithm only from the overlapped region. Then, the RANSAC method is used to match feature points of both images. Finally, the two images are fused into a seamlessly panoramic image by the simple linear weighted fusion method or other method. The proposed method is implemented in C++ language based on OpenCV and GDAL, and tested by Worldview-2 multispectral images with a spatial resolution of 2 meters. Results show that the proposed method can detect feature points efficiently and mosaic images automatically.

  17. Multi-model image classification in heterogeneous databases


    Kachouri, Rostom


    Image recognition is widely studied by the scientific community. The proposed research in this field is addressed to various applications of computer vision systems and multiple source image categorization. This PhD dissertation deals particularly with content based image recognition systems in heterogeneous databases. Images in this kind of databases belong to different concepts and represent a heterogeneous content. In this case and to ensure a reliable representation, a broad description i...

  18. Evolving matched filter transform pairs for satellite image processing (United States)

    Peterson, Michael R.; Horner, Toby; Moore, Frank


    Wavelets provide an attractive method for efficient image compression. For transmission across noisy or bandwidth limited channels, a signal may be subjected to quantization in which the signal is transcribed onto a reduced alphabet in order to save bandwidth. Unfortunately, the performance of the discrete wavelet transform (DWT) degrades at increasing levels of quantization. In recent years, evolutionary algorithms (EAs) have been employed to optimize wavelet-inspired transform filters to improve compression performance in the presence of quantization. Wavelet filters consist of a pair of real-valued coefficient sets; one set represents the compression filter while the other set defines the image reconstruction filter. The reconstruction filter is defined as the biorthogonal inverse of the compression filter. Previous research focused upon two approaches to filter optimization. In one approach, the original wavelet filter is used for image compression while the reconstruction filter is evolved by an EA. In the second approach, both the compression and reconstruction filters are evolved. In both cases, the filters are not biorthogonally related to one another. We propose a novel approach to filter evolution. The EA optimizes a compression filter. Rather than using a wavelet filter or evolving a second filter for reconstruction, the reconstruction filter is computed as the biorthogonal inverse of the evolved compression filter. The resulting filter pair retains some of the mathematical properties of wavelets. This paper compares this new approach to existing filter optimization approaches to determine its suitability for the optimization of image filters appropriate for defense applications of image processing.

  19. Visual Analytics Applied to Image Analysis : From Segmentation to Classification

    NARCIS (Netherlands)

    Rauber, Paulo


    Image analysis is the field of study concerned with extracting information from images. This field is immensely important for commercial and scientific applications, from identifying people in photographs to recognizing diseases in medical images. The goal behind the work presented in this thesis is

  20. Hyperspectral Image Enhancement and Mixture Deep-Learning Classification of Corneal Epithelium Injuries (United States)

    Md Noor, Siti Salwa; Michael, Kaleena; Marshall, Stephen; Ren, Jinchang


    In our preliminary study, the reflectance signatures obtained from hyperspectral imaging (HSI) of normal and abnormal corneal epithelium tissues of porcine show similar morphology with subtle differences. Here we present image enhancement algorithms that can be used to improve the interpretability of data into clinically relevant information to facilitate diagnostics. A total of 25 corneal epithelium images without the application of eye staining were used. Three image feature extraction approaches were applied for image classification: (i) image feature classification from histogram using a support vector machine with a Gaussian radial basis function (SVM-GRBF); (ii) physical image feature classification using deep-learning Convolutional Neural Networks (CNNs) only; and (iii) the combined classification of CNNs and SVM-Linear. The performance results indicate that our chosen image features from the histogram and length-scale parameter were able to classify with up to 100% accuracy; particularly, at CNNs and CNNs-SVM, by employing 80% of the data sample for training and 20% for testing. Thus, in the assessment of corneal epithelium injuries, HSI has high potential as a method that could surpass current technologies regarding speed, objectivity, and reliability. PMID:29144388

  1. A Public Image Database for Benchmark of Plant Seedling Classification Algorithms

    DEFF Research Database (Denmark)

    Giselsson, Thomas Mosgaard; Nyholm Jørgensen, Rasmus; Jensen, Peter Kryger

    A database of images of approximately 960 unique plants belonging to 12 species at several growth stages is made publicly available. It comprises annotated RGB images with a physical resolution of roughly 10 pixels per mm. To standardise the evaluation of classification results obtained with the ...

