Sample records for microarray image segmentation

  1. Microarray BASICA: Background Adjustment, Segmentation, Image Compression and Analysis of Microarray Images

    Jianping Hua


    Full Text Available This paper presents microarray BASICA: an integrated image processing tool for background adjustment, segmentation, image compression, and analysis of cDNA microarray images. BASICA uses a fast Mann-Whitney test-based algorithm to segment cDNA microarray images, and performs postprocessing to eliminate the segmentation irregularities. The segmentation results, along with the foreground and background intensities obtained with the background adjustment, are then used for independent compression of the foreground and background. We introduce a new distortion measurement for cDNA microarray image compression and devise a coding scheme by modifying the embedded block coding with optimized truncation (EBCOT algorithm (Taubman, 2000 to achieve optimal rate-distortion performance in lossy coding while still maintaining outstanding lossless compression performance. Experimental results show that the bit rate required to ensure sufficiently accurate gene expression measurement varies and depends on the quality of cDNA microarray images. For homogeneously hybridized cDNA microarray images, BASICA is able to provide from a bit rate as low as 5 bpp the gene expression data that are 99% in agreement with those of the original 32 bpp images.


    V.G. Biju


    Full Text Available An automatic cDNA microarray image processing using an improved fuzzy clustering algorithm is presented in this paper. The spot segmentation algorithm proposed uses the gridding technique developed by the authors earlier, for finding the co-ordinates of each spot in an image. Automatic cropping of spots from microarray image is done using these co-ordinates. The present paper proposes an improved fuzzy clustering algorithm Possibility fuzzy local information c means (PFLICM to segment the spot foreground (FG from background (BG. The PFLICM improves fuzzy local information c means (FLICM algorithm by incorporating typicality of a pixel along with gray level information and local spatial information. The performance of the algorithm is validated using a set of simulated cDNA microarray images added with different levels of AWGN noise. The strength of the algorithm is tested by computing the parameters such as the Segmentation matching factor (SMF, Probability of error (pe, Discrepancy distance (D and Normal mean square error (NMSE. SMF value obtained for PFLICM algorithm shows an improvement of 0.9 % and 0.7 % for high noise and low noise microarray images respectively compared to FLICM algorithm. The PFLICM algorithm is also applied on real microarray images and gene expression values are computed.

  3. Segmentation and intensity estimation for microarray images with saturated pixels

    Yang Yan


    Full Text Available Abstract Background Microarray image analysis processes scanned digital images of hybridized arrays to produce the input spot-level data for downstream analysis, so it can have a potentially large impact on those and subsequent analysis. Signal saturation is an optical effect that occurs when some pixel values for highly expressed genes or peptides exceed the upper detection threshold of the scanner software (216 - 1 = 65, 535 for 16-bit images. In practice, spots with a sizable number of saturated pixels are often flagged and discarded. Alternatively, the saturated values are used without adjustments for estimating spot intensities. The resulting expression data tend to be biased downwards and can distort high-level analysis that relies on these data. Hence, it is crucial to effectively correct for signal saturation. Results We developed a flexible mixture model-based segmentation and spot intensity estimation procedure that accounts for saturated pixels by incorporating a censored component in the mixture model. As demonstrated with biological data and simulation, our method extends the dynamic range of expression data beyond the saturation threshold and is effective in correcting saturation-induced bias when the lost information is not tremendous. We further illustrate the impact of image processing on downstream classification, showing that the proposed method can increase diagnostic accuracy using data from a lymphoma cancer diagnosis study. Conclusions The presented method adjusts for signal saturation at the segmentation stage that identifies a pixel as part of the foreground, background or other. The cluster membership of a pixel can be altered versus treating saturated values as truly observed. Thus, the resulting spot intensity estimates may be more accurate than those obtained from existing methods that correct for saturation based on already segmented data. As a model-based segmentation method, our procedure is able to identify inner

  4. Robust protein microarray image segmentation using improved seeded region growing algorithm

    Liqiang Wang(王立强); Xuxiang Ni(倪旭翔); Zukang Lu(陆祖康)


    Protein microarray technology has recently emerged as a powerful tool for biomedical research. Before automatic analysis the protein microarray images, protein spots in the images must be determined appropriately by spot segmentation algorithm. In this paper, an improved seeded region growing (ISRG)algorithm for protein microarray segmentation is presented, the seeds are obtained by finding the positions of the printed spots, and the protein spot regions are grown through these seeds. The experiment results show that the presented algorithm is accurate for adaptive shape segmentation and robust for protein microarray images contaminated by noise.

  5. Segmentation of cDNA Microarray Images using Parallel Spectral Clustering

    Sandrine MOUYSSET


    Full Text Available Microarray technology generates large amounts of expression level of genes to be analyzed simultaneously. This analysis implies microarray image segmentation to extract the quantitative information from spots. Spectral clustering is one of the most relevant unsupervised methods able to gather data without a priori information on shapes or locality. We propose and test on microarray images a parallel strategy for the Spectral Clustering method based on domain decomposition with a criterion to determine the number of clusters.

  6. Segmentation of cDNA Microarray Images using Parallel Spectral Clustering

    Daniel RUIZ


    Full Text Available Microarray technology generates large amounts of expression level of genes to be analyzed simultaneously. This analysis implies microarray image segmentation to extract the quantitative information from spots. Spectral clustering is one of the most relevant unsupervised methods able to gather data without a priori information on shapes or locality. We propose and test on microarray images a parallel strategy for the Spectral Clustering method based on domain decomposition with a criterion to determine the number of clusters.

  7. MIGS-GPU: Microarray Image Gridding and Segmentation on the GPU.

    Katsigiannis, Stamos; Zacharia, Eleni; Maroulis, Dimitris


    cDNA microarray is a powerful tool for simultaneously studying the expression level of thousands of genes. Nevertheless, the analysis of microarray images remains an arduous and challenging task due to the poor quality of the images which often suffer from noise, artifacts, and uneven background. In this work, the MIGS-GPU (Microarray Image Gridding and Segmentation on GPU) software for gridding and segmenting microarray images is presented. MIGS-GPU's computations are performed on the graphics processing unit (GPU) by means of the CUDA architecture in order to achieve fast performance and increase the utilization of available system resources. Evaluation on both real and synthetic cDNA microarray images showed that MIGS-GPU provides better performance than state-of-the-art alternatives, while the proposed GPU implementation achieves significantly lower computational times compared to the respective CPU approaches. Consequently, MIGS-GPU can be an advantageous and useful tool for biomedical laboratories, offering a userfriendly interface that requires minimum input in order to run.

  8. Skin Images Segmentation

    Ali E. Zaart


    Full Text Available Problem statement: Image segmentation is a fundamental step in many applications of image processing. Skin cancer has been the most common of all new cancers detected each year. At early stage detection of skin cancer, simple and economic treatment can cure it mostly. An accurate segmentation of skin images can help the diagnosis to define well the region of the cancer. The principal approach of segmentation is based on thresholding (classification that is lied to the problem of the thresholds estimation. Approach: The objective of this study is to develop a method to segment the skin images based on a mixture of Beta distributions. We assume that the data in skin images can be modeled by a mixture of Beta distributions. We used an unsupervised learning technique with Beta distribution to estimate the statistical parameters of the data in skin image and then estimate the thresholds for segmentation. Results: The proposed method of skin images segmentation was implemented and tested on different skin images. We obtained very good results in comparing with the same techniques with Gamma distribution. Conclusion: The experiment showed that the proposed method obtained very good results but it requires more testing on different types of skin images.

  9. Dictionary Based Image Segmentation

    Dahl, Anders Bjorholm; Dahl, Vedrana Andersen


    We propose a method for weakly supervised segmentation of natural images, which may contain both textured or non-textured regions. Our texture representation is based on a dictionary of image patches. To divide an image into separated regions with similar texture we use an implicit level sets...


    Jesús Angulo


    Full Text Available Robust image analysis of spots in microarrays (quality control + spot segmentation + quantification is a requirement for automated software which is of fundamental importance for a high-throughput analysis of genomics microarray-based data. This paper deals with the development of model-based image processing algorithms for qualifying/segmenting/quantifying adaptively each spot according to its morphology. A series of morphologicalmodels for spot intensities are introduced. The spot typologies representmost of the possible qualitative cases identified from a large database (different routines, techniques, etc.. Then, based on these spot models, a classification framework has been developed. The spot feature extraction and classification (without segmenting is based on converting the spot image to polar coordinates and, after computing the radial/angular projections, the calculation of granulometric curves and derived parameters from these projections. Spot contour segmentation can also be solved by working in polar coordinates, calculating the up/downminimal path, which is easily obtained with the generalized distance function. With this model-based technique, the segmentation can be regularised by controlling different elements of the algorithm. According to the spot typology (e.g., doughnut-like or egg-like spots, several minimal paths can be computed to obtain a multi-region segmentation. Moreover, this segmentation is more robust and sensible to weak spots, improving the previous approaches.

  11. Scorpion image segmentation system

    Joseph, E.; Aibinu, A. M.; Sadiq, B. A.; Bello Salau, H.; Salami, M. J. E.


    Death as a result of scorpion sting has been a major public health problem in developing countries. Despite the high rate of death as a result of scorpion sting, little report exists in literature of intelligent device and system for automatic detection of scorpion. This paper proposed a digital image processing approach based on the floresencing characteristics of Scorpion under Ultra-violet (UV) light for automatic detection and identification of scorpion. The acquired UV-based images undergo pre-processing to equalize uneven illumination and colour space channel separation. The extracted channels are then segmented into two non-overlapping classes. It has been observed that simple thresholding of the green channel of the acquired RGB UV-based image is sufficient for segmenting Scorpion from other background components in the acquired image. Two approaches to image segmentation have also been proposed in this work, namely, the simple average segmentation technique and K-means image segmentation. The proposed algorithm has been tested on over 40 UV scorpion images obtained from different part of the world and results obtained show an average accuracy of 97.7% in correctly classifying the pixel into two non-overlapping clusters. The proposed 1system will eliminate the problem associated with some of the existing manual approaches presently in use for scorpion detection.

  12. Microscopic Halftone Image Segmentation

    WANG Yong-gang; YANG Jie; DING Yong-sheng


    Microscopic halftone image recognition and analysis can provide quantitative evidence for printing quality control and fault diagnosis of printing devices, while halftone image segmentation is one of the significant steps during the procedure. Automatic segmentation on microscopic dots by the aid of the Fuzzy C-Means (FCM) method that takes account of the fuzziness of halftone image and utilizes its color information adequately is realized. Then some examples show the technique effective and simple with better performance of noise immunity than some usual methods. In addition, the segmentation results obtained by the FCM in different color spaces are compared, which indicates that the method using the FCM in the f1f2f3 color space is superior to the rest.

  13. Statistical Images Segmentation

    Corina Curilă


    Full Text Available This paper deals with fuzzy statistical imagesegmentation. We introduce a new hierarchicalMarkovian fuzzy hidden field model, which extends to thefuzzy case the classical Pérez and Heitz hard model. Twofuzzy statistical segmentation methods related with themodel proposed are defined in this paper and we show viasimulations that they are competitive with, in some casesthan, the classical Maximum Posterior Mode (MPMbased methods. Furthermore, they are faster, which willshould facilitate extensions to more than two hard classesin future work. In addition, the model proposed isapplicable to the multiscale segmentation andmultiresolution images fusion problems.

  14. Automated medical image segmentation techniques

    Sharma Neeraj


    Full Text Available Accurate segmentation of medical images is a key step in contouring during radiotherapy planning. Computed topography (CT and Magnetic resonance (MR imaging are the most widely used radiographic techniques in diagnosis, clinical studies and treatment planning. This review provides details of automated segmentation methods, specifically discussed in the context of CT and MR images. The motive is to discuss the problems encountered in segmentation of CT and MR images, and the relative merits and limitations of methods currently available for segmentation of medical images.

  15. Multiple Segmentation of Image Stacks

    Smets, Jonathan; Jaeger, Manfred


    We propose a method for the simultaneous construction of multiple image segmentations by combining a recently proposed “convolution of mixtures of Gaussians” model with a multi-layer hidden Markov random field structure. The resulting method constructs for a single image several, alternative...... segmentations that capture different structural elements of the image. We also apply the method to collections of images with identical pixel dimensions, which we call image stacks. Here it turns out that the method is able to both identify groups of similar images in the stack, and to provide segmentations...

  16. High-throughput biomarker segmentation on ovarian cancer tissue microarrays via hierarchical normalized cuts.

    Janowczyk, Andrew; Chandran, Sharat; Singh, Rajendra; Sasaroli, Dimitra; Coukos, George; Feldman, Michael D; Madabhushi, Anant


    We present a system for accurately quantifying the presence and extent of stain on account of a vascular biomarker on tissue microarrays. We demonstrate our flexible, robust, accurate, and high-throughput minimally supervised segmentation algorithm, termed hierarchical normalized cuts (HNCuts) for the specific problem of quantifying extent of vascular staining on ovarian cancer tissue microarrays. The high-throughput aspect of HNCut is driven by the use of a hierarchically represented data structure that allows us to merge two powerful image segmentation algorithms-a frequency weighted mean shift and the normalized cuts algorithm. HNCuts rapidly traverses a hierarchical pyramid, generated from the input image at various color resolutions, enabling the rapid analysis of large images (e.g., a 1500 × 1500 sized image under 6 s on a standard 2.8-GHz desktop PC). HNCut is easily generalizable to other problem domains and only requires specification of a few representative pixels (swatch) from the object of interest in order to segment the target class. Across ten runs, the HNCut algorithm was found to have average true positive, false positive, and false negative rates (on a per pixel basis) of 82%, 34%, and 18%, in terms of overlap, when evaluated with respect to a pathologist annotated ground truth of the target region of interest. By comparison, a popular supervised classifier (probabilistic boosting trees) was only able to marginally improve on the true positive and false negative rates (84% and 14%) at the expense of a higher false positive rate (73%), with an additional computation time of 62% compared to HNCut. We also compared our scheme against a k-means clustering approach, which both the HNCut and PBT schemes were able to outperform. Our success in accurately quantifying the extent of vascular stain on ovarian cancer TMAs suggests that HNCut could be a very powerful tool in digital pathology and bioinformatics applications where it could be used to

  17. Employing image processing techniques for cancer detection using microarray images.

    Dehghan Khalilabad, Nastaran; Hassanpour, Hamid


    Microarray technology is a powerful genomic tool for simultaneously studying and analyzing the behavior of thousands of genes. The analysis of images obtained from this technology plays a critical role in the detection and treatment of diseases. The aim of the current study is to develop an automated system for analyzing data from microarray images in order to detect cancerous cases. The proposed system consists of three main phases, namely image processing, data mining, and the detection of the disease. The image processing phase performs operations such as refining image rotation, gridding (locating genes) and extracting raw data from images the data mining includes normalizing the extracted data and selecting the more effective genes. Finally, via the extracted data, cancerous cell is recognized. To evaluate the performance of the proposed system, microarray database is employed which includes Breast cancer, Myeloid Leukemia and Lymphomas from the Stanford Microarray Database. The results indicate that the proposed system is able to identify the type of cancer from the data set with an accuracy of 95.45%, 94.11%, and 100%, respectively.

  18. Neural network for image segmentation

    Skourikhine, Alexei N.; Prasad, Lakshman; Schlei, Bernd R.


    Image analysis is an important requirement of many artificial intelligence systems. Though great effort has been devoted to inventing efficient algorithms for image analysis, there is still much work to be done. It is natural to turn to mammalian vision systems for guidance because they are the best known performers of visual tasks. The pulse- coupled neural network (PCNN) model of the cat visual cortex has proven to have interesting properties for image processing. This article describes the PCNN application to the processing of images of heterogeneous materials; specifically PCNN is applied to image denoising and image segmentation. Our results show that PCNNs do well at segmentation if we perform image smoothing prior to segmentation. We use PCNN for obth smoothing and segmentation. Combining smoothing and segmentation enable us to eliminate PCNN sensitivity to the setting of the various PCNN parameters whose optimal selection can be difficult and can vary even for the same problem. This approach makes image processing based on PCNN more automatic in our application and also results in better segmentation.