  2. Classification of photographed document images based on deep-learning features (United States)

    Zhong, Guoqiang; Yao, Hui; Liu, Yutong; Hong, Chen; Pham, Tuan


    In this paper, we propose two new problems related to classification of photographed document images, and based on deep learning methods, present the baseline solutions for these two problems. The first problem is that, for some photographed document images, which book do they belong to? The second one is, for some photographed document images, what is the type of the book they belong to? To address these two problems, we apply "AexNet" to the collected document images. Using the pre-trained "AlexNet" on the ImageNet data set directly, we obtain 92.57% accuracy for the book-name classification and 93.33% accuracy for the book-type one. After fine-tuning on the training set of the photographed document images, the accuracy of the book-name classification increases to 95.54% and that of the booktype one to 95.42%. To our best knowledge, although there exist many image classification algorithm, no previous work has targeted to these two challenging problems. In addition, the experiments demonstrate that deep-learning features outperform features extracted with traditional image descriptors on these two problems.

  3. Distance-Based Image Classification: Generalizing to New Classes at Near Zero Cost

    NARCIS (Netherlands)

    Mensink, T.; Verbeek, J.; Perronnin, F.; Csurka, G.


    We study large-scale image classification methods that can incorporate new classes and training images continuously over time at negligible cost. To this end, we consider two distance-based classifiers, the k-nearest neighbor (k-NN) and nearest class mean (NCM) classifiers, and introduce a new

  4. A Multivariate Model for Coastal Water Quality Mapping Using Satellite Remote Sensing Images. (United States)

    Su, Yuan-Fong; Liou, Jun-Jih; Hou, Ju-Chen; Hung, Wei-Chun; Hsu, Shu-Mei; Lien, Yi-Ting; Su, Ming-Daw; Cheng, Ke-Sheng; Wang, Yeng-Fung


    his study demonstrates the feasibility of coastal water quality mapping using satellite remote sensing images. Water quality sampling campaigns were conducted over a coastal area in northern Taiwan for measurements of three water quality variables including Secchi disk depth, turbidity, and total suspended solids. SPOT satellite images nearly concurrent with the water quality sampling campaigns were also acquired. A spectral reflectance estimation scheme proposed in this study was applied to SPOT multispectral images for estimation of the sea surface reflectance. Two models, univariate and multivariate, for water quality estimation using the sea surface reflectance derived from SPOT images were established. The multivariate model takes into consideration the wavelength-dependent combined effect of individual seawater constituents on the sea surface reflectance and is superior over the univariate model. Finally, quantitative coastal water quality mapping was accomplished by substituting the pixel-specific spectral reflectance into the multivariate water quality estimation model.

  5. Novel Unsupervised Classification of Collapsed Buildings Using Satellite Imagery, Hazard Scenarios and Fragility Functions

    Directory of Open Access Journals (Sweden)

    Luis Moya


    Full Text Available Although supervised machine learning classification techniques have been successfully applied to detect collapsed buildings, there is still a major problem that few publications have addressed. The success of supervised machine learning strongly depends on the availability of training samples. Unfortunately, in the aftermath of a large-scale disaster, training samples become available only after several weeks or even months. However, following a disaster, information on the damage situation is one of the most important necessities for rapid search-and-rescue efforts and relief distribution. In this paper, a modification of the supervised machine learning classification technique called logistic regression is presented. Here, the training samples are replaced with probabilistic information, which is calculated from the spatial distribution of the hazard under consideration and one or more fragility functions. Such damage probabilities can be collected almost in real time for specific disasters such as earthquakes and/or tsunamis. We present the application of the proposed method to the 2011 Great East Japan Earthquake and Tsunami for collapsed building detection. The results show good agreement with a field survey performed by the Ministry of Land, Infrastructure, Transport and Tourism, with an overall accuracy of over 80%. Thus, the proposed method can significantly contribute to a rapid estimation of the number and locations of collapsed buildings.

  6. Wavelet-based multicomponent denoising on GPU to improve the classification of hyperspectral images (United States)

    Quesada-Barriuso, Pablo; Heras, Dora B.; Argüello, Francisco; Mouriño, J. C.


    Supervised classification allows handling a wide range of remote sensing hyperspectral applications. Enhancing the spatial organization of the pixels over the image has proven to be beneficial for the interpretation of the image content, thus increasing the classification accuracy. Denoising in the spatial domain of the image has been shown as a technique that enhances the structures in the image. This paper proposes a multi-component denoising approach in order to increase the classification accuracy when a classification method is applied. It is computed on multicore CPUs and NVIDIA GPUs. The method combines feature extraction based on a 1Ddiscrete wavelet transform (DWT) applied in the spectral dimension followed by an Extended Morphological Profile (EMP) and a classifier (SVM or ELM). The multi-component noise reduction is applied to the EMP just before the classification. The denoising recursively applies a separable 2D DWT after which the number of wavelet coefficients is reduced by using a threshold. Finally, inverse 2D-DWT filters are applied to reconstruct the noise free original component. The computational cost of the classifiers as well as the cost of the whole classification chain is high but it is reduced achieving real-time behavior for some applications through their computation on NVIDIA multi-GPU platforms.

  7. The effects of rectification and Global Positioning System errors on satellite image-based estimates of forest area (United States)

    Ronald E. McRoberts


    Satellite image-based maps of forest attributes are of considerable interest and are used for multiple purposes such as international reporting by countries that have no national forest inventory and small area estimation for all countries. Construction of the maps typically entails, in part, rectifying the satellite images to a geographic coordinate system, observing...

  8. Object-based image analysis for cadastral mapping using satellite images (United States)

    Kohli, D.; Crommelinck, S.; Bennett, R.; Koeva, M.; Lemmen, C.


    Cadasters together with land registry form a core ingredient of any land administration system. Cadastral maps comprise of the extent, ownership and value of land which are essential for recording and updating land records. Traditional methods for cadastral surveying and mapping often prove to be labor, cost and time intensive: alternative approaches are thus being researched for creating such maps. With the advent of very high resolution (VHR) imagery, satellite remote sensing offers a tremendous opportunity for (semi)-automation of cadastral boundaries detection. In this paper, we explore the potential of object-based image analysis (OBIA) approach for this purpose by applying two segmentation methods, i.e. MRS (multi-resolution segmentation) and ESP (estimation of scale parameter) to identify visible cadastral boundaries. Results show that a balance between high percentage of completeness and correctness is hard to achieve: a low error of commission often comes with a high error of omission. However, we conclude that the resulting segments/land use polygons can potentially be used as a base for further aggregation into tenure polygons using participatory mapping.

  9. Review On Feasibility of Using Satellite Imaging for Risk Management of Derailment Related Turnout Component Failures (United States)

    Dindar, Serdar; Kaewunruen, Sakdirat; Osman, Mohd H.


    One of the emerging significant advances in engineering, satellite imaging (SI) is becoming very common in any kind of civil engineering projects e.g., bridge, canal, dam, earthworks, power plant, water works etc., to provide an accurate, economical and expeditious means of acquiring a rapid assessment. Satellite imaging services in general utilise combinations of high quality satellite imagery, image processing and interpretation to obtain specific required information, e.g. surface movement analysis. To extract, manipulate and provide such a precise knowledge, several systems, including geographic information systems (GIS) and global positioning system (GPS), are generally used for orthorectification. Although such systems are useful for mitigating risk from projects, their productiveness is arguable and operational risk after application is open to discussion. As the applicability of any novel application to the railway industry is often measured in terms of whether or not it has gained in-depth knowledge and to what degree, as a result of errors during its operation, this novel application generates risk in ongoing projects. This study reviews what can be achievable for risk management of railway turnouts thorough satellite imaging. The methodology is established on the basis of other published articles in this area and the results of applications to understand how applicable such imagining process is on railway turnouts, and how sub-systems in turnouts can be effectively traced/operated with less risk than at present. As a result of this review study, it is aimed that the railway sector better understands risk mitigation in particular applications.