  19. Extended -Regular Sequence for Automated Analysis of Microarray Images

    Jin Hee-Jeong


    Full Text Available Microarray study enables us to obtain hundreds of thousands of expressions of genes or genotypes at once, and it is an indispensable technology for genome research. The first step is the analysis of scanned microarray images. This is the most important procedure for obtaining biologically reliable data. Currently most microarray image processing systems require burdensome manual block/spot indexing work. Since the amount of experimental data is increasing very quickly, automated microarray image analysis software becomes important. In this paper, we propose two automated methods for analyzing microarray images. First, we propose the extended -regular sequence to index blocks and spots, which enables a novel automatic gridding procedure. Second, we provide a methodology, hierarchical metagrid alignment, to allow reliable and efficient batch processing for a set of microarray images. Experimental results show that the proposed methods are more reliable and convenient than the commercial tools.

  20. Low-complexity PDE-based approach for automatic microarray image processing.

    Belean, Bogdan; Terebes, Romulus; Bot, Adrian


    Microarray image processing is known as a valuable tool for gene expression estimation, a crucial step in understanding biological processes within living organisms. Automation and reliability are open subjects in microarray image processing, where grid alignment and spot segmentation are essential processes that can influence the quality of gene expression information. The paper proposes a novel partial differential equation (PDE)-based approach for fully automatic grid alignment in case of microarray images. Our approach can handle image distortions and performs grid alignment using the vertical and horizontal luminance function profiles. These profiles are evolved using a hyperbolic shock filter PDE and then refined using the autocorrelation function. The results are compared with the ones delivered by state-of-the-art approaches for grid alignment in terms of accuracy and computational complexity. Using the same PDE formalism and curve fitting, automatic spot segmentation is achieved and visual results are presented. Considering microarray images with different spots layouts, reliable results in terms of accuracy and reduced computational complexity are achieved, compared with existing software platforms and state-of-the-art methods for microarray image processing.

  1. Research Progress on Image Segmentation



  2. An Active Contour for Range Image Segmentation

    Khaldi Amine; Merouani Hayet Farida


    In this paper a new classification of range image segmentation method is proposed according to the criterion of homogeneity which obeys the segmentation, then, a deformable model-type active contour “Snake” is applied to segment range images.

  3. Image Segmentation Based on Support Vector Machine

    XU Hai-xiang; ZHU Guang-xi; TIAN Jin-wen; ZHANG Xiang; PENG Fu-yuan


    Image segmentation is a necessary step in image analysis. Support vector machine (SVM) approach is proposed to segment images and its segmentation performance is evaluated.Experimental results show that: the effects of kernel function and model parameters on the segmentation performance are significant; SVM approach is less sensitive to noise in image segmentation; The segmentation performance of SVM approach is better than that of back-propagation multi-layer perceptron (BP-MLP) approach and fuzzy c-means (FCM) approach.

  4. Segmentation in dermatological hyperspectral images: dedicated methods

    Koprowski, Robert; Olczyk, Paweł


    Background Segmentation of hyperspectral medical images is one of many image segmentation methods which require profiling. This profiling involves either the adjustment of existing, known image segmentation methods or a proposal of new dedicated methods of hyperspectral image segmentation. Taking into consideration the size of analysed data, the time of analysis is of major importance. Therefore, the authors proposed three new dedicated methods of hyperspectral image segmentation with special...

  5. Medical image segmentation by MDP model

    Lu, Yisu; Chen, Wufan


    MDP (Dirichlet Process Mixtures) model is applied to segment medical images in this paper. Segmentation can been automatically done without initializing segmentation class numbers. The MDP model segmentation algorithm is used to segment natural images and MR (Magnetic Resonance) images in the paper. To demonstrate the accuracy of the MDP model segmentation algorithm, many compared experiments, such as EM (Expectation Maximization) image segmentation algorithm, K-means image segmentation algorithm and MRF (Markov Field) image segmentation algorithm, have been done to segment medical MR images. All the methods are also analyzed quantitatively by using DSC (Dice Similarity Coefficients). The experiments results show that DSC of MDP model segmentation algorithm of all slices exceed 90%, which show that the proposed method is robust and accurate.

  6. Imaging combined autoimmune and infectious disease microarrays

    Ewart, Tom; Raha, Sandeep; Kus, Dorothy; Tarnopolsky, Mark


    Bacterial and viral pathogens are implicated in many severe autoimmune diseases, acting through such mechanisms as molecular mimicry, and superantigen activation of T-cells. For example, Helicobacter pylori, well known cause of stomach ulcers and cancers, is also identified in ischaemic heart disease (mimicry of heat shock protein 65), autoimmune pancreatitis, systemic sclerosis, autoimmune thyroiditis (HLA DRB1*0301 allele susceptibility), and Crohn's disease. Successful antibiotic eradication of H.pylori often accompanies their remission. Yet current diagnostic devices, and test-limiting cost containment, impede recognition of the linkage, delaying both diagnosis and therapeutic intervention until the chronic debilitating stage. We designed a 15 minute low cost 39 antigen microarray assay, combining autoimmune, viral and bacterial antigens1. This enables point-of-care serodiagnosis and cost-effective narrowly targeted concurrent antibiotic and monoclonal anti-T-cell and anti-cytokine immunotherapy. Arrays of 26 pathogen and 13 autoimmune antigens with IgG and IgM dilution series were printed in triplicate on epoxysilane covalent binding slides with Teflon well masks. Sera diluted 1:20 were incubated 10 minutes, washed off, anti-IgG-Cy3 (green) and anti-IgM-Dy647 (red) were incubated for 5 minutes, washed off and the slide was read in an ArrayWoRx(e) scanning CCD imager (Applied Precision, Issaquah, WA). As a preliminary model for the combined infectious disease-autoimmune diagnostic microarray we surveyed 98 unidentified, outdated sera that were discarded after Hepatitis B antibody testing. In these, significant IgG or IgM autoantibody levels were found: dsDNA 5, ssDNA 11, Ro 2, RNP 7, SSB 4, gliadin 2, thyroglobulin 13 cases. Since control sera showed no autoantibodies, the high frequency of anti-DNA and anti-thyroglobulin antibodies found in infected sera lend increased support for linkage of infection to subsequent autoimmune disease. Expansion of the antigen

  7. Segmentation of Color Images Based on Different Segmentation Techniques

    Purnashti Bhosale


    Full Text Available In this paper, we propose an Color image segmentation algorithm based on different segmentation techniques. We recognize the background objects such as the sky, ground, and trees etc based on the color and texture information using various methods of segmentation. The study of segmentation techniques by using different threshold methods such as global and local techniques and they are compared with one another so as to choose the best technique for threshold segmentation. Further segmentation is done by using clustering method and Graph cut method to improve the results of segmentation.

  8. XRA image segmentation using regression

    Jin, Jesse S.


    Segmentation is an important step in image analysis. Thresholding is one of the most important approaches. There are several difficulties in segmentation, such as automatic selecting threshold, dealing with intensity distortion and noise removal. We have developed an adaptive segmentation scheme by applying the Central Limit Theorem in regression. A Gaussian regression is used to separate the distribution of background from foreground in a single peak histogram. The separation will help to automatically determine the threshold. A small 3 by 3 widow is applied and the modal of the local histogram is used to overcome noise. Thresholding is based on local weighting, where regression is used again for parameter estimation. A connectivity test is applied to the final results to remove impulse noise. We have applied the algorithm to x-ray angiogram images to extract brain arteries. The algorithm works well for single peak distribution where there is no valley in the histogram. The regression provides a method to apply knowledge in clustering. Extending regression for multiple-level segmentation needs further investigation.

  9. An Active Contour for Range Image Segmentation

    Khaldi Amine


    Full Text Available In this paper a new classification of range image segmentation method is proposed according to the criterion of homogeneity which obeys the segmentation, then, a deformable model-type active contour “Snake” is applied to segment range images.

  10. Image Segmentation by Using Threshold Techniques

    Al-amri, Salem Saleh; D., Khamitkar S


    This paper attempts to undertake the study of segmentation image techniques by using five threshold methods as Mean method, P-tile method, Histogram Dependent Technique (HDT), Edge Maximization Technique (EMT) and visual Technique and they are compared with one another so as to choose the best technique for threshold segmentation techniques image. These techniques applied on three satellite images to choose base guesses for threshold segmentation image.

  11. Fluorescence Lifetime Imaging of Quantum Dot Labeled DNA Microarrays

    Jonathan G. Terry


    Full Text Available Quantum dot (QD labeling combined with fluorescence lifetime imaging microscopy is proposed as a powerful transduction technique for the detection of DNA hybridization events. Fluorescence lifetime analysis of DNA microarray spots of hybridized QD labeled target indicated a characteristic lifetime value of 18.8 ns, compared to 13.3 ns obtained for spots of free QD solution, revealing that QD labels are sensitive to the spot microenvironment. Additionally, time gated detection was shown to improve the microarray image contrast ratio by 1.8, achieving femtomolar target sensitivity. Finally, lifetime multiplexing based on Qdot525 and Alexa430 was demonstrated using a single excitation-detection readout channel.

  12. Liver segmentation in color images (Conference Presentation)

    Ma, Burton; Kingham, T. Peter; Miga, Michael I.; Jarnagin, William R.; Simpson, Amber L.


    We describe the use of a deep learning method for semantic segmentation of the liver from color images. Our intent is to eventually embed a semantic segmentation method into a stereo-vision based navigation system for open liver surgery. Semantic segmentation of the stereo images will allow us to reconstruct a point cloud containing the liver surfaces and excluding all other non-liver structures. We trained a deep learning algorithm using 136 images and 272 augmented images computed by rotating the original images. We tested the trained algorithm on 27 images that were not used for training purposes. The method achieves an 88% median pixel labeling accuracy over the test images.

  13. Hierarchical image segmentation for learning object priors

    Prasad, Lakshman [Los Alamos National Laboratory; Yang, Xingwei [TEMPLE UNIV.; Latecki, Longin J [TEMPLE UNIV.; Li, Nan [TEMPLE UNIV.


    The proposed segmentation approach naturally combines experience based and image based information. The experience based information is obtained by training a classifier for each object class. For a given test image, the result of each classifier is represented as a probability map. The final segmentation is obtained with a hierarchial image segmentation algorithm that considers both the probability maps and the image features such as color and edge strength. We also utilize image region hierarchy to obtain not only local but also semi-global features as input to the classifiers. Moreover, to get robust probability maps, we take into account the region context information by averaging the probability maps over different levels of the hierarchical segmentation algorithm. The obtained segmentation results are superior to the state-of-the-art supervised image segmentation algorithms.

  14. Convolutional Neural Networks for SAR Image Segmentation

    Malmgren-Hansen, David; Nobel-Jørgensen, Morten


    Segmentation of Synthetic Aperture Radar (SAR) images has several uses, but it is a difficult task due to a number of properties related to SAR images. In this article we show how Convolutional Neural Networks (CNNs) can easily be trained for SAR image segmentation with good results. Besides...

  15. Distance measures for image segmentation evaluation

    Monteiro, Fernando C.; Campilho, Aurélio C.


    In this paper we present a study of evaluation measures that enable the quantification of the quality of an image segmentation result. Despite significant advances in image segmentation techniques, evaluation of these techniques thus far has been largely subjective. Typically, the effectiveness of a new algorithm is demonstrated only by the presentation of a few segmented images and is otherwise left to subjective evaluation by the reader. Such an evaluation criterion can be useful for differ...

  16. Unsupervised Performance Evaluation of Image Segmentation

    Chabrier Sebastien


    Full Text Available We present in this paper a study of unsupervised evaluation criteria that enable the quantification of the quality of an image segmentation result. These evaluation criteria compute some statistics for each region or class in a segmentation result. Such an evaluation criterion can be useful for different applications: the comparison of segmentation results, the automatic choice of the best fitted parameters of a segmentation method for a given image, or the definition of new segmentation methods by optimization. We first present the state of art of unsupervised evaluation, and then, we compare six unsupervised evaluation criteria. For this comparative study, we use a database composed of 8400 synthetic gray-level images segmented in four different ways. Vinet's measure (correct classification rate is used as an objective criterion to compare the behavior of the different criteria. Finally, we present the experimental results on the segmentation evaluation of a few gray-level natural images.

  17. Image Segmentation Using Hierarchical Merge Tree

    Liu, Ting; Seyedhosseini, Mojtaba; Tasdizen, Tolga


    This paper investigates one of the most fundamental computer vision problems: image segmentation. We propose a supervised hierarchical approach to object-independent image segmentation. Starting with over-segmenting superpixels, we use a tree structure to represent the hierarchy of region merging, by which we reduce the problem of segmenting image regions to finding a set of label assignment to tree nodes. We formulate the tree structure as a constrained conditional model to associate region merging with likelihoods predicted using an ensemble boundary classifier. Final segmentations can then be inferred by finding globally optimal solutions to the model efficiently. We also present an iterative training and testing algorithm that generates various tree structures and combines them to emphasize accurate boundaries by segmentation accumulation. Experiment results and comparisons with other very recent methods on six public data sets demonstrate that our approach achieves the state-of-the-art region accuracy and is very competitive in image segmentation without semantic priors.

  18. Different Image Segmentation Techniques for Dental Image Extraction

    R. Bala Subramanyam


    Full Text Available Image segmentation is the process of partitioning a digital image into multiple segments and often used to locate objects and boundaries (lines, curves etc.. In this paper, we have proposed image segmentation techniques: Region based, Texture based, Edge based. These techniques have been implemented on dental radiographs and gained good results compare to conventional technique known as Thresholding based technique. The quantitative results show the superiority of the image segmentation technique over three proposed techniques and conventional technique.

  19. Plugin procedure in segmentation and application to hyperspectral image segmentation

    Girard, R


    In this article we give our contribution to the problem of segmentation with plug-in procedures. We give general sufficient conditions under which plug in procedure are efficient. We also give an algorithm that satisfy these conditions. We give an application of the used algorithm to hyperspectral images segmentation. Hyperspectral images are images that have both spatial and spectral coherence with thousands of spectral bands on each pixel. In the proposed procedure we combine a reduction dimension technique and a spatial regularisation technique. This regularisation is based on the mixlet modelisation of Kolaczyck and Al.

  20. Colour application on mammography image segmentation

    Embong, R.; Aziz, N. M. Nik Ab.; Karim, A. H. Abd; Ibrahim, M. R.


    The segmentation process is one of the most important steps in image processing and computer vision since it is vital in the initial stage of image analysis. Segmentation of medical images involves complex structures and it requires precise segmentation result which is necessary for clinical diagnosis such as the detection of tumour, oedema, and necrotic tissues. Since mammography images are grayscale, researchers are looking at the effect of colour in the segmentation process of medical images. Colour is known to play a significant role in the perception of object boundaries in non-medical colour images. Processing colour images require handling more data, hence providing a richer description of objects in the scene. Colour images contain ten percent (10%) additional edge information as compared to their grayscale counterparts. Nevertheless, edge detection in colour image is more challenging than grayscale image as colour space is considered as a vector space. In this study, we implemented red, green, yellow, and blue colour maps to grayscale mammography images with the purpose of testing the effect of colours on the segmentation of abnormality regions in the mammography images. We applied the segmentation process using the Fuzzy C-means algorithm and evaluated the percentage of average relative error of area for each colour type. The results showed that all segmentation with the colour map can be done successfully even for blurred and noisy images. Also the size of the area of the abnormality region is reduced when compare to the segmentation area without the colour map. The green colour map segmentation produced the smallest percentage of average relative error (10.009%) while yellow colour map segmentation gave the largest percentage of relative error (11.367%).

  1. Iris image segmentation based on phase congruency

    Gao, Chao; Jiang, Da-Qin; Guo, Yong-Cai


    Iris image segmentation is very important for an iris recognition system. There are always iris noises as eyelash, eyelid, reflection and pupil in iris images. The paper proposes a virtual method of segmentation. By locating and normalizing iris images with Gabor filter, we can acquire information of image texture in a series of frequencies and orientations. Iris noise regions are determined based on phase congruency by a group of Gabor filters whose kernels are suitable for edge detection. These regions are filled according to the characteristics of iris noise. The experimental results show that the proposed method can segment iris images effectively.