  10. Attitude motion compensation for imager on Fengyun-4 geostationary meteorological satellite (United States)

    Lyu, Wang; Dai, Shoulun; Dong, Yaohai; Shen, Yili; Song, Xiaozheng; Wang, Tianshu


    A compensation method is used in Chinese Fengyun-4 satellite to counteracting the line-of-sight influence by attitude motion during imaging. The method is acted on-board by adding the compensation amount to the instrument scanning control circuit. The mathematics simulation and the three-axis air-bearing test results show that the method works effectively.

  11. Vegetation Cover Change in Yellowstone National Park Detected Using Landsat Satellite Image Analysis (United States)

    Potter, Christopher S.


    Results from Landsat satellite image analysis since 1987 in all unburned areas (since the 1880s) of Yellowstone National Park (YNP) showed that consistent decreases in the normalized difference vegetation index (NDVI) have been strongly dependent on periodic variations in peak annual snow water equivalents (SWE).

  12. Effects of satellite image spatial aggregation and resolution on estimates of forest land area (United States)

    M.D. Nelson; R.E. McRoberts; G.R. Holden; M.E. Bauer


    Satellite imagery is being used increasingly in association with national forest inventories (NFIs) to produce maps and enhance estimates of forest attributes. We simulated several image spatial resolutions within sparsely and heavily forested study areas to assess resolution effects on estimates of forest land area, independent of other sensor characteristics. We...

  13. Simultaneous hierarchical segmentation and vectorization of satellite images through combined data sampling and anisotropic triangulation

    Energy Technology Data Exchange (ETDEWEB)

    Grazzini, Jacopo [Los Alamos National Laboratory; Prasad, Lakshman [Los Alamos National Laboratory; Dillard, Scott [PNNL


    The automatic detection, recognition , and segmentation of object classes in remote sensed images is of crucial importance for scene interpretation and understanding. However, it is a difficult task because of the high variability of satellite data. Indeed, the observed scenes usually exhibit a high degree of complexity, where complexity refers to the large variety of pictorial representations of objects with the same semantic meaning and also to the extensive amount of available det.ails. Therefore, there is still a strong demand for robust techniques for automatic information extraction and interpretation of satellite images. In parallel, there is a growing interest in techniques that can extract vector features directly from such imagery. In this paper, we investigate the problem of automatic hierarchical segmentation and vectorization of multispectral satellite images. We propose a new algorithm composed of the following steps: (i) a non-uniform sampling scheme extracting most salient pixels in the image, (ii) an anisotropic triangulation constrained by the sampled pixels taking into account both strength and directionality of local structures present in the image, (iii) a polygonal grouping scheme merging, through techniques based on perceptual information , the obtained segments to a smaller quantity of superior vectorial objects. Besides its computational efficiency, this approach provides a meaningful polygonal representation for subsequent image analysis and/or interpretation.

  14. Optimal query-based relevance feedback in medical image retrieval using score fusion-based classification. (United States)

    Behnam, Mohammad; Pourghassem, Hossein


    In this paper, a new content-based medical image retrieval (CBMIR) framework using an effective classification method and a novel relevance feedback (RF) approach are proposed. For a large-scale database with diverse collection of different modalities, query image classification is inevitable due to firstly, reducing the computational complexity and secondly, increasing influence of data fusion by removing unimportant data and focus on the more valuable information. Hence, we find probability distribution of classes in the database using Gaussian mixture model (GMM) for each feature descriptor and then using the fusion of obtained scores from the dependency probabilities, the most relevant clusters are identified for a given query. Afterwards, visual similarity of query image and images in relevant clusters are calculated. This method is performed separately on all feature descriptors, and then the results are fused together using feature similarity ranking level fusion algorithm. In the RF level, we propose a new approach to find the optimal queries based on relevant images. The main idea is based on density function estimation of positive images and strategy of moving toward the aggregation of estimated density function. The proposed framework has been evaluated on ImageCLEF 2005 database consisting of 10,000 medical X-ray images of 57 semantic classes. The experimental results show that compared with the existing CBMIR systems, our framework obtains the acceptable performance both in the image classification and in the image retrieval by RF.


    Directory of Open Access Journals (Sweden)

    A. Kianisarkaleh


    Full Text Available Feature extraction plays a key role in hyperspectral images classification. Using unlabeled samples, often unlimitedly available, unsupervised and semisupervised feature extraction methods show better performance when limited number of training samples exists. This paper illustrates the importance of selecting appropriate unlabeled samples that used in feature extraction methods. Also proposes a new method for unlabeled samples selection using spectral and spatial information. The proposed method has four parts including: PCA, prior classification, posterior classification and sample selection. As hyperspectral image passes these parts, selected unlabeled samples can be used in arbitrary feature extraction methods. The effectiveness of the proposed unlabeled selected samples in unsupervised and semisupervised feature extraction is demonstrated using two real hyperspectral datasets. Results show that through selecting appropriate unlabeled samples, the proposed method can improve the performance of feature extraction methods and increase classification accuracy.

  16. Efficiency of the spectral-spatial classification of hyperspectral imaging data (United States)

    Borzov, S. M.; Potaturkin, O. I.


    The efficiency of methods of the spectral-spatial classification of similarly looking types of vegetation on the basis of hyperspectral data of remote sensing of the Earth, which take into account local neighborhoods of analyzed image pixels, is experimentally studied. Algorithms that involve spatial pre-processing of the raw data and post-processing of pixel-based spectral classification maps are considered. Results obtained both for a large-size hyperspectral image and for its test fragment with different methods of training set construction are reported. The classification accuracy in all cases is estimated through comparisons of ground-truth data and classification maps formed by using the compared methods. The reasons for the differences in these estimates are discussed.

  17. Astrophysical Information from Objective Prism Digitized Images: Classification with an Artificial Neural Network

    Directory of Open Access Journals (Sweden)

    Bratsolis Emmanuel


    Full Text Available Stellar spectral classification is not only a tool for labeling individual stars but is also useful in studies of stellar population synthesis. Extracting the physical quantities from the digitized spectral plates involves three main stages: detection, extraction, and classification of spectra. Low-dispersion objective prism images have been used and automated methods have been developed. The detection and extraction problems have been presented in previous works. In this paper, we present a classification method based on an artificial neural network (ANN. We make a brief presentation of the entire automated system and we compare the new classification method with the previously used method of maximum correlation coefficient (MCC. Digitized photographic material has been used here. The method can also be used on CCD spectral images.

  18. Utility of multispectral imaging for nuclear classification of routine clinical histopathology imagery

    Directory of Open Access Journals (Sweden)

    Harvey Neal R


    Full Text Available Abstract Background We present an analysis of the utility of multispectral versus standard RGB imagery for routine H&E stained histopathology images, in particular for pixel-level classification of nuclei. Our multispectral imagery has 29 spectral bands, spaced 10 nm within the visual range of 420–700 nm. It has been hypothesized that the additional spectral bands contain further information useful for classification as compared to the 3 standard bands of RGB imagery. We present analyses of our data designed to test this hypothesis. Results For classification using all available image bands, we find the best performance (equal tradeoff between detection rate and false alarm rate is obtained from either the multispectral or our "ccd" RGB imagery, with an overall increase in performance of 0.79% compared to the next best performing image type. For classification using single image bands, the single best multispectral band (in the red portion of the spectrum gave a performance increase of 0.57%, compared to performance of the single best RGB band (red. Additionally, red bands had the highest coefficients/preference in our classifiers. Principal components analysis of the multispectral imagery indicates only two significant image bands, which is not surprising given the presence of two stains. Conclusion Our results indicate that multispectral imagery for routine H&E stained histopathology provides minimal additional spectral information for a pixel-level nuclear classification task than would standard RGB imagery.