  2. Iris image Segmentation Based on Phase Congruency

    GAO Chao; JIANG Da-qin; Guo Yong-cai


    @@ Iris image segmentation is very important for an iris recognition system.There are always iris noises as eyelash,eyelid,reflection and pupil in iris images.The paper proposes a virtual method of segmentation.By locating and normalizing iris images with Gabor filter,we can acquire information of image texture in a series of frequencies and orientations.Iris noise regions are determined based on phase congruency by a group of Gabor filters whose kernels are suitable for edge detection.These regions are filled according to the characteristics of iris noise.The experimental results show that the proposed method can segment iris images effectively.

  3. Probabilistic segmentation of remotely sensed images.

    Gorte, B.


    For information extraction from image data to create or update geographic information systems, objects are identified and labeled using an integration of segmentation and classification. This yields geometric and thematic information, respectively.Bayesian image classifiers calculate class posterior

  4. Multispectral image segmentation of breast pathology

    Hornak, Joseph P.; Blaakman, Andre; Rubens, Deborah; Totterman, Saara


    The signal intensity in a magnetic resonance image is not only a function of imaging parameters but also of several intrinsic tissue properties. Therefore, unlike other medical imaging modalities, magnetic resonance imaging (MRI) allows the imaging scientist to locate pathology using multispectral image segmentation. Multispectral image segmentation works best when orthogonal spectral regions are employed. In MRI, possible spectral regions are spin density (rho) , spin-lattice relaxation time T1, spin-spin relaxation time T2, and texture for each nucleus type and chemical shift. This study examines the ability of multispectral image segmentation to locate breast pathology using the total hydrogen T1, T2, and (rho) . The preliminary results indicate that our technique can locate cysts and fibroadenoma breast lesions with a minimum number of false-positives and false-negatives. Results, T1, T2, and (rho) algorithms, and segmentation techniques are presented.

  5. A New Framework for Interactive Images Segmentation



    Full Text Available Image segmentation has become a widely studied research problem in image processing. There exist different graph based solutions for interactive image segmentation but the domain of image segmentation still needs persistent improvements. The segmentation quality of existing techniques generally depends on the manual input provided in beginning, therefore, these algorithms may not produce quality segmentation with initial seed labels provided by a novice user. In this work we investigated the use of cellular automata in image segmentation and proposed a new algorithm that follows a cellular automaton in label propagation. It incorporates both the pixels? local and global information in the segmentation process. We introduced the novel global constraints in automata evolution rules; hence proposed scheme of automata evolution is more effective than the automata based earlier evolution schemes. Global constraints are also effective in deceasing the sensitivity towards small changes made in manual input; therefore proposed approach is less dependent on label seed marks. It can produce the quality segmentation with modest user efforts. Segmentation results indicate that the proposed algorithm performs better than the earlier segmentation techniques.

  6. Cluster Ensemble-based Image Segmentation

    Xiaoru Wang; Junping Du; Shuzhe Wu; Xu Li; Fu Li


    Image segmentation is the foundation of computer vision applications. In this paper, we propose a new cluster ensemble-based image segmentation algorithm, which overcomes several problems of traditional methods. We make two main contributions in this paper. First, we introduce the cluster ensemble concept to fuse the segmentation results from different types of visual features effectively, which can deliver a better final result and achieve a much more stable performance for broad categories ...

  7. Image segmentation with a finite element method

    Bourdin, Blaise


    The Mumford-Shah functional for image segmentation is an original approach of the image segmentation problem, based on a minimal energy criterion. Its minimization can be seen as a free discontinuity problem and is based on \\Gamma-convergence and bounded variation functions theories.Some new regu...

  8. Image Series Segmentation and Improved MC Algorithm

    WAN Wei-bing; SHI Peng-fei


    A semiautomatic segmentation method based on active contour is proposed for computed tomog-raphy (CT) image series. First, to get initial contour, one image slice was segmented exactly by C-V method based on Mumford-Shah model. Next, the computer will segment the nearby slice automatically using the snake model one by one. During segmenting of image slices, former slice boundary, as next slice initial con-tour, may cross over next slice real boundary and never return to right position. To avoid contour skipping over, the distance variance between two slices is evaluated by an threshold, which decides whether to initiate again. Moreover, a new improved marching cubes (MC) algorithm based on 2D images series segmentation boundary is given for 3D image reconstruction. Compared with the standard method, the proposed algorithm reduces detecting time and needs less storing memory. The effectiveness and capabilities of the algorithm were illustrated by experimental results.

  9. Metric Learning for Hyperspectral Image Segmentation

    Bue, Brian D.; Thompson, David R.; Gilmore, Martha S.; Castano, Rebecca


    We present a metric learning approach to improve the performance of unsupervised hyperspectral image segmentation. Unsupervised spatial segmentation can assist both user visualization and automatic recognition of surface features. Analysts can use spatially-continuous segments to decrease noise levels and/or localize feature boundaries. However, existing segmentation methods use tasks-agnostic measures of similarity. Here we learn task-specific similarity measures from training data, improving segment fidelity to classes of interest. Multiclass Linear Discriminate Analysis produces a linear transform that optimally separates a labeled set of training classes. The defines a distance metric that generalized to a new scenes, enabling graph-based segmentation that emphasizes key spectral features. We describe tests based on data from the Compact Reconnaissance Imaging Spectrometer (CRISM) in which learned metrics improve segment homogeneity with respect to mineralogical classes.

  10. Unsupervised Color-texture Image Segmentation

    YU Sheng-yang; ZHANG Fan; WANG Yong-gang; YANG Jie


    The measure J in J value segmentation (JSEG) falls to represent the discontinuity of color, which degrades the robustness and discrimination of JSEG. An improved approach for JSEG algorithm was proposed for unsupervised color-texture image segmentation. The texture and photometric invariant edge information were combined, which results in a discriminative measure for color-texture homogeneity. Based on the image whose pixel values are values of the new measure, region growing-merging algorithm used in JSEG was then employed to segment the image. Finally, experiments on a variety of real color images demonstrate performance improvement due to the proposed method.

  11. Adaptive textural segmentation of medical images

    Kuklinski, Walter S.; Frost, Gordon S.; MacLaughlin, Thomas


    A number of important problems in medical imaging can be described as segmentation problems. Previous fractal-based image segmentation algorithms have used either the local fractal dimension alone or the local fractal dimension and the corresponding image intensity as features for subsequent pattern recognition algorithms. An image segmentation algorithm that utilized the local fractal dimension, image intensity, and the correlation coefficient of the local fractal dimension regression analysis computation, to produce a three-dimension feature space that was partitioned to identify specific pixels of dental radiographs as being either bone, teeth, or a boundary between bone and teeth also has been reported. In this work we formulated the segmentation process as a configurational optimization problem and discuss the application of simulated annealing optimization methods to the solution of this specific optimization problem. The configurational optimization method allows information about both, the degree of correspondence between a candidate segment and an assumed textural model, and morphological information about the candidate segment to be used in the segmentation process. To apply this configurational optimization technique with a fractal textural model however, requires the estimation of the fractal dimension of an irregularly shaped candidate segment. The potential utility of a discrete Gerchberg-Papoulis bandlimited extrapolation algorithm to the estimation of the fractal dimension of an irregularly shaped candidate segment is also discussed.

  12. An efficient algorithm for color image segmentation

    Shikha Yadav


    Full Text Available In field of image processing, image segmentation plays an important role that focus on splitting the whole image into segments. Representation of an image so that it can be more easily analysed and involves more information is an important segmentation goal. The process of partitioning an image can be usually realized by Region based, Boundary based or edge based method. In this work a hybrid approach is followed that combines improved bee colony optimization and Tabu search for color image segmentation. The results produced from this hybrid approach are compared with non-sorted particle swarm optimization, non-sorted genetic algorithm and improved bee colony optimization. Results show that the Hybrid algorithm has better or somewhat similar performance as compared to other algorithms that are based on population. The algorithm is successfully implemented on MATLAB.

  13. Improving image segmentation by learning region affinities

    Prasad, Lakshman [Los Alamos National Laboratory; Yang, Xingwei [TEMPLE UNIV.; Latecki, Longin J [TEMPLE UNIV.


    We utilize the context information of other regions in hierarchical image segmentation to learn new regions affinities. It is well known that a single choice of quantization of an image space is highly unlikely to be a common optimal quantization level for all categories. Each level of quantization has its own benefits. Therefore, we utilize the hierarchical information among different quantizations as well as spatial proximity of their regions. The proposed affinity learning takes into account higher order relations among image regions, both local and long range relations, making it robust to instabilities and errors of the original, pairwise region affinities. Once the learnt affinities are obtained, we use a standard image segmentation algorithm to get the final segmentation. Moreover, the learnt affinities can be naturally unutilized in interactive segmentation. Experimental results on Berkeley Segmentation Dataset and MSRC Object Recognition Dataset are comparable and in some aspects better than the state-of-art methods.

  14. Anterior Segment Imaging in Combat Ocular Trauma

    Denise S. Ryan


    Full Text Available Purpose. To evaluate the use of ocular imaging to enhance management and diagnosis of war-related anterior segment ocular injuries. Methods. This study was a prospective observational case series from an ongoing IRB-approved combat ocular trauma tracking study. Subjects with anterior segment ocular injury were imaged, when possible, using anterior segment optical coherence tomography (AS-OCT, confocal microscopy (CM, and slit lamp biomicroscopy. Results. Images captured from participants with combat ocular trauma on different systems provided comprehensive and alternate views of anterior segment injury to investigators. Conclusion. In combat-related trauma of the anterior segment, adjunct image acquisition enhances slit lamp examination and enables real time In vivo observation of the cornea facilitating injury characterization, progression, and management.

  15. Probabilistic multiscale image segmentation by the hyperstack

    Vincken, Koenraad Lucas


    In the medical community, images from different modalities have found their way to a variety of medical disciplines. Multidimensional images have become indispensable in clinical diagnosis, therapy planning and evaluation. Image segmentation -- dividing an image into meaningful objects -- is a s

  16. SAR Image Segmentation using Vector Quantization Technique on Entropy Images

    Kekre, H B; Sarode, Tanuja K


    The development and application of various remote sensing platforms result in the production of huge amounts of satellite image data. Therefore, there is an increasing need for effective querying and browsing in these image databases. In order to take advantage and make good use of satellite images data, we must be able to extract meaningful information from the imagery. Hence we proposed a new algorithm for SAR image segmentation. In this paper we propose segmentation using vector quantization technique on entropy image. Initially, we obtain entropy image and in second step we use Kekre's Fast Codebook Generation (KFCG) algorithm for segmentation of the entropy image. Thereafter, a codebook of size 128 was generated for the Entropy image. These code vectors were further clustered in 8 clusters using same KFCG algorithm and converted into 8 images. These 8 images were displayed as a result. This approach does not lead to over segmentation or under segmentation. We compared these results with well known Gray L...

  17. BW Trained HMM based Aerial Image Segmentation

    R Rajasree; J. Nalini; S C Ramesh


    Image segmentation is an essential preprocessing tread in a complicated and composite image dealing out algorithm. In segmenting arial image the expenditure of misclassification could depend on the factual group of pupils. In this paper, aggravated by modern advances in contraption erudition conjecture, I introduce a modus operandi to make light of the misclassification expenditure with class-dependent expenditure. The procedure assumes the hidden Markov model (HMM) which has been popularly u...


    Sourati, Jamshid; Brooks, Dana H.; Dy, Jennifer G.; Erdogmus, Deniz


    Constrained spectral clustering with affinity propagation in its original form is not practical for large scale problems like image segmentation. In this paper we employ novelty selection sub-sampling strategy, besides using efficient numerical eigen-decomposition methods to make this algorithm work efficiently for images. In addition, entropy-based active learning is also employed to select the queries posed to the user more wisely in an interactive image segmentation framework. We evaluate ...

  19. Enhancing the quality metric of protein microarray image

    王立强; 倪旭翔; 陆祖康; 郑旭峰; 李映笙


    The novel method of improving the quality metric of protein microarray image presented in this paper reduces impulse noise by using an adaptive median filter that employs the switching scheme based on local statistics characters; and achieves the impulse detection by using the difference between the standard deviation of the pixels within the filter window and the current pixel of concern. It also uses a top-hat filter to correct the background variation. In order to decrease time consumption, the top-hat filter core is cross structure. The experimental results showed that, for a protein microarray image contaminated by impulse noise and with slow background variation, the new method can significantly increase the signal-to-noise ratio, correct the trends in the background, and enhance the flatness of the background and the consistency of the signal intensity.

  20. Regression Segmentation for M³ Spinal Images.

    Wang, Zhijie; Zhen, Xiantong; Tay, KengYeow; Osman, Said; Romano, Walter; Li, Shuo


    Clinical routine often requires to analyze spinal images of multiple anatomic structures in multiple anatomic planes from multiple imaging modalities (M(3)). Unfortunately, existing methods for segmenting spinal images are still limited to one specific structure, in one specific plane or from one specific modality (S(3)). In this paper, we propose a novel approach, Regression Segmentation, that is for the first time able to segment M(3) spinal images in one single unified framework. This approach formulates the segmentation task innovatively as a boundary regression problem: modeling a highly nonlinear mapping function from substantially diverse M(3) images directly to desired object boundaries. Leveraging the advancement of sparse kernel machines, regression segmentation is fulfilled by a multi-dimensional support vector regressor (MSVR) which operates in an implicit, high dimensional feature space where M(3) diversity and specificity can be systematically categorized, extracted, and handled. The proposed regression segmentation approach was thoroughly tested on images from 113 clinical subjects including both disc and vertebral structures, in both sagittal and axial planes, and from both MRI and CT modalities. The overall result reaches a high dice similarity index (DSI) 0.912 and a low boundary distance (BD) 0.928 mm. With our unified and expendable framework, an efficient clinical tool for M(3) spinal image segmentation can be easily achieved, and will substantially benefit the diagnosis and treatment of spinal diseases.

  1. Image segmentation based on competitive learning

    ZHANG Jing; LIU Qun; Baikunth Nath


    Image segment is a primary step in image analysis of unexploded ordnance (UXO) detection by ground p enetrating radar (GPR) sensor which is accompanied with a lot of noises and other elements that affect the recognition of real target size. In this paper we bring forward a new theory, that is, we look the weight sets as target vector sets which is the new cues in semi-automatic segmentation to form the final image segmentation. The experiment results show that the measure size of target with our method is much smaller than the size with other methods and close to the real size of target.

  2. Segmentation-based CT image compression

    Thammineni, Arunoday; Mukhopadhyay, Sudipta; Kamath, Vidya


    The existing image compression standards like JPEG and JPEG 2000, compress the whole image as a single frame. This makes the system simple but inefficient. The problem is acute for applications where lossless compression is mandatory viz. medical image compression. If the spatial characteristics of the image are considered, it can give rise to a more efficient coding scheme. For example, CT reconstructed images have uniform background outside the field of view (FOV). Even the portion within the FOV can be divided as anatomically relevant and irrelevant parts. They have distinctly different statistics. Hence coding them separately will result in more efficient compression. Segmentation is done based on thresholding and shape information is stored using 8-connected differential chain code. Simple 1-D DPCM is used as the prediction scheme. The experiments show that the 1st order entropies of images fall by more than 11% when each segment is coded separately. For simplicity and speed of decoding Huffman code is chosen for entropy coding. Segment based coding will have an overhead of one table per segment but the overhead is minimal. Lossless compression of image based on segmentation resulted in reduction of bit rate by 7%-9% compared to lossless compression of whole image as a single frame by the same prediction coder. Segmentation based scheme also has the advantage of natural ROI based progressive decoding. If it is allowed to delete the diagnostically irrelevant portions, the bit budget can go down as much as 40%. This concept can be extended to other modalities.

  3. Scale selection for supervised image segmentation

    Li, Yan; Tax, David M J; Loog, Marco


    Finding the right scales for feature extraction is crucial for supervised image segmentation based on pixel classification. There are many scale selection methods in the literature; among them the one proposed by Lindeberg is widely used for image structures such as blobs, edges and ridges. Those...... schemes are usually unsupervised, as they do not take into account the actual segmentation problem at hand. In this paper, we consider the problem of selecting scales, which aims at an optimal discrimination between user-defined classes in the segmentation. We show the deficiency of the classical...... our approach back to Lindeberg's original proposal. In the experiments, the max rule is applied to artificial and real-world image segmentation tasks, which is shown to choose the right scales for different problems and lead to better segmentation results. © 2012 Elsevier B.V....