  19. Using different satellite imagery and classification techniques to assess the contribution of trees outside forests in the municipality of Maringá, Brazil

    Directory of Open Access Journals (Sweden)

    Betina Doubrawa


    Full Text Available Forest cover of the Maringá municipality, located in northern Parana State, was mapped in this study. Mapping was carried out by using high-resolution HRC sensor imagery and medium resolution CCD sensor imagery from the CBERS satellite. Images were georeferenced and forest vegetation patches (TOFs - trees outside forests were classified using two methods of digital classification: reflectance-based or the digital number of each pixel, and object-oriented. The areas of each polygon were calculated, which allowed each polygon to be segregated into size classes. Thematic maps were built from the resulting polygon size classes and summary statistics generated from each size class for each area. It was found that most forest fragments in Maringá were smaller than 500 m². There was also a difference of 58.44% in the amount of vegetation between the high-resolution imagery and medium resolution imagery due to the distinct spatial resolution of the sensors. It was concluded that high-resolution geotechnology is essential to provide reliable information on urban greens and forest cover under highly human-perturbed landscapes.

  20. Study of Image Analysis Algorithms for Segmentation, Feature Extraction and Classification of Cells

    Directory of Open Access Journals (Sweden)

    Margarita Gamarra


    Full Text Available Recent advances in microcopy and improvements in image processing algorithms have allowed the development of computer-assisted analytical approaches in cell identification. Several applications could be mentioned in this field: Cellular phenotype identification, disease detection and treatment, identifying virus entry in cells and virus classification; these applications could help to complement the opinion of medical experts. Although many surveys have been presented in medical image analysis, they focus mainly in tissues and organs and none of the surveys about image cells consider an analysis following the stages in the typical image processing: Segmentation, feature extraction and classification. The goal of this study is to provide comprehensive and critical analyses about the trends in each stage of cell image processing. In this paper, we present a literature survey about cell identification using different image processing techniques.


    Directory of Open Access Journals (Sweden)

    Marcio Augusto Reolon Schmidt


    Full Text Available Orbital imaging techniques offer comprehensive coverage of different regions for numerous environmental and socioeconomic applications, revealing the spatial characteristics and land use of those regions. The advantages of remote sensing include its ability to record spatial distribution patterns, and spectral and temporal data over large regions. The objective of this research is to evaluate the performance of different multispectral image classification methods in the selection of general vegetation, based on a set of samples taken from a Landsat 8 image. The quality of multispectral images and their final classification is usually evaluated based on the Kappa index, which is used as the quality standard in many remote sensing software programs. The classification methods chosen for this study were Parallelepiped, Maximum Likelihood, Mahalanobis Distance, and neural networks. The most suitable classification was used as standard and the other images were compared with it to determine the degree of similarity ranking (IS1x, defined as the percentage of pixels classified differently from those of the standard image. The IS1x was determined using a Matlab routine involving pixel subtraction between images. The results indicate that probability distribution methods are more suitable for discriminating vegetation types than other methods, and that some band combinations should be chosen.