  4. Automatic tissue segmentation of breast biopsies imaged by QPI

    Majeed, Hassaan; Nguyen, Tan; Kandel, Mikhail; Marcias, Virgilia; Do, Minh; Tangella, Krishnarao; Balla, Andre; Popescu, Gabriel


    The current tissue evaluation method for breast cancer would greatly benefit from higher throughput and less inter-observer variation. Since quantitative phase imaging (QPI) measures physical parameters of tissue, it can be used to find quantitative markers, eliminating observer subjectivity. Furthermore, since the pixel values in QPI remain the same regardless of the instrument used, classifiers can be built to segment various tissue components without need for color calibration. In this work we use a texton-based approach to segment QPI images of breast tissue into various tissue components (epithelium, stroma or lumen). A tissue microarray comprising of 900 unstained cores from 400 different patients was imaged using Spatial Light Interference Microscopy. The training data were generated by manually segmenting the images for 36 cores and labelling each pixel (epithelium, stroma or lumen.). For each pixel in the data, a response vector was generated by the Leung-Malik (LM) filter bank and these responses were clustered using the k-means algorithm to find the centers (called textons). A random forest classifier was then trained to find the relationship between a pixel's label and the histogram of these textons in that pixel's neighborhood. The segmentation was carried out on the validation set by calculating the texton histogram in a pixel's neighborhood and generating a label based on the model learnt during training. Segmentation of the tissue into various components is an important step toward efficiently computing parameters that are markers of disease. Automated segmentation, followed by diagnosis, can improve the accuracy and speed of analysis leading to better health outcomes.

  5. FISICO: Fast Image SegmentatIon COrrection.

    Waldo Valenzuela

    Full Text Available In clinical diagnosis, medical image segmentation plays a key role in the analysis of pathological regions. Despite advances in automatic and semi-automatic segmentation techniques, time-effective correction tools are commonly needed to improve segmentation results. Therefore, these tools must provide faster corrections with a lower number of interactions, and a user-independent solution to reduce the time frame between image acquisition and diagnosis.We present a new interactive method for correcting image segmentations. Our method provides 3D shape corrections through 2D interactions. This approach enables an intuitive and natural corrections of 3D segmentation results. The developed method has been implemented into a software tool and has been evaluated for the task of lumbar muscle and knee joint segmentations from MR images.Experimental results show that full segmentation corrections could be performed within an average correction time of 5.5±3.3 minutes and an average of 56.5±33.1 user interactions, while maintaining the quality of the final segmentation result within an average Dice coefficient of 0.92±0.02 for both anatomies. In addition, for users with different levels of expertise, our method yields a correction time and number of interaction decrease from 38±19.2 minutes to 6.4±4.3 minutes, and 339±157.1 to 67.7±39.6 interactions, respectively.

  6. Visual Knowledge Representation and Intelligent Image Segmentation


    Automatic medical image analysis shows that image segmentation is a crucial task for any practical AI system in this field.On the basis of evaluation of the existing segmentation methods,a new image segmentation method is presented.To seek the perfct solution to knowledge representation in low level machine vision,a new knowledge representation approach--“Notebbok”approach is proposed and the processing of visual knowledge is discussed at all levels.To integrate the computer vision theory with Gestalt psychology and knowledge engineering,a new integrated method for intelligent image segmentation of sonargraphs- “Generalized-pattern guided segmentation”is proposed.With the methods and techniques mentioned above,the medical diagnosis expert system for sonargraphs can be built The work on the preliminary experiments is also introduced.

  7. Cluster Ensemble-based Image Segmentation

    Xiaoru Wang


    Full Text Available Image segmentation is the foundation of computer vision applications. In this paper, we propose a new\tcluster ensemble-based image\tsegmentation algorithm, which overcomes several problems of traditional methods. We make two main contributions in this paper. First, we introduce the cluster ensemble concept to fuse the segmentation results from different types of visual features effectively, which can deliver a better final result and achieve a much more stable performance for broad categories of images. Second, we exploit the PageRank idea from Internet applications and apply it to the image segmentation task. This can improve the final segmentation results by combining the spatial information of the image and the semantic similarity of regions. Our experiments on four public image databases validate the superiority of our algorithm over conventional single type of feature or multiple types of features-based algorithms, since our algorithm can fuse multiple types of features effectively for better segmentation results. Moreover, our method is also proved to be very competitive in comparison with other state-of-the-art segmentation algorithms.

  8. Review methods for image segmentation from computed tomography images

    Mamat, Nurwahidah; Rahman, Wan Eny Zarina Wan Abdul; Soh, Shaharuddin Cik [Faculty of Science Computer and Mathematics, Universiti Teknologi Mara Malaysia, 40450 Shah Alam Selangor (Malaysia); Mahmud, Rozi [Faculty of Medicine and Health Sciences, Universiti Putra Malaysia 43400 Serdang Selangor (Malaysia)


    Image segmentation is a challenging process in order to get the accuracy of segmentation, automation and robustness especially in medical images. There exist many segmentation methods that can be implemented to medical images but not all methods are suitable. For the medical purposes, the aims of image segmentation are to study the anatomical structure, identify the region of interest, measure tissue volume to measure growth of tumor and help in treatment planning prior to radiation therapy. In this paper, we present a review method for segmentation purposes using Computed Tomography (CT) images. CT images has their own characteristics that affect the ability to visualize anatomic structures and pathologic features such as blurring of the image and visual noise. The details about the methods, the goodness and the problem incurred in the methods will be defined and explained. It is necessary to know the suitable segmentation method in order to get accurate segmentation. This paper can be a guide to researcher to choose the suitable segmentation method especially in segmenting the images from CT scan.

  9. Semantic Image Segmentation with Contextual Hierarchical Models.

    Seyedhosseini, Mojtaba; Tasdizen, Tolga


    Semantic segmentation is the problem of assigning an object label to each pixel. It unifies the image segmentation and object recognition problems. The importance of using contextual information in semantic segmentation frameworks has been widely realized in the field. We propose a contextual framework, called contextual hierarchical model (CHM), which learns contextual information in a hierarchical framework for semantic segmentation. At each level of the hierarchy, a classifier is trained based on downsampled input images and outputs of previous levels. Our model then incorporates the resulting multi-resolution contextual information into a classifier to segment the input image at original resolution. This training strategy allows for optimization of a joint posterior probability at multiple resolutions through the hierarchy. Contextual hierarchical model is purely based on the input image patches and does not make use of any fragments or shape examples. Hence, it is applicable to a variety of problems such as object segmentation and edge detection. We demonstrate that CHM performs at par with state-of-the-art on Stanford background and Weizmann horse datasets. It also outperforms state-of-the-art edge detection methods on NYU depth dataset and achieves state-of-the-art on Berkeley segmentation dataset (BSDS 500).

  10. On image segmentation using information theoretic criteria

    Aue, Alexander; 10.1214/11-AOS925


    Image segmentation is a long-studied and important problem in image processing. Different solutions have been proposed, many of which follow the information theoretic paradigm. While these information theoretic segmentation methods often produce excellent empirical results, their theoretical properties are still largely unknown. The main goal of this paper is to conduct a rigorous theoretical study into the statistical consistency properties of such methods. To be more specific, this paper investigates if these methods can accurately recover the true number of segments together with their true boundaries in the image as the number of pixels tends to infinity. Our theoretical results show that both the Bayesian information criterion (BIC) and the minimum description length (MDL) principle can be applied to derive statistically consistent segmentation methods, while the same is not true for the Akaike information criterion (AIC). Numerical experiments were conducted to illustrate and support our theoretical fin...

  11. Natural color image segmentation using integrated mechanism

    Jie Xu (徐杰); Pengfei Shi (施鹏飞)


    A new method for natural color image segmentation using integrated mechanism is proposed in this paper.Edges are first detected in term of the high phase congruency in the gray-level image. K-mean cluster is used to label long edge lines based on the global color information to estimate roughly the distribution of objects in the image, while short ones are merged based on their positions and local color differences to eliminate the negative affection caused by texture or other trivial features in image. Region growing technique is employed to achieve final segmentation results. The proposed method unifies edges, whole and local color distributions, as well as spatial information to solve the natural image segmentation problem.The feasibility and effectiveness of this method have been demonstrated by various experiments.

  12. Automated detection of regions of interest for tissue microarray experiments: an image texture analysis

    Tözeren Aydin


    Full Text Available Abstract Background Recent research with tissue microarrays led to a rapid progress toward quantifying the expressions of large sets of biomarkers in normal and diseased tissue. However, standard procedures for sampling tissue for molecular profiling have not yet been established. Methods This study presents a high throughput analysis of texture heterogeneity on breast tissue images for the purpose of identifying regions of interest in the tissue for molecular profiling via tissue microarray technology. Image texture of breast histology slides was described in terms of three parameters: the percentage of area occupied in an image block by chromatin (B, percentage occupied by stroma-like regions (P, and a statistical heterogeneity index H commonly used in image analysis. Texture parameters were defined and computed for each of the thousands of image blocks in our dataset using both the gray scale and color segmentation. The image blocks were then classified into three categories using the texture feature parameters in a novel statistical learning algorithm. These categories are as follows: image blocks specific to normal breast tissue, blocks specific to cancerous tissue, and those image blocks that are non-specific to normal and disease states. Results Gray scale and color segmentation techniques led to identification of same regions in histology slides as cancer-specific. Moreover the image blocks identified as cancer-specific belonged to those cell crowded regions in whole section image slides that were marked by two pathologists as regions of interest for further histological studies. Conclusion These results indicate the high efficiency of our automated method for identifying pathologic regions of interest on histology slides. Automation of critical region identification will help minimize the inter-rater variability among different raters (pathologists as hundreds of tumors that are used to develop an array have typically been evaluated

  13. DISR: Dental Image Segmentation and Retrieval.

    Pilevar, Abdol Hamid


    In this paper, we propose novel algorithms for retrieving dental images from databases by their contents. Based on special information of dental images, for better content-based dental image retrieval and representation, the image attributes are used. We propose Dental Image Segmentation and Retrieval (DISR), a content-based image retrieval method that is robust to translation and scaling of the objects in the images. A novel model is used to calculate the features of the image. We implemented the dentition plaster casts and proposed a special technique for segmenting teeth in our dental study models. For testing the efficiency of the presented algorithm, a software system is developed and 60 dental study models are used. The models are covering different kinds of malocclusions. Our experiments show that 95% of the extracted results are accurate and the presented algorithm is efficient.

  14. An attribute-based image segmentation method

    M.C. de Andrade


    Full Text Available This work addresses a new image segmentation method founded on Digital Topology and Mathematical Morphology grounds. The ABA (attribute based absorptions transform can be viewed as a region-growing method by flooding simulation working at the scale of the main structures of the image. In this method, the gray level image is treated as a relief flooded from all its local minima, which are progressively detected and merged as the flooding takes place. Each local minimum is exclusively associated to one catchment basin (CB. The CBs merging process is guided by their geometric parameters as depth, area and/or volume. This solution enables the direct segmentation of the original image without the need of a preprocessing step or the explicit marker extraction step, often required by other flooding simulation methods. Some examples of image segmentation, employing the ABA transform, are illustrated for uranium oxide samples. It is shown that the ABA transform presents very good segmentation results even in presence of noisy images. Moreover, it's use is often easier and faster when compared to similar image segmentation methods.

  15. Self imaging in segmented waveguide arrays

    Heinrich, Matthias; Szameit, Alexander; Dreisow, Felix; Pertsch, Thomas; Nolte, Stefan; Tünnermann, Andreas; Suran, Eric; Louradour, Frédéric; Bathélémy, Alain; Longhi, Stefano


    Self-imaging in integrated optical devices is interesting for many applications including image transmission, optical collimation and even reshaping of ultrashort laser pulses. However, in general this relies on boundary-free light propagation, since interaction with boundaries results in a considerable distortion of the self-imaging effect. This problem can be overcome in waveguide arrays by segmentation of particular lattice sites, yielding phase shifts which result in image reconstruction in one- as well as two-dimensional configurations. Here, we demonstrate the first experimental realization of this concept. For the fabrication of the segmented waveguide arrays we used the femtosecond laser direct-writing technique. The total length of the arrays is 50mm with a waveguide spacing of 16 μm and 20μm in the one- and two-dimensional case, respectively. The length of the segmented area was 2.6mm, while the segmentation period was chosen to be 16 μm. This results in a complete inversion of the global phase of the travelling field inside the array, so that the evolution dynamics are reversed and the input field is imaged onto the sample output facet. Accordingly, segmented integrated optical devices provide a new and attractive opportunity for image transmission in finite systems.

  16. MRI Brain Image Segmentation based on Thresholding

    G. Evelin Sujji, Y.V.S. Lakshmi, G. Wiselin Jiji


    Full Text Available Medical Image processing is one of the mostchallenging topics in research field. The mainobjective of image segmentation is to extract variousfeatures of the image that are used foranalysing,interpretation and understanding of images.Medical Resonance Image plays a major role inMedical diagnostics. Image processing in MRI ofbrain is highlyessential due to accurate detection ofthe type of brain abnormality which can reduce thechance of fatal result. This paper outlines anefficient image segmentation technique that candistinguish the pathological tissues such asedemaandtumourfrom thenormal tissues such as WhiteMatter(WM,GreyMatter(GM, andCerebrospinal Fluid(CSF. Thresholding is simplerand most commonly used techniques in imagesegmentation. This technique can be used to detectthe contour of thetumourin brain.

  17. Image segmentation using neural tree networks

    Samaddar, Sumitro; Mammone, Richard J.


    We present a technique for Image Segmentation using Neural Tree Networks (NTN). We also modify the NTN architecture to let is solve multi-class classification problems with only binary fan-out. We have used a realistic case study of segmenting the pole, coil and painted coil regions of light bulb filaments (LBF). The input to the network is a set of maximum, minimum and average of intensities in radial slices of a circular window around a pixel, taken from a front-lit and a back-lit image of an LBF. Training is done with a composite image drawn from images of many LBFs. Each node of the NTN is a multi-layer perceptron and has one output for each segment class. These outputs are treated as probabilities to compute a confidence value for the segmentation of that pixel. Segmentation results with high confidence values are deemed to be correct and not processed further, while those with moderate and low confidence values are deemed to be outliers by this node and passed down the tree to children nodes. These tend to be pixels in boundary of different regions. The results are favorably compared with a traditional segmentation technique applied to the LBF test case.

  18. Neural tree network method for image segmentation

    Samaddar, Sumitro; Mammone, Richard J.


    We present an extension of the neural tree network (NTN) architecture to let it solve multi- class classification problems with only binary fan-out. We then demonstrate it's effectiveness by applying it in a method for image segmentation. Each node of the NTN is a multi-layer perceptron and has one output for each segment class. These outputs are treated as probabilities to compute a confidence value for the segmentation of that pixel. Segmentation results with high confidence values are deemed to be correct and not processed further, while those with moderate and low confidence values are deemed to be outliers by this node and passed down the tree to children nodes. These tend to be pixels in boundary of different regions. We have used a realistic case study of segmenting the pole, coil and painted coil regions of light bulb filaments (LBF). The input to the network is a set of maximum, minimum and average of intensities in radial slices of a circular window around a pixel, taken from a front-lit and a back-lit image of an LBF. Training is done with a composite image drawn from images of many LBFs. The results are favorably compared with a traditional segmentation technique applied to the LBF test case.

  19. Segmentation of elongated structures in medical images

    Staal, Jozef Johannes


    The research described in this thesis concerns the automatic detection, recognition and segmentation of elongated structures in medical images. For this purpose techniques have been developed to detect subdimensional pointsets (e.g. ridges, edges) in images of arbitrary dimension. These pointsets ar

  20. Intuitionistic fuzzy segmentation of medical images.

    Chaira, Tamalika


    This paper proposes a novel and probably the first method, using Attanassov intuitionistic fuzzy set theory to segment blood vessels and also the blood cells in pathological images. This type of segmentation is very important in detecting different types of human diseases, e.g., an increase in the number of vessels may lead to cancer in prostates, mammary, etc. The medical images are not properly illuminated, and segmentation in that case becomes very difficult. A novel image segmentation approach using intuitionistic fuzzy set theory and a new membership function is proposed using restricted equivalence function from automorphisms, for finding the membership values of the pixels of the image. An intuitionistic fuzzy image is constructed using Sugeno type intuitionistic fuzzy generator. Local thresholding is applied to threshold medical images. The results showed a much better performance on poor contrast medical images, where almost all the blood vessels and blood cells are visible properly. There are several fuzzy and intuitionistic fuzzy thresholding methods, but these methods are not related to the medical images. To make a comparison with the proposed method with other thresholding methods, the method is compared with six nonfuzzy, fuzzy, and intuitionistic fuzzy methods.

  1. Unsupervised image segmentation with neural networks

    Gieling, Th.H.; Janssen, H.J.J.; Vries, de H.C.; Loef, P.


    The segmentation of colour images (RGB), distinguishing clusters of image points, representing for example background, leaves and flowers, is performed in a multi-dimensional environment. Considering a two dimensional environment, clusters can be divided by lines. In a three dimensional environment


    Sourati, Jamshid; Brooks, Dana H.; Dy, Jennifer G.; Erdogmus, Deniz


    Constrained spectral clustering with affinity propagation in its original form is not practical for large scale problems like image segmentation. In this paper we employ novelty selection sub-sampling strategy, besides using efficient numerical eigen-decomposition methods to make this algorithm work efficiently for images. In addition, entropy-based active learning is also employed to select the queries posed to the user more wisely in an interactive image segmentation framework. We evaluate the algorithm on general and medical images to show that the segmentation results will improve using constrained clustering even if one works with a subset of pixels. Furthermore, this happens more efficiently when pixels to be labeled are selected actively. PMID:24466500

  3. Intravascular Ultrasound Image Segmentation Using Morphological Snakes

    Hamdi Mohamed Ali


    Full Text Available From the first use of the technics of intravascular ultrasound (IVUS as an imaging technique for the coronary artery system at the 70th century until now , the segmentation of the arterial wall boundaries still an important problem . Much research has been done to give better segmentation result for better diagnostics , evaluation and therapy planning. In this paper we present a new segmentation technics based on Morphological Snakes which developed by Luis Álvarez used for the first time for IVUS segmentation. It is a simple , fast and stable approach of snakes evolution algorithm. Results are presented and discussed in order to demonstrate the effectiveness of this approach in IVUS segmentation.

  4. Image Segmentation Using Weak Shape Priors

    Xu, Robert Sheng; Salama, Magdy


    The problem of image segmentation is known to become particularly challenging in the case of partial occlusion of the object(s) of interest, background clutter, and the presence of strong noise. To overcome this problem, the present paper introduces a novel approach segmentation through the use of "weak" shape priors. Specifically, in the proposed method, an segmenting active contour is constrained to converge to a configuration at which its geometric parameters attain their empirical probability densities closely matching the corresponding model densities that are learned based on training samples. It is shown through numerical experiments that the proposed shape modeling can be regarded as "weak" in the sense that it minimally influences the segmentation, which is allowed to be dominated by data-related forces. On the other hand, the priors provide sufficient constraints to regularize the convergence of segmentation, while requiring substantially smaller training sets to yield less biased results as compare...

  5. Evaluation for Uncertain Image Classification and Segmentation

    Martin, Arnaud; Arnold-Bos, Andreas


    Each year, numerous segmentation and classification algorithms are invented or reused to solve problems where machine vision is needed. Generally, the efficiency of these algorithms is compared against the results given by one or many human experts. However, in many situations, the location of the real boundaries of the objects as well as their classes are not known with certainty by the human experts. Furthermore, only one aspect of the segmentation and classification problem is generally evaluated. In this paper we present a new evaluation method for classification and segmentation of image, where we take into account both the classification and segmentation results as well as the level of certainty given by the experts. As a concrete example of our method, we evaluate an automatic seabed characterization algorithm based on sonar images.

  6. Optical image segmentation using wavelet filtering techniques

    Veronin, Christopher P.


    This research effort successfully implemented an automatic, optically based image segmentation scheme for locating potential targets in a cluttered FLIR image. Such a design is critical to achieve real-time segmentation and classification for machine vision applications. The segmentation scheme used in this research was based on texture discrimination and employs orientation specific, bandpass spatial filters as its main component. The orientation specific, bandpass spatial filters designed during this research include symmetrically located circular apertures implemented on heavy, black aluminum foil; cosine and sine Gabor filters implemented with detour-phase computer generated holography photoreduced onto glass slides; and symmetrically located circular apertures implemented on a liquid crystal television (LCTV) for real-time filter selection. The most successful design was the circular aperture pairs implemented on the aluminum foil. Segmentation was illustrated for simple and complex texture slides, glass template slides, and static and real-time FLIR imagery displayed on an LCTV.

  7. Dermoscopic Image Segmentation using Machine Learning Algorithm

    L. P. Suresh


    Full Text Available Problem statement: Malignant melanoma is the most frequent type of skin cancer. Its incidence has been rapidly increasing over the last few decades. Medical image segmentation is the most essential and crucial process in order to facilitate the characterization and visualization of the structure of interest in medical images. Approach: This study explains the task of segmenting skin lesions in Dermoscopy images based on intelligent systems such as Fuzzy and Neural Networks clustering techniques for the early diagnosis of Malignant Melanoma. The various intelligent system based clustering techniques used are Fuzzy C Means Algorithm (FCM, Possibilistic C Means Algorithm (PCM, Hierarchical C Means Algorithm (HCM; C-mean based Fuzzy Hopfield Neural Network, Adaline Neural Network and Regression Neural Network. Results: The segmented images are compared with the ground truth image using various parameters such as False Positive Error (FPE, False Negative Error (FNE Coefficient of similarity, spatial overlap and their performance is evaluated. Conclusion: The experimental results show that the Hierarchical C Means algorithm( Fuzzy provides better segmentation than other (Fuzzy C Means, Possibilistic C Means, Adaline Neural Network, FHNN and GRNN clustering algorithms. Thus Hierarchical C Means approach can handle uncertainties that exist in the data efficiently and useful for the lesion segmentation in a computer aided diagnosis system to assist the clinical diagnosis of dermatologists.

  8. BW Trained HMM based Aerial Image Segmentation

    R Rajasree


    Full Text Available Image segmentation is an essential preprocessing tread in a complicated and composite image dealing out algorithm. In segmenting arial image the expenditure of misclassification could depend on the factual group of pupils. In this paper, aggravated by modern advances in contraption erudition conjecture, I introduce a modus operandi to make light of the misclassification expenditure with class-dependent expenditure. The procedure assumes the hidden Markov model (HMM which has been popularly used for image segmentation in recent years. We represent all feasible HMM based segmenters (or classifiers as a set of points in the beneficiary operating characteristic (ROC space. optimizing HMM parameters is still an important and challenging work in automatic image segmentation research area. Usually the Baum-Welch (B-W Algorithm is used to calculate the HMM model parameters. However, the B-W algorithm uses an initial random guess of the parameters, therefore after convergence the output tends to be close to this initial value of the algorithm, which is not necessarily the global optimum of the model parameters. In this project, a Adaptive Baum-Welch (GA-BW is proposed.

  9. Segmentation and Classification of Burn Color Images


    2Grupo de Ingeniería Biomédica. Escuela Superior de Ingenieros. Universidad de Sevilla. Spain. e-mail:, aim of the algorithm described in this paper is to separate burned skin from normal skin in burn color images and to classify them...Segmentation Results To perform the segmentation, a previous characterization of the hue and saturation component histograms for both normal and burnt skin

  10. Video-based noncooperative iris image segmentation.

    Du, Yingzi; Arslanturk, Emrah; Zhou, Zhi; Belcher, Craig


    In this paper, we propose a video-based noncooperative iris image segmentation scheme that incorporates a quality filter to quickly eliminate images without an eye, employs a coarse-to-fine segmentation scheme to improve the overall efficiency, uses a direct least squares fitting of ellipses method to model the deformed pupil and limbic boundaries, and develops a window gradient-based method to remove noise in the iris region. A remote iris acquisition system is set up to collect noncooperative iris video images. An objective method is used to quantitatively evaluate the accuracy of the segmentation results. The experimental results demonstrate the effectiveness of this method. The proposed method would make noncooperative iris recognition or iris surveillance possible.


    Ms Maya Eapen


    Full Text Available Computed Tomography-Angiography (CTA images of the abdomen, followed by precise segmentation and subsequent computation of shape based features of liver play an important role in hepatic surgery, patient/donor diagnosis during liver transplantation and at various treatment stages. Nevertheless, the issues like intensity similarity and Partial Volume Effect (PVE between the neighboring organs; left the task of liver segmentation critical. The accurate segmentation of liver helps the surgeons to perfectly classify the patients based on their liver anatomy which in turn helps them in the treatment decision phase. In this study, we propose an effective Advanced Region Growing (ARG algorithm for segmentation of liver from CTA images. The performance of the proposed technique was tested with several CTA images acquired across a wide range of patients. The proposed ARG algorithm identifies the liver regions on the images based on the statistical features (intensity distribution and orientation value. The proposed technique addressed the aforementioned issues and been evaluated both quantitatively and qualitatively. For quantitative analysis proposed method was compared with manual segmentation (gold standard. The method was also compared with standard region growing.

  12. Remote Sensing Image Segmentation with Probabilistic Neural Networks

    LIU Gang


    This paper focuses on the image segmentation with probabilistic neural networks (PNNs). Back propagation neural networks (BpNNs) and multi perceptron neural networks (MLPs) are also considered in this study. Especially, this paper investigates the implementation of PNNs in image segmentation and optimal processing of image segmentation with a PNN. The comparison between image segmentations with PNNs and with other neural networks is given. The experimental results show that PNNs can be successfully applied to image segmentation for good results.

  13. Performance evaluation of image segmentation algorithms on microscopic image data.

    Beneš, Miroslav; Zitová, Barbara


    In our paper, we present a performance evaluation of image segmentation algorithms on microscopic image data. In spite of the existence of many algorithms for image data partitioning, there is no universal and 'the best' method yet. Moreover, images of microscopic samples can be of various character and quality which can negatively influence the performance of image segmentation algorithms. Thus, the issue of selecting suitable method for a given set of image data is of big interest. We carried out a large number of experiments with a variety of segmentation methods to evaluate the behaviour of individual approaches on the testing set of microscopic images (cross-section images taken in three different modalities from the field of art restoration). The segmentation results were assessed by several indices used for measuring the output quality of image segmentation algorithms. In the end, the benefit of segmentation combination approach is studied and applicability of achieved results on another representatives of microscopic data category - biological samples - is shown.

  14. Segmenting Images for a Better Diagnosis


    NASA's Hierarchical Segmentation (HSEG) software has been adapted by Bartron Medical Imaging, LLC, for use in segmentation feature extraction, pattern recognition, and classification of medical images. Bartron acquired licenses from NASA Goddard Space Flight Center for application of the HSEG concept to medical imaging, from the California Institute of Technology/Jet Propulsion Laboratory to incorporate pattern-matching software, and from Kennedy Space Center for data-mining and edge-detection programs. The Med-Seg[TM] united developed by Bartron provides improved diagnoses for a wide range of medical images, including computed tomography scans, positron emission tomography scans, magnetic resonance imaging, ultrasound, digitized Z-ray, digitized mammography, dental X-ray, soft tissue analysis, and moving object analysis. It also can be used in analysis of soft-tissue slides. Bartron's future plans include the application of HSEG technology to drug development. NASA is advancing it's HSEG software to learn more about the Earth's magnetosphere.

  15. Neural network segmentation of magnetic resonance images

    Frederick, Blaise


    Neural networks are well adapted to the task of grouping input patterns into subsets which share some similarity. Moreover once trained they can generalize their classification rules to classify new data sets. Sets of pixel intensities from magnetic resonance (MR) images provide a natural input to a neural network by varying imaging parameters MR images can reflect various independent physical parameters of tissues in their pixel intensities. A neural net can then be trained to classify physically similar tissue types based on sets of pixel intensities resulting from different imaging studies on the same subject. A neural network classifier for image segmentation was implemented on a Sun 4/60 and was tested on the task of classifying tissues of canine head MR images. Four images of a transaxial slice with different imaging sequences were taken as input to the network (three spin-echo images and an inversion recovery image). The training set consisted of 691 representative samples of gray matter white matter cerebrospinal fluid bone and muscle preclassified by a neuroscientist. The network was trained using a fast backpropagation algorithm to derive the decision criteria to classify any location in the image by its pixel intensities and the image was subsequently segmented by the classifier. The classifier''s performance was evaluated as a function of network size number of network layers and length of training. A single layer neural network performed quite well at


    Chen Xiaotang; Yu Yinglin


    This letter presents an efficient and simple image segmentation method for semantic object spatial segmentation. First, the image is filtered using contour-preserving filters. Then it is quasi-flat labeled. The small regions near the contour are classified as uncertain regions and are eliminated by region growing and merging. Further region merging is used to reduce the region number. The simulation results show its efficiency and simplicity. It can preserve the semantic object shape while emphasize on the perceptual complex part of the object. So it conforms to the human visual perception very well.


    ChenXiaotang; YuYinglin


    This letter presents an efficient and simple image segmentation method for semantic object spatial segmentation.First,the image is filtered using contour-preserving filters.Then it is quasi-flat labeled.The small regions near the contour are classified as uncertain regions and are eliminated by region growing and merging.Further region merging is used to reduce the region number.The simulation results show its efficiency and simplicity,It can preserve the semantic object shape while emphasize on the perceptual complex part of the object.So it conforms to the humann visual perception very well.

  18. Parallel fuzzy connected image segmentation on GPU

    Zhuge, Ying; Cao, Yong; Udupa, Jayaram K.; Miller, Robert W.


    Purpose: Image segmentation techniques using fuzzy connectedness (FC) principles have shown their effectiveness in segmenting a variety of objects in several large applications. However, one challenge in these algorithms has been their excessive computational requirements when processing large image datasets. Nowadays, commodity graphics hardware provides a highly parallel computing environment. In this paper, the authors present a parallel fuzzy connected image segmentation algorithm implementation on NVIDIA’s compute unified device Architecture (cuda) platform for segmenting medical image data sets. Methods: In the FC algorithm, there are two major computational tasks: (i) computing the fuzzy affinity relations and (ii) computing the fuzzy connectedness relations. These two tasks are implemented as cuda kernels and executed on GPU. A dramatic improvement in speed for both tasks is achieved as a result. Results: Our experiments based on three data sets of small, medium, and large data size demonstrate the efficiency of the parallel algorithm, which achieves a speed-up factor of 24.4x, 18.1x, and 10.3x, correspondingly, for the three data sets on the NVIDIA Tesla C1060 over the implementation of the algorithm on CPU, and takes 0.25, 0.72, and 15.04 s, correspondingly, for the three data sets. Conclusions: The authors developed a parallel algorithm of the widely used fuzzy connected image segmentation method on the NVIDIA GPUs, which are far more cost- and speed-effective than both cluster of workstations and multiprocessing systems. A near-interactive speed of segmentation has been achieved, even for the large data set. PMID:21859037

  19. Automatic segmentation of bladder in CT images

    Feng SHI; Jie YANG; Yue-min ZHU


    Segmentation of the bladder in computerized tomography (CT) images is an important step in radiation therapy planning of prostate cancer. We present a new segmentation scheme to automatically delineate the bladder contour in CT images with three major steps. First, we use the mean shift algorithm to obtain a clustered image containing the rough contour of the bladder, which is then extracted in the second step by applying a region-growing algorithm with the initial seed point selected from a line-by-line scanning process. The third step is to refine the bladder contour more accurately using the rolling-ball algorithm. These steps are then extended to segment the bladder volume in a slice-by-slice manner. The obtained results were compared to manual segmentation by radiation oncologists. The average values of sensitivity, specificity, positive predictive value, negative predictive value, and Hausdorff distance are 86.5%, 96.3%, 90.5%, 96.5%, and 2.8 pixels, respectively. The results show that the bladder can be accurately segmented.