  2. Contextual convolutional neural networks for lung nodule classification using Gaussian-weighted average image patches (United States)

    Lee, Haeil; Lee, Hansang; Park, Minseok; Kim, Junmo


    Lung cancer is the most common cause of cancer-related death. To diagnose lung cancers in early stages, numerous studies and approaches have been developed for cancer screening with computed tomography (CT) imaging. In recent years, convolutional neural networks (CNN) have become one of the most common and reliable techniques in computer aided detection (CADe) and diagnosis (CADx) by achieving state-of-the-art-level performances for various tasks. In this study, we propose a CNN classification system for false positive reduction of initially detected lung nodule candidates. First, image patches of lung nodule candidates are extracted from CT scans to train a CNN classifier. To reflect the volumetric contextual information of lung nodules to 2D image patch, we propose a weighted average image patch (WAIP) generation by averaging multiple slice images of lung nodule candidates. Moreover, to emphasize central slices of lung nodules, slice images are locally weighted according to Gaussian distribution and averaged to generate the 2D WAIP. With these extracted patches, 2D CNN is trained to achieve the classification of WAIPs of lung nodule candidates into positive and negative labels. We used LUNA 2016 public challenge database to validate the performance of our approach for false positive reduction in lung CT nodule classification. Experiments show our approach improves the classification accuracy of lung nodules compared to the baseline 2D CNN with patches from single slice image.

  3. Comparison of Object-Based Image Analysis Approaches to Mapping New Buildings in Accra, Ghana Using Multi-Temporal QuickBird Satellite Imagery

    Directory of Open Access Journals (Sweden)

    Yu Hsin Tsai


    Full Text Available The goal of this study was to map and quantify the number of newly constructed buildings in Accra, Ghana between 2002 and 2010 based on high spatial resolution satellite image data. Two semi-automated feature detection approaches for detecting and mapping newly constructed buildings based on QuickBird very high spatial resolution satellite imagery were analyzed: (1 post-classification comparison; and (2 bi-temporal layerstack classification. Feature Analyst software based on a spatial contextual classifier and ENVI Feature Extraction that uses a true object-based image analysis approach of image segmentation and segment classification were evaluated. Final map products representing new building objects were compared and assessed for accuracy using two object-based accuracy measures, completeness and correctness. The bi-temporal layerstack method generated more accurate results compared to the post-classification comparison method due to less confusion with background objects. The spectral/spatial contextual approach (Feature Analyst outperformed the true object-based feature delineation approach (ENVI Feature Extraction due to its ability to more reliably delineate individual buildings of various sizes. Semi-automated, object-based detection followed by manual editing appears to be a reliable and efficient approach for detecting and enumerating new building objects. A bivariate regression analysis was performed using neighborhood-level estimates of new building density regressed on a census-derived measure of socio-economic status, yielding an inverse relationship with R2 = 0.31 (n = 27; p = 0.00. The primary utility of the new building delineation results is to support spatial analyses of land cover and land use and demographic change.

  4. The galilean satellites and jupiter: voyager 2 imaging science results. (United States)

    Smith, B A; Soderblom, L A; Beebe, R; Boyce, J; Briggs, G; Carr, M; Collins, S A; Cook, A F; Danielson, G E; Davies, M E; Hunt, G E; Ingersoll, A; Johnson, T V; Masursky, H; McCauley, J; Morrison, D; Owen, T; Sagan, C; Shoemaker, E M; Strom, R; Suomi, V E; Veverka, J


    Voyager 2, during its encounter with the Jupiter system, provided images that both complement and supplement in important ways the Voyager 1 images. While many changes have been observed in Jupiter's visual appearance, few, yet significant, changes have been detected in the principal atmospheric currents. Jupiter's ring system is strongly forward scattering at visual wavelengths and consists of a narrow annulus of highest particle density, within which is a broader region in which the density is lower. On Io, changes are observed in eruptive activity, plume structure, and surface albedo patterns. Europa's surface retains little or no record of intense meteorite bombardment, but does reveal a complex and, as yet, little-understood system of overlapping bright and dark linear features. Ganymede is found to have at least one unit of heavily cratered terrain on a surface that otherwise suggests widespread tectonism. Except for two large ringed basins, Callisto's entire surface is heavily cratered.

  5. Building identification from very high-resolution satellite images (United States)

    Lhomme, Stephane

    Urbanisation still remains one of the main problems worldwide. The extent and rapidity of the urban growth induce a number of socio-economic and environmental conflicts everywhere. In order to reduce these problems, urban planners need to integrate spatial information in planning tools. Actually high expectations are made on Very High Spatial Resolution imagery (VHSR). These high-spatial resolution images are available at a reasonable price and due to short revisit periods, they offer a high degree of actuality. However, interpretation methods seem not to be adapted to this new type of images. The aim of our study is to develop a new method for semi-automatic building extraction with VHSR. The different steps performed to achieve our objective are each presented in a chapter. In the first chapter, the general context of our research is described with the definition of our objective. After a short historical review of urbanisation, we focus on urban growth and associated problems. In the following we discuss the possible contributions of geography to reduce these problems. After discussing concepts, theories and methodologies of geographical analysis in urban areas, we present existing general urban planning tools. Finally, we show the special interest of our study that is due to a growing need to integrate spatial information in these decision support tools. In the second chapter we verify the possibility of reaching our objective by analysing the technical characteristics of the images, the noise and the distortions which affect the images. Quality and interpretability of the studied image is analysed in order to show the capacity of these image to represent urban objects as close to reality as possible. The results confirm the potential of VHSR Imagery for urban objects analysis. The third chapter deal with the preliminary steps necessary for the elaboration of our method of building extraction. First, we evaluate the quality of the Sherbrooke Ikonos image

  6. Image Fusion-Based Land Cover Change Detection Using Multi-Temporal High-Resolution Satellite Images

    Directory of Open Access Journals (Sweden)

    Biao Wang


    Full Text Available Change detection is usually treated as a problem of explicitly detecting land cover transitions in satellite images obtained at different times, and helps with emergency response and government management. This study presents an unsupervised change detection method based on the image fusion of multi-temporal images. The main objective of this study is to improve the accuracy of unsupervised change detection from high-resolution multi-temporal images. Our method effectively reduces change detection errors, since spatial displacement and spectral differences between multi-temporal images are evaluated. To this end, a total of four cross-fused images are generated with multi-temporal images, and the iteratively reweighted multivariate alteration detection (IR-MAD method—a measure for the spectral distortion of change information—is applied to the fused images. In this experiment, the land cover change maps were extracted using multi-temporal IKONOS-2, WorldView-3, and GF-1 satellite images. The effectiveness of the proposed method compared with other unsupervised change detection methods is demonstrated through experimentation. The proposed method achieved an overall accuracy of 80.51% and 97.87% for cases 1 and 2, respectively. Moreover, the proposed method performed better when differentiating the water area from the vegetation area compared to the existing change detection methods. Although the water area beneath moderate and sparse vegetation canopy was captured, vegetation cover and paved regions of the water body were the main sources of omission error, and commission errors occurred primarily in pixels of mixed land use and along the water body edge. Nevertheless, the proposed method, in conjunction with high-resolution satellite imagery, offers a robust and flexible approach to land cover change mapping that requires no ancillary data for rapid implementation.


    Directory of Open Access Journals (Sweden)

    N. Champion


    Full Text Available Detecting clouds and their shadows is one of the primaries steps to perform when processing satellite images because they may alter the quality of some products such as large-area orthomosaics. The main goal of this paper is to present the automatic method developed at IGN-France for detecting clouds and shadows in a sequence of satellite images. In our work, surface reflectance orthoimages are used. They were processed from initial satellite images using a dedicated software. The cloud detection step consists of a region-growing algorithm. Seeds are firstly extracted. For that purpose and for each input ortho-image to process, we select the other ortho-images of the sequence that intersect it. The pixels of the input ortho-image are secondly labelled seeds if the difference of reflectance (in the blue channel with overlapping ortho-images is bigger than a given threshold. Clouds are eventually delineated using a region-growing method based on a radiometric and homogeneity criterion. Regarding the shadow detection, our method is based on the idea that a sha