  20. Noise Removal From Microarray Images Using Maximum a Posteriori Based Bivariate Estimator

    A.Sharmila Agnal


    Full Text Available Microarray Image contains information about thousands of genes in an organism and these images are affected by several types of noises. They affect the circular edges of spots and thus degrade the image quality. Hence noise removal is the first step of cDNA microarray image analysis for obtaining gene expression level and identifying the infected cells. The Dual Tree Complex Wavelet Transform (DT-CWT is preferred for denoising microarray images due to its properties like improved directional selectivity and near shift-invariance. In this paper, bivariate estimators namely Linear Minimum Mean Squared Error (LMMSE and Maximum A Posteriori (MAP derived by applying DT-CWT are used for denoising microarray images. Experimental results show that MAP based denoising method outperforms existing denoising techniques for microarray images.

  1. Text line Segmentation of Curved Document Images



    Full Text Available Document image analysis has been widely used in historical and heritage studies, education and digital library. Document image analytical techniques are mainly used for improving the human readability and the OCR quality of the document. During the digitization, camera captured images contain warped document due perspective and geometric distortions. The main difficulty is text line detection in the document. Many algorithms had been proposed to address the problem of printed document text line detection, but they failed to extract text lines in curved document. This paper describes a segmentation technique that detects the curled text line in camera captured document images.

  2. Field Sampling from a Segmented Image

    Debba, Pravesh


    Full Text Available Image Debba, Stein, van der Meer, Carranza, Lucieer Objective Study Site Methods The ICM Algorithm Sampling Per Category Sample Size Per Category Fitness Function Per Category Simulated Annealing Per Category Results Experiment Case... Study Conclusions Field Sampling from a Segmented Image P. Debba1 A. Stein2 F.D. van der Meer2 E.J.M. Carranza2 A. Lucieer3 1The Council for Scientific and Industrial Research (CSIR), Logistics and Quantitative Methods, CSIR Built Environment, P...

  3. Quantitative color analysis for capillaroscopy image segmentation.

    Goffredo, Michela; Schmid, Maurizio; Conforto, Silvia; Amorosi, Beatrice; D'Alessio, Tommaso; Palma, Claudio


    This communication introduces a novel approach for quantitatively evaluating the role of color space decomposition in digital nailfold capillaroscopy analysis. It is clinically recognized that any alterations of the capillary pattern, at the periungual skin region, are directly related to dermatologic and rheumatic diseases. The proposed algorithm for the segmentation of digital capillaroscopy images is optimized with respect to the choice of the color space and the contrast variation. Since the color space is a critical factor for segmenting low-contrast images, an exhaustive comparison between different color channels is conducted and a novel color channel combination is presented. Results from images of 15 healthy subjects are compared with annotated data, i.e. selected images approved by clinicians. By comparison, a set of figures of merit, which highlights the algorithm capability to correctly segment capillaries, their shape and their number, is extracted. Experimental tests depict that the optimized procedure for capillaries segmentation, based on a novel color channel combination, presents values of average accuracy higher than 0.8, and extracts capillaries whose shape and granularity are acceptable. The obtained results are particularly encouraging for future developments on the classification of capillary patterns with respect to dermatologic and rheumatic diseases.

  4. An algorithm of image segmentation for overlapping grain image

    WANG Zhi; JIN Guang; SUN Xiao-wei


    Aiming at measurement of granularity size of nonmetal grain, an algorithm of image segmentation and parameter calculation for microscopic overlapping grain image was studied. This algorithm presents some new attributes of graph sequence from discrete attribute of graph,and consequently achieves the geometrical characteristics from input graph, and the new graph sequence in favor of image segmentation is recombined. The conception that image edge denoted with "twin-point" is put forward, base on geometrical characters of point, image edge is transformed into serial edge, and on recombined serial image edge, based on direction vector definition of line and some additional restricted conditions, the segmentation twin-points are searched with, thus image segmentation is accomplished. Serial image edge is transformed into twin-point pattern, to realize calculation of area and granularity size of nonmetal grain. The inkling and uncertainty on selection of structure element which base on mathematical morphology are avoided in this algorithm, and image segmentation and parameter calculation are realized without changing grain's self statistical characters.

  5. Medical image segmentation using improved FCM

    ZHANG XiaoFeng; ZHANG CaiMing; TANG WenJing; WEI ZhenWen


    Image segmentation is one of the most important problems in medical image processing,and the existence of partial volume effect and other phenomena makes the problem much more complex. Fuzzy Cmeans,as an effective tool to deal with PVE,however,is faced with great challenges in efficiency.Aiming at this,this paper proposes one improved FCM algorithm based on the histogram of the given image,which will be denoted as HisFCM and divided into two phases.The first phase will retrieve several intervals on which to compute cluster centroids,and the second one will perform image segmentation based on improved FCM algorithm.Compared with FCM and other improved algorithms,HisFCM is of much higher efficiency with satisfying results.Experiments on medical images show that HisFCM can achieve good segmentation results in less than 0.1 second,and can satisfy real-time requirements of medical image processing.

  6. Polynomial-time solutions to image segmentation

    Asano, Tetsuo [Osaka Electro-Communication Univ., Neyagawa (Japan); Chen, D.Z. [Notre Dame, South Bend, IN (United States); Katoh, Naoki [Kobe Univ. of Commerce (Japan)


    Separating an object in an image from its background is a central problem (called segmentation) in pattern recognition and computer vision. In this paper, we study the complexity of the segmentation problem, assuming that the object forms a connected region in an intensity image. We show that the optimization problem of separating a connected region in an n-pixel grid is NP-hard under the interclass variance, a criterion that is used in discriminant analysis. More importantly, we consider the basic case in which the object is separated by two x-monotone curves (i.e., the object itself is x-monotone), and present polynomial-time algorithms for computing exact and approximate optimal segmentation. Our main algorithm for exact optimal segmentation by two x-monotone curves runs in O(n{sup 2}) time; this algorithm is based on several techniques such as a parametric optimization formulation, a hand-probing algorithm for the convex hull of an unknown point set, and dynamic programming using fast matrix searching. Our efficient approximation scheme obtains an {epsilon}-approximate solution in O({epsilon}{sup -1} n log L) time, where {epsilon} is any fixed constant with 1 > {epsilon} > 0, and L is the total sum of the absolute values of brightness levels of the image.

  7. Mammographic images segmentation using texture descriptors.

    Mascaro, Angelica A; Mello, Carlos A B; Santos, Wellington P; Cavalcanti, George D C


    Tissue classification in mammography can help the diagnosis of breast cancer by separating healthy tissue from lesions. We present herein the use of three texture descriptors for breast tissue segmentation purposes: the Sum Histogram, the Gray Level Co-Occurrence Matrix (GLCM) and the Local Binary Pattern (LBP). A modification of the LBP is also proposed for a better distinction of the tissues. In order to segment the image into its tissues, these descriptors are compared using a fidelity index and two clustering algorithms: k-Means and SOM (Self-Organizing Maps).

  8. Segmentation Toolbox for Tomographic Image Data

    Einarsdottir, Hildur

    , techniques to automatically analyze such data becomes ever more important. Most segmentation methods for large datasets, such as CT images, deal with simple thresholding techniques, where intensity values cut offs are predetermined and hard coded. For data where the intensity difference is not sufficient...... to automatically determine parameters of the different classes present in the data, and edge weighted smoothing of the final segmentation based on Markov Random Fields (MRF). The toolbox is developed for Matlab users and requires only minimal background knowledge of Matlab....

  9. Unimodal transform of variables selected by interval segmentation purity for classification tree modeling of high-dimensional microarray data.

    Du, Wen; Gu, Ting; Tang, Li-Juan; Jiang, Jian-Hui; Wu, Hai-Long; Shen, Guo-Li; Yu, Ru-Qin


    As a greedy search algorithm, classification and regression tree (CART) is easily relapsing into overfitting while modeling microarray gene expression data. A straightforward solution is to filter irrelevant genes via identifying significant ones. Considering some significant genes with multi-modal expression patterns exhibiting systematic difference in within-class samples are difficult to be identified by existing methods, a strategy that unimodal transform of variables selected by interval segmentation purity (UTISP) for CART modeling is proposed. First, significant genes exhibiting varied expression patterns can be properly identified by a variable selection method based on interval segmentation purity. Then, unimodal transform is implemented to offer unimodal featured variables for CART modeling via feature extraction. Because significant genes with complex expression patterns can be properly identified and unimodal feature extracted in advance, this developed strategy potentially improves the performance of CART in combating overfitting or underfitting while modeling microarray data. The developed strategy is demonstrated using two microarray data sets. The results reveal that UTISP-based CART provides superior performance to k-nearest neighbors or CARTs coupled with other gene identifying strategies, indicating UTISP-based CART holds great promise for microarray data analysis.

  10. Segmentation of Medical Image using Clustering and Watershed Algorithms

    M. C.J. Christ; R.M.S Parvathi


    Problem statement: Segmentation plays an important role in medical imaging. Segmentation of an image is the division or separation of the image into dissimilar regions of similar attribute. In this study we proposed a methodology that integrates clustering algorithm and marker controlled watershed segmentation algorithm for medical image segmentation. The use of the conservative watershed algorithm for medical image analysis is pervasive because of its advantages, such as always being able to...

  11. A comparative study on medical image segmentation methods

    Praylin Selva Blessy SELVARAJ ASSLEY; Helen Sulochana CHELLAKKON


    Image segmentation plays an important role in medical images. It has been a relevant research area in computer vision and image analysis. Many segmentation algorithms have been proposed for medical images. This paper makes a review on segmentation methods for medical images. In this survey, segmentation methods are divided into five categories: region based, boundary based, model based, hybrid based and atlas based. The five different categories with their principle ideas, advantages and disa...

  12. Image quality, compression and segmentation in medicine.

    Morgan, Pam; Frankish, Clive


    This review considers image quality in the context of the evolving technology of image compression, and the effects image compression has on perceived quality. The concepts of lossless, perceptually lossless, and diagnostically lossless but lossy compression are described, as well as the possibility of segmented images, combining lossy compression with perceptually lossless regions of interest. The different requirements for diagnostic and training images are also discussed. The lack of established methods for image quality evaluation is highlighted and available methods discussed in the light of the information that may be inferred from them. Confounding variables are also identified. Areas requiring further research are illustrated, including differences in perceptual quality requirements for different image modalities, image regions, diagnostic subtleties, and tasks. It is argued that existing tools for measuring image quality need to be refined and new methods developed. The ultimate aim should be the development of standards for image quality evaluation which take into consideration both the task requirements of the images and the acceptability of the images to the users.

  13. A Survey on Image Segmentation Techniques Used In Leukemia Detection

    Mashiat Fatma


    Full Text Available Image segmentation commonly known as partitioning of an image is one of the intrinsic parts of any image processing technique. In this image processing step, the digital image of choice is segregated into sets of pixels on the basis of some predefined and preselected measures or standards. There have been presented many algorithms for segmenting a digital image. This paper presents a general review of algorithms that have been presented for the purpose of image segmentation.

  14. Automatic segmentation of mammogram and tomosynthesis images

    Sargent, Dusty; Park, Sun Young


    Breast cancer is a one of the most common forms of cancer in terms of new cases and deaths both in the United States and worldwide. However, the survival rate with breast cancer is high if it is detected and treated before it spreads to other parts of the body. The most common screening methods for breast cancer are mammography and digital tomosynthesis, which involve acquiring X-ray images of the breasts that are interpreted by radiologists. The work described in this paper is aimed at optimizing the presentation of mammography and tomosynthesis images to the radiologist, thereby improving the early detection rate of breast cancer and the resulting patient outcomes. Breast cancer tissue has greater density than normal breast tissue, and appears as dense white image regions that are asymmetrical between the breasts. These irregularities are easily seen if the breast images are aligned and viewed side-by-side. However, since the breasts are imaged separately during mammography, the images may be poorly centered and aligned relative to each other, and may not properly focus on the tissue area. Similarly, although a full three dimensional reconstruction can be created from digital tomosynthesis images, the same centering and alignment issues can occur for digital tomosynthesis. Thus, a preprocessing algorithm that aligns the breasts for easy side-by-side comparison has the potential to greatly increase the speed and accuracy of mammogram reading. Likewise, the same preprocessing can improve the results of automatic tissue classification algorithms for mammography. In this paper, we present an automated segmentation algorithm for mammogram and tomosynthesis images that aims to improve the speed and accuracy of breast cancer screening by mitigating the above mentioned problems. Our algorithm uses information in the DICOM header to facilitate preprocessing, and incorporates anatomical region segmentation and contour analysis, along with a hidden Markov model (HMM) for

  15. Image segmentation with a unified graphical model.

    Zhang, Lei; Ji, Qiang


    We propose a unified graphical model that can represent both the causal and noncausal relationships among random variables and apply it to the image segmentation problem. Specifically, we first propose to employ Conditional Random Field (CRF) to model the spatial relationships among image superpixel regions and their measurements. We then introduce a multilayer Bayesian Network (BN) to model the causal dependencies that naturally exist among different image entities, including image regions, edges, and vertices. The CRF model and the BN model are then systematically and seamlessly combined through the theories of Factor Graph to form a unified probabilistic graphical model that captures the complex relationships among different image entities. Using the unified graphical model, image segmentation can be performed through a principled probabilistic inference. Experimental results on the Weizmann horse data set, on the VOC2006 cow data set, and on the MSRC2 multiclass data set demonstrate that our approach achieves favorable results compared to state-of-the-art approaches as well as those that use either the BN model or CRF model alone.

  16. Transfer learning improves supervised image segmentation across imaging protocols

    van Opbroek, Annegreet; Ikram, M. Arfan; Vernooij, Meike W.;


    well, often require a large amount of labeled training data that is exactly representative of the target data. We therefore propose to use transfer learning for image segmentation. Transfer-learning techniques can cope with differences in distributions between training and target data, and therefore......The variation between images obtained with different scanners or different imaging protocols presents a major challenge in automatic segmentation of biomedical images. This variation especially hampers the application of otherwise successful supervised-learning techniques which, in order to perform...... may improve performance over supervised learning for segmentation across scanners and scan protocols. We present four transfer classifiers that can train a classification scheme with only a small amount of representative training data, in addition to a larger amount of other training data...

  17. Image Segmentation, Registration, Compression, and Matching

    Yadegar, Jacob; Wei, Hai; Yadegar, Joseph; Ray, Nilanjan; Zabuawala, Sakina


    A novel computational framework was developed of a 2D affine invariant matching exploiting a parameter space. Named as affine invariant parameter space (AIPS), the technique can be applied to many image-processing and computer-vision problems, including image registration, template matching, and object tracking from image sequence. The AIPS is formed by the parameters in an affine combination of a set of feature points in the image plane. In cases where the entire image can be assumed to have undergone a single affine transformation, the new AIPS match metric and matching framework becomes very effective (compared with the state-of-the-art methods at the time of this reporting). No knowledge about scaling or any other transformation parameters need to be known a priori to apply the AIPS framework. An automated suite of software tools has been created to provide accurate image segmentation (for data cleaning) and high-quality 2D image and 3D surface registration (for fusing multi-resolution terrain, image, and map data). These tools are capable of supporting existing GIS toolkits already in the marketplace, and will also be usable in a stand-alone fashion. The toolkit applies novel algorithmic approaches for image segmentation, feature extraction, and registration of 2D imagery and 3D surface data, which supports first-pass, batched, fully automatic feature extraction (for segmentation), and registration. A hierarchical and adaptive approach is taken for achieving automatic feature extraction, segmentation, and registration. Surface registration is the process of aligning two (or more) data sets to a common coordinate system, during which the transformation between their different coordinate systems is determined. Also developed here are a novel, volumetric surface modeling and compression technique that provide both quality-guaranteed mesh surface approximations and compaction of the model sizes by efficiently coding the geometry and connectivity

  18. Heat Equation to 3D Image Segmentation

    Nikolay Sirakov


    Full Text Available This paper presents a new approach, capable of 3D image segmentation and objects' surface reconstruction. The main advantages of the method are: large capture range; quick segmentation of a 3D scene/image to regions; multiple 3D objects reconstruction. The method uses centripetal force and penalty function to segment the entire 3D scene/image to regions containing a single 3D object. Each region is inscribed in a convex, smooth closed surface, which defines a centripetal force. Then the surface is evolved by the geometric heat differential equation toward the force's direction. The penalty function is defined to stop evolvement of those surface patches, whose normal vectors encountered object's surface. On the base of the theoretical model Forward Difference Algorithm was developed and coded by Mathematica. Stability convergence condition, truncation error and calculation complexity of the algorithm are determined. The obtained results, advantages and disadvantages of the method are discussed at the end of this paper.

  19. A comparative study on medical image segmentation methods

    Praylin Selva Blessy SELVARAJ ASSLEY


    Full Text Available Image segmentation plays an important role in medical images. It has been a relevant research area in computer vision and image analysis. Many segmentation algorithms have been proposed for medical images. This paper makes a review on segmentation methods for medical images. In this survey, segmentation methods are divided into five categories: region based, boundary based, model based, hybrid based and atlas based. The five different categories with their principle ideas, advantages and disadvantages in segmenting different medical images are discussed.

  20. An Improved Image Segmentation Based on Mean Shift Algorithm

    CHENHanfeng; QIFeihu


    Gray image segmentation is to segment an image into some homogeneous regions and only one gray level is defined for each region as the result. These grayl evels are called major gray levels. Mean shift algorithm(MSA) has shown its efficiency in image segmentation. An improved gray image segmentation method based on MSAis proposed in this paper since usual image segmentation methods based on MSA often fail in segmenting imageswith weak edges. Corrupted block and its J-value are defined firstly in the proposed method. Then, J-matrix gotten from corrupted blocks are proposed to measure whether weak edges appear in the image. According to the J-matrix, major gray levels gotten with usual segmen-tation methods based on MSA are augmented and corre-sponding allocation windows are modified to detect weak edges. Experimental results demonstrate the effectiveness of the proposed method in gray image segmentation.

  1. Automatic Vessel Segmentation on Retinal Images

    Chun-Yuan Yu; Chia-Jen Chang; Yen-Ju Yao; Shyr-Shen Yu


    Several features of retinal vessels can be used to monitor the progression of diseases. Changes in vascular structures, for example, vessel caliber, branching angle, and tortuosity, are portents of many diseases such as diabetic retinopathy and arterial hyper-tension. This paper proposes an automatic retinal vessel segmentation method based on morphological closing and multi-scale line detection. First, an illumination correction is performed on the green band retinal image. Next, the morphological closing and subtraction processing are applied to obtain the crude retinal vessel image. Then, the multi-scale line detection is used to fine the vessel image. Finally, the binary vasculature is extracted by the Otsu algorithm. In this paper, for improving the drawbacks of multi-scale line detection, only the line detectors at 4 scales are used. The experimental results show that the accuracy is 0.939 for DRIVE (digital retinal images for vessel extraction) retinal database, which is much better than other methods.

  2. Image segmentation using association rule features.

    Rushing, John A; Ranganath, Heggere; Hinke, Thomas H; Graves, Sara J


    A new type of texture feature based on association rules is described. Association rules have been used in applications such as market basket analysis to capture relationships present among items in large data sets. It is shown that association rules can be adapted to capture frequently occurring local structures in images. The frequency of occurrence of these structures can be used to characterize texture. Methods for segmentation of textured images based on association rule features are described. Simulation results using images consisting of man made and natural textures show that association rule features perform well compared to other widely used texture features. Association rule features are used to detect cumulus cloud fields in GOES satellite images and are found to achieve higher accuracy than other statistical texture features for this problem.

  3. Advanced numerical methods for image denoising and segmentation

    Liu, Xiaoyang


    Image denoising is one of the most major steps in current image processing. It is a pre-processing step which aims to remove certain unknown, random noise from an image and obtain an image free of noise for further image processing, such as image segmentation. Image segmentation, as another branch of image processing, plays a significant role in connecting low-level image processing and high-level image processing. Its goal is to segment an image into different parts and extract meaningful in...

  4. Optimal retinal cyst segmentation from OCT images

    Oguz, Ipek; Zhang, Li; Abramoff, Michael D.; Sonka, Milan


    Accurate and reproducible segmentation of cysts and fluid-filled regions from retinal OCT images is an important step allowing quantification of the disease status, longitudinal disease progression, and response to therapy in wet-pathology retinal diseases. However, segmentation of fluid-filled regions from OCT images is a challenging task due to their inhomogeneous appearance, the unpredictability of their number, size and location, as well as the intensity profile similarity between such regions and certain healthy tissue types. While machine learning techniques can be beneficial for this task, they require large training datasets and are often over-fitted to the appearance models of specific scanner vendors. We propose a knowledge-based approach that leverages a carefully designed cost function and graph-based segmentation techniques to provide a vendor-independent solution to this problem. We illustrate the results of this approach on two publicly available datasets with a variety of scanner vendors and retinal disease status. Compared to a previous machine-learning based approach, the volume similarity error was dramatically reduced from 81:3+/-56:4% to 22:2+/-21:3% (paired t-test, p << 0:001).

  5. Embedded Implementation of VHR Satellite Image Segmentation.

    Li, Chao; Balla-Arabé, Souleymane; Ginhac, Dominique; Yang, Fan


    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.

  6. Text segmentation in degraded historical document images

    A.S. Kavitha


    Full Text Available Text segmentation from degraded Historical Indus script images helps Optical Character Recognizer (OCR to achieve good recognition rates for Hindus scripts; however, it is challenging due to complex background in such images. In this paper, we present a new method for segmenting text and non-text in Indus documents based on the fact that text components are less cursive compared to non-text ones. To achieve this, we propose a new combination of Sobel and Laplacian for enhancing degraded low contrast pixels. Then the proposed method generates skeletons for text components in enhanced images to reduce computational burdens, which in turn helps in studying component structures efficiently. We propose to study the cursiveness of components based on branch information to remove false text components. The proposed method introduces the nearest neighbor criterion for grouping components in the same line, which results in clusters. Furthermore, the proposed method classifies these clusters into text and non-text cluster based on characteristics of text components. We evaluate the proposed method on a large dataset containing varieties of images. The results are compared with the existing methods to show that the proposed method is effective in terms of recall and precision.

  7. Multiphase Image Segmentation Using the Deformable Simplicial Complex Method

    Dahl, Vedrana Andersen; Christiansen, Asger Nyman; Bærentzen, Jakob Andreas


    The deformable simplicial complex method is a generic method for tracking deformable interfaces. It provides explicit interface representation, topological adaptivity, and multiphase support. As such, the deformable simplicial complex method can readily be used for representing active contours...... in image segmentation based on deformable models. We show the benefits of using the deformable simplicial complex method for image segmentation by segmenting an image into a known number of segments characterized by distinct mean pixel intensities....

  8. Histological image segmentation using fast mean shift clustering method

    Wu, Geming; Zhao, Xinyan; Luo, Shuqian; Shi, Hongli


    Background Colour image segmentation is fundamental and critical for quantitative histological image analysis. The complexity of the microstructure and the approach to make histological images results in variable staining and illumination variations. And ultra-high resolution of histological images makes it is hard for image segmentation methods to achieve high-quality segmentation results and low computation cost at the same time. Methods Mean Shift clustering approach is employed for histol...

  9. Unsupervised Multiresolution Image Segmentation Integrating Color and Texture

    XINGQiang; YUANBaozong; TANGXiaofang


    Unsupervised segmentation of images is highly useful in various applications including contentbased image retrieval. A novel multiresolution image segmentation algorithm, designed to separate a focused object of interest from background automatically, is described in this paper. According to the principle of human vision system, our algorithm first searches the salient block representing object in global image domain. Then all image blocks are clustered using the feature of color moments and texture in salient block. At last the algorithm classifies the image blocks belonging to object class in high resolution. Experiment shows that our algorithm achieves better segmentation results at higher speed compared with the traditional image segmentation approach using global optimization.

  10. Segmentation of moving images by the human visual system.

    Chantelau, K


    New segments appearing in an image sequence or spontaneously accelerated segments are band limited by the visual system due to a nonperfect tracking of these segments by eye movements. In spite of this band limitation and acceleration of segments, a coarse segmentation (initial segmentation phase) can be performed by the visual system. This is interesting for the development of purely automatic segmentation algorithms for multimedia applications. In this paper the segmentation of the visual system is modelled and used in an automatic coarse initial segmentation. A suitable model for motion processing based on a spectral representation is presented and applied to the segmentation of synthetic and real image sequences with band limited and accelerated moving foreground and background segments.

  11. Underwater color image segmentation method via RGB channel fusion

    Xuan, Li; Mingjun, Zhang


    Aiming at the problem of low segmentation accuracy and high computation time by applying existing segmentation methods for underwater color images, this paper has proposed an underwater color image segmentation method via RGB color channel fusion. Based on thresholding segmentation methods to conduct fast segmentation, the proposed method relies on dynamic estimation of the optimal weights for RGB channel fusion to obtain the grayscale image with high foreground-background contrast and reaches high segmentation accuracy. To verify the segmentation accuracy of the proposed method, the authors have conducted various underwater comparative experiments. The experimental results demonstrate that the proposed method is robust to illumination, and it is superior to existing methods in terms of both segmentation accuracy and computation time. Moreover, a segmentation technique is proposed for image sequences for real-time autonomous underwater vehicle operations.

  12. Automatic segmentation of seven retinal layers in SDOCT images congruent with expert manual segmentation.

    Chiu, Stephanie J; Li, Xiao T; Nicholas, Peter; Toth, Cynthia A; Izatt, Joseph A; Farsiu, Sina


    Segmentation of anatomical and pathological structures in ophthalmic images is crucial for the diagnosis and study of ocular diseases. However, manual segmentation is often a time-consuming and subjective process. This paper presents an automatic approach for segmenting retinal layers in Spectral Domain Optical Coherence Tomography images using graph theory and dynamic programming. Results show that this method accurately segments eight retinal layer boundaries in normal adult eyes more closely to an expert grader as compared to a second expert grader.

  13. Improved detection of differentially expressed genes in microarray experiments through multiple scanning and image integration

    Romualdi, Chiara; Trevisan, Silvia; Celegato, Barbara; Costa, Germano; Lanfranchi, Gerolamo


    The variability of results in microarray technology is in part due to the fact that independent scans of a single hybridised microarray give spot images that are not quite the same. To solve this problem and turn it to our advantage, we introduced the approach of multiple scanning and of image integration of microarrays. To this end, we have developed specific software that creates a virtual image that statistically summarises a series of consecutive scans of a microarray. We provide evidence that the use of multiple imaging (i) enhances the detection of differentially expressed genes; (ii) increases the image homogeneity; and (iii) reveals false-positive results such as differentially expressed genes that are detected by a single scan but not confirmed by successive scanning replicates. The increase in the final number of differentially expressed genes detected in a microarray experiment with this approach is remarkable; 50% more for microarrays hybridised with targets labelled by reverse transcriptase, and 200% more for microarrays developed with the tyramide signal amplification (TSA) technique. The results have been confirmed by semi-quantitative RT–PCR tests. PMID:14627839

  14. A Semantic Connected Coherence Scheme for Efficient Image Segmentation



    Full Text Available Image processing is a comprehensively research topic with an elongated history. Segmenting an image is the most challenging and difficult task in image processing and analysis. The principal intricacy met in image segmentation is the ability of techniques to discover semantic objects efficiently from an image without any prior knowledge. One recent work presented connected coherence tree algorithm (CCTA for image segmentation (with no prior knowledge which discovered regions of semantic coherence based on neighbor coherence segmentation criteria. It deployed an adaptive spatial scale and a suitable intensity-difference scale to extract several sets of coherent neighboring pixels and maximize the probability of single image content and minimize complex backgrounds. However CCTA segmented images either consists of small, lengthy and slender objects or rigorously ruined by noise, irregular lighting, occlusion, poor illumination, and shadow.In this paper, we present a Cluster based Semantic Coherent Tree (CBSCT scheme for image segmentation. CBSCT’s initial work is on the semantic connected coherence criteria for the image segregation. Semantic coherent regions are clustered based on Bayesian nearest neighbor search of neighborhood pixels. The segmentation regions are extracted from the images based on the cluster object purity obtained through semantic coherent regions. The clustered image regions are post processed with non linear noise filters. Performance metrics used in the evaluation of CBSCT are semantic coherent pixel size, number of cluster objects, and purity levels of the cluster, segmented coherent region intensity threshold, and quality of segmented images in terms of image clarity with PSNR.

  15. FPGA based system for automatic cDNA microarray image processing.

    Belean, Bogdan; Borda, Monica; Le Gal, Bertrand; Terebes, Romulus


    Automation is an open subject in DNA microarray image processing, aiming reliable gene expression estimation. The paper presents a novel shock filter based approach for automatic microarray grid alignment. The proposed method brings up significantly reduced computational complexity compared to state of the art approaches, while similar results in terms of accuracy are achieved. Based on this approach, we also propose an FPGA based system for microarray image analysis that eliminates the shortcomings of existing software platforms: user intervention, increased computational time and cost. Our system includes application-specific architectures which involve algorithm parallelization, aiming fast and automated cDNA microarray image processing. The proposed automated image processing chain is implemented both on a general purpose processor and using the developed hardware architectures as co-processors in a FPGA based system. The comparative results included in the last section show that an important gain in terms of computational time is obtained using hardware based implementations.

  16. Hierarchical Non-linear Image Registration Integrating Deformable Segmentation

    RAN Xin; QI Fei-hu


    A hierarchical non-linear method for image registration was presented, which integrates image segmentation and registration under a variational framework. An improved deformable model is used to simultaneously segment and register feature from multiple images. The objects in the image pair are segmented by evolving a single contour and meanwhile the parameters of affine registration transformation are found out. After that, a contour-constrained elastic registration is applied to register the images correctly. The experimental results indicate that the proposed approach is effective to segment and register medical images.

  17. Image microarrays derived from tissue microarrays (IMA-TMA: New resource for computer-aided diagnostic algorithm development

    Jennifer A Hipp


    Full Text Available Background: Conventional tissue microarrays (TMAs consist of cores of tissue inserted into a recipient paraffin block such that a tissue section on a single glass slide can contain numerous patient samples in a spatially structured pattern. Scanning TMAs into digital slides for subsequent analysis by computer-aided diagnostic (CAD algorithms all offers the possibility of evaluating candidate algorithms against a near-complete repertoire of variable disease morphologies. This parallel interrogation approach simplifies the evaluation, validation, and comparison of such candidate algorithms. A recently developed digital tool, digital core (dCORE, and image microarray maker (iMAM enables the capture of uniformly sized and resolution-matched images, with these representing key morphologic features and fields of view, aggregated into a single monolithic digital image file in an array format, which we define as an image microarray (IMA. We further define the TMA-IMA construct as IMA-based images derived from whole slide images of TMAs themselves. Methods: Here we describe the first combined use of the previously described dCORE and iMAM tools, toward the goal of generating a higher-order image construct, with multiple TMA cores from multiple distinct conventional TMAs assembled as a single digital image montage. This image construct served as the basis of the carrying out of a massively parallel image analysis exercise, based on the use of the previously described spatially invariant vector quantization (SIVQ algorithm. Results: Multicase, multifield TMA-IMAs of follicular lymphoma and follicular hyperplasia were separately rendered, using the aforementioned tools. Each of these two IMAs contained a distinct spectrum of morphologic heterogeneity with respect to both tingible body macrophage (TBM appearance and apoptotic body morphology. SIVQ-based pattern matching, with ring vectors selected to screen for either tingible body macrophages or apoptotic

  18. Image microarrays derived from tissue microarrays (IMA-TMA): New resource for computer-aided diagnostic algorithm development.

    Hipp, Jennifer A; Hipp, Jason D; Lim, Megan; Sharma, Gaurav; Smith, Lauren B; Hewitt, Stephen M; Balis, Ulysses G J


    Conventional tissue microarrays (TMAs) consist of cores of tissue inserted into a recipient paraffin block such that a tissue section on a single glass slide can contain numerous patient samples in a spatially structured pattern. Scanning TMAs into digital slides for subsequent analysis by computer-aided diagnostic (CAD) algorithms all offers the possibility of evaluating candidate algorithms against a near-complete repertoire of variable disease morphologies. This parallel interrogation approach simplifies the evaluation, validation, and comparison of such candidate algorithms. A recently developed digital tool, digital core (dCORE), and image microarray maker (iMAM) enables the capture of uniformly sized and resolution-matched images, with these representing key morphologic features and fields of view, aggregated into a single monolithic digital image file in an array format, which we define as an image microarray (IMA). We further define the TMA-IMA construct as IMA-based images derived from whole slide images of TMAs themselves. Here we describe the first combined use of the previously described dCORE and iMAM tools, toward the goal of generating a higher-order image construct, with multiple TMA cores from multiple distinct conventional TMAs assembled as a single digital image montage. This image construct served as the basis of the carrying out of a massively parallel image analysis exercise, based on the use of the previously described spatially invariant vector quantization (SIVQ) algorithm. Multicase, multifield TMA-IMAs of follicular lymphoma and follicular hyperplasia were separately rendered, using the aforementioned tools. Each of these two IMAs contained a distinct spectrum of morphologic heterogeneity with respect to both tingible body macrophage (TBM) appearance and apoptotic body morphology. SIVQ-based pattern matching, with ring vectors selected to screen for either tingible body macrophages or apoptotic bodies, was subsequently carried out on the

  19. SAR Image Segmentation Based On Hybrid PSOGSA Optimization Algorithm

    Amandeep Kaur


    Full Text Available Image segmentation is useful in many applications. It can identify the regions of interest in a scene or annotate the data. It categorizes the existing segmentation algorithm into region-based segmentation, data clustering, and edge-base segmentation. Region-based segmentation includes the seeded and unseeded region growing algorithms, the JSEG, and the fast scanning algorithm. Due to the presence of speckle noise, segmentation of Synthetic Aperture Radar (SAR images is still a challenging problem. We proposed a fast SAR image segmentation method based on Particle Swarm Optimization-Gravitational Search Algorithm (PSO-GSA. In this method, threshold estimation is regarded as a search procedure that examinations for an appropriate value in a continuous grayscale interval. Hence, PSO-GSA algorithm is familiarized to search for the optimal threshold. Experimental results indicate that our method is superior to GA based, AFS based and ABC based methods in terms of segmentation accuracy, segmentation time, and Thresholding.

  20. Variation-based approach to image segmentation Variation-based approach to image segmentation

    张永平; 郑南宁; 赵荣椿


    A new approach to image segmentation is presented using a variation framework. Regarding the edge points as interpolating points and minimizing an energy functional to interpolate a smooth threshold surface it carries out the image segmentation. In order to preserve the edge information of the original image in the threshold surface, without unduly sharping the edge of the image, a non-convex energy functional is adopted. A relaxation algorithm with the property of global convergence, for solving the optimization problem, is proposed by introducing a binary energy. As a result the non-convex optimization problem is transformed into a series of convex optimization problems, and the problem of slow convergence or nonconvergence is solved. The presented method is also tested experimentally. Finally the method of determining the parameters in optimizing is also explored.   

  1. An Improved FCM Medical Image Segmentation Algorithm Based on MMTD

    Ningning Zhou


    Full Text Available Image segmentation plays an important role in medical image processing. Fuzzy c-means (FCM is one of the popular clustering algorithms for medical image segmentation. But FCM is highly vulnerable to noise due to not considering the spatial information in image segmentation. This paper introduces medium mathematics system which is employed to process fuzzy information for image segmentation. It establishes the medium similarity measure based on the measure of medium truth degree (MMTD and uses the correlation of the pixel and its neighbors to define the medium membership function. An improved FCM medical image segmentation algorithm based on MMTD which takes some spatial features into account is proposed in this paper. The experimental results show that the proposed algorithm is more antinoise than the standard FCM, with more certainty and less fuzziness. This will lead to its practicable and effective applications in medical image segmentation.

  2. Statistical multiscale image segmentation via Alpha-stable modeling

    Wan, Tao; Canagarajah, CN; Achim, AM


    This paper presents a new statistical image segmentation algorithm, in which the texture features are modeled by symmetric alpha-stable (SalphaS) distributions. These features are efficiently combined with the dominant color feature to perform automatic segmentation. First, the image is roughly segmented into textured and nontextured regions using the dual-tree complex wavelet transform (DT-CWT) with the sub-band coefficients modeled as SalphaS random variables. A mul-tiscale segmentation is ...

  3. An Efficient Approach for Tree Digital Image Segmentation

    Cheng Lei; Song Tieying


    This paper proposes an improved method to segment tree image based on color and texture feature and amends the segmented result by mathematical morphology. The crown and trunk of one tree have been successfully segmented and the experimental result is deemed effective. The authors conclude that building a standard data base for a range of species, featuring color and texture is a necessary condition and constitutes the essential groundwork for tree image segmentation in order to insure its quality.

  4. Fingerprint Image Enhancement:Segmentation to Thinning

    Iwasokun Gabriel Babatunde


    Full Text Available Fingerprint has remained a very vital index for human recognition. In the field of security, series of Automatic Fingerprint Identification Systems (AFIS have been developed. One of the indices for evaluating the contributions of these systems to the enforcement of security is the degree with which they appropriately verify or identify input fingerprints. This degree is generally determined by the quality of the fingerprint images and the efficiency of the algorithm. In this paper, some of the sub-models of an existing mathematical algorithm for the fingerprint image enhancement were modified to obtain new and improved versions. The new versions consist of different mathematical models for fingerprint image segmentation, normalization, ridge orientation estimation, ridge frequency estimation, Gabor filtering, binarization and thinning. The implementation was carried out in an environment characterized by Window Vista Home Basic operating system as platform and Matrix Laboratory (MatLab as frontend engine. Synthetic images as well as real fingerprints obtained from the FVC2004 fingerprint database DB3 set A were used to test the adequacy of the modified sub-models and the resulting algorithm. The results show that the modified sub-models perform well with significant improvement over the original versions. The results also show the necessity of each level of the enhancement.

  5. Image Segmentation for Connectomics Using Machine Learning

    Tasdizen, Tolga; Seyedhosseini, Mojtaba; Liu, TIng; Jones, Cory; Jurrus, Elizabeth R.


    Reconstruction of neural circuits at the microscopic scale of individual neurons and synapses, also known as connectomics, is an important challenge for neuroscience. While an important motivation of connectomics is providing anatomical ground truth for neural circuit models, the ability to decipher neural wiring maps at the individual cell level is also important in studies of many neurodegenerative diseases. Reconstruction of a neural circuit at the individual neuron level requires the use of electron microscopy images due to their extremely high resolution. Computational challenges include pixel-by-pixel annotation of these images into classes such as cell membrane, mitochondria and synaptic vesicles and the segmentation of individual neurons. State-of-the-art image analysis solutions are still far from the accuracy and robustness of human vision and biologists are still limited to studying small neural circuits using mostly manual analysis. In this chapter, we describe our image analysis pipeline that makes use of novel supervised machine learning techniques to tackle this problem.

  6. [An adaptive threshloding segmentation method for urinary sediment image].

    Li, Yongming; Zeng, Xiaoping; Qin, Jian; Han, Liang


    In this paper is proposed a new method to solve the segmentation of the complicated defocusing urinary sediment image. The main points of the method are: (1) using wavelet transforms and morphology to erase the effect of defocusing and realize the first segmentation, (2) using adaptive threshold processing in accordance to the subimages after wavelet processing, and (3) using 'peel off' algorithm to deal with the overlapped cells' segmentations. The experimental results showed that this method was not affected by the defocusing, and it made good use of many kinds of characteristics of the images. So this new mehtod can get very precise segmentation; it is effective for defocusing urinary sediment image segmentation.

  7. An Interactive Image Segmentation Method in Hand Gesture Recognition.

    Chen, Disi; Li, Gongfa; Sun, Ying; Kong, Jianyi; Jiang, Guozhang; Tang, Heng; Ju, Zhaojie; Yu, Hui; Liu, Honghai


    In order to improve the recognition rate of hand gestures a new interactive image segmentation method for hand gesture recognition is presented, and popular methods, e.g., Graph cut, Random walker, Interactive image segmentation using geodesic star convexity, are studied in this article. The Gaussian Mixture Model was employed for image modelling and the iteration of Expectation Maximum algorithm learns the parameters of Gaussian Mixture Model. We apply a Gibbs random field to the image segmentation and minimize the Gibbs Energy using Min-cut theorem to find the optimal segmentation. The segmentation result of our method is tested on an image dataset and compared with other methods by estimating the region accuracy and boundary accuracy. Finally five kinds of hand gestures in different backgrounds are tested on our experimental platform, and the sparse representation algorithm is used, proving that the segmentation of hand gesture images helps to improve the recognition accuracy.

  8. SVM for density estimation and application to medical image segmentation

    ZHANG Zhao; ZHANG Su; ZHANG Chen-xi; CHEN Ya-zhu


    A method of medical image segmentation based on support vector machine (SVM) for density estimation is presented. We used this estimator to construct a prior model of the image intensity and curvature profile of the structure from training images. When segmenting a novel image similar to the training images, the technique of narrow level set method is used. The higher dimensional surface evolution metric is defined by the prior model instead of by energy minimization function. This method offers several advantages. First, SVM for density estimation is consistent and its solution is sparse. Second, compared to the traditional level set methods, this method incorporates shape information on the object to be segmented into the segmentation process.Segmentation results are demonstrated on synthetic images, MR images and ultrasonic images.

  9. A Survey Paper on Fuzzy Image Segmentation Techniques

    Ms. R. Saranya Pon Selvi


    Full Text Available The image segmentation plays an important role in the day-to-day life. The new technologies are emerging in the field of Image processing, especially in the domain of segmentation.Segmentation is considered as one of the main steps in image processing. It divides a digital image into multiple regions in order to analyze them. It is also used to distinguish different objects in the image. Several image segmentation techniques have been developed by the researchers in order to make images smooth and easy to evaluate. This paper presents a brief outline on some of the most commonly used segmentation techniques like thresholding, Region based, Model based, Edge detection..etc. mentioning its advantages as well as the drawbacks. Some of the techniques are suitable for noisy images.

  10. A CT Image Segmentation Algorithm Based on Level Set Method

    QU Jing-yi; SHI Hao-shan


    Level Set methods are robust and efficient numerical tools for resolving curve evolution in image segmentation. This paper proposes a new image segmentation algorithm based on Mumford-Shah module. The method is used to CT images and the experiment results demonstrate its efficiency and veracity.

  11. Application of reinforcement learning for segmentation of transrectal ultrasound images

    Tizhoosh Hamid R


    Full Text Available Abstract Background Among different medical image modalities, ultrasound imaging has a very widespread clinical use. But, due to some factors, such as poor image contrast, noise and missing or diffuse boundaries, the ultrasound images are inherently difficult to segment. An important application is estimation of the location and volume of the prostate in transrectal ultrasound (TRUS images. For this purpose, manual segmentation is a tedious and time consuming procedure. Methods We introduce a new method for the segmentation of the prostate in transrectal ultrasound images, using a reinforcement learning scheme. This algorithm is used to find the appropriate local values for sub-images and to extract the prostate. It contains an offline stage, where the reinforcement learning agent uses some images and manually segmented versions of these images to learn from. The reinforcement agent is provided with reward/punishment, determined objectively to explore/exploit the solution space. After this stage, the agent has acquired knowledge stored in the Q-matrix. The agent can then use this knowledge for new input images to extract a coarse version of the prostate. Results We have carried out experiments to segment TRUS images. The results demonstrate the potential of this approach in the field of medical image segmentation. Conclusion By using the proposed method, we can find the appropriate local values and segment the prostate. This approach can be used for segmentation tasks containing one object of interest. To improve this prototype, more investigations are needed.

  12. SAR image target segmentation based on entropy maximization and morphology

    柏正尧; 刘洲峰; 何佩琨


    Entropy maximization thresholding is a simple, effective image segmentation method. The relation between the histogram entropy and the gray level of an image is analyzed. An approach, which speeds the computation of optimal threshold based on entropy maximization, is proposed. The suggested method has been applied to the synthetic aperture radar (SAR) image targets segmentation. Mathematical morphology works well in reducing the residual noise.

  13. Image segmentation using an improved differential algorithm

    Gao, Hao; Shi, Yujiao; Wu, Dongmei


    Among all the existing segmentation techniques, the thresholding technique is one of the most popular due to its simplicity, robustness, and accuracy (e.g. the maximum entropy method, Otsu's method, and K-means clustering). However, the computation time of these algorithms grows exponentially with the number of thresholds due to their exhaustive searching strategy. As a population-based optimization algorithm, differential algorithm (DE) uses a population of potential solutions and decision-making processes. It has shown considerable success in solving complex optimization problems within a reasonable time limit. Thus, applying this method into segmentation algorithm should be a good choice during to its fast computational ability. In this paper, we first propose a new differential algorithm with a balance strategy, which seeks a balance between the exploration of new regions and the exploitation of the already sampled regions. Then, we apply the new DE into the traditional Otsu's method to shorten the computation time. Experimental results of the new algorithm on a variety of images show that, compared with the EA-based thresholding methods, the proposed DE algorithm gets more effective and efficient results. It also shortens the computation time of the traditional Otsu method.

  14. Anatomy packing with hierarchical segments: an algorithm for segmentation of pulmonary nodules in CT images.

    Tsou, Chi-Hsuan; Lor, Kuo-Lung; Chang, Yeun-Chung; Chen, Chung-Ming


    This paper proposes a semantic segmentation algorithm that provides the spatial distribution patterns of pulmonary ground-glass nodules with solid portions in computed tomography (CT) images. The proposed segmentation algorithm, anatomy packing with hierarchical segments (APHS), performs pulmonary nodule segmentation and quantification in CT images. In particular, the APHS algorithm consists of two essential processes: hierarchical segmentation tree construction and anatomy packing. It constructs the hierarchical segmentation tree based on region attributes and local contour cues along the region boundaries. Each node of the tree corresponds to the soft boundary associated with a family of nested segmentations through different scales applied by a hierarchical segmentation operator that is used to decompose the image in a structurally coherent manner. The anatomy packing process detects and localizes individual object instances by optimizing a hierarchical conditional random field model. Ninety-two histopathologically confirmed pulmonary nodules were used to evaluate the performance of the proposed APHS algorithm. Further, a comparative study was conducted with two conventional multi-label image segmentation algorithms based on four assessment metrics: the modified Williams index, percentage statistic, overlapping ratio, and difference ratio. Under the same framework, the proposed APHS algorithm was applied to two clinical applications: multi-label segmentation of nodules with a solid portion and surrounding tissues and pulmonary nodule segmentation. The results obtained indicate that the APHS-generated boundaries are comparable to manual delineations with a modified Williams index of 1.013. Further, the resulting segmentation of the APHS algorithm is also better than that achieved by two conventional multi-label image segmentation algorithms. The proposed two-level hierarchical segmentation algorithm effectively labelled the pulmonary nodule and its surrounding

  15. Graph Laplacian for spectral clustering and seeded image segmentation

    Wallace Correa de Oliveira Casaca


    Image segmentation is an essential tool to enhance the ability of computer systems to efficiently perform elementary cognitive tasks such as detection, recognition and tracking. In this thesis we concentrate on the investigation of two fundamental topics in the context of image segmentation: spectral clustering and seeded image segmentation. We introduce two new algorithms for those topics that, in summary, rely on Laplacian-based operators, spectral graph theory, and minimization of energy f...

  16. Advanced techniques in medical image segmentation of the liver

    López Mir, Fernando


    [EN] Image segmentation is, along with multimodal and monomodal registration, the operation with the greatest applicability in medical image processing. There are many operations and filters, as much as applications and cases, where the segmentation of an organic tissue is the first step. The case of liver segmentation in radiological images is, after the brain, that on which the highest number of scientific publications can be found. This is due, on the one hand, to the need to continue inno...

  17. Noise reduction of cDNA microarray images using complex wavelets.

    Howlader, Tamanna; Chaubey, Yogendra P


    Noise reduction is an essential step of cDNA microarray image analysis for obtaining better-quality gene expression measurements. Wavelet-based denoising methods have shown significant success in traditional image processing. The complex wavelet transform (CWT) is preferred to the classical discrete wavelet transform for denoising of microarray images due to its improved directional selectivity for better representation of the circular edges of spots and near shift-invariance property. Existing CWT-based denoising methods are not efficient for microarray image processing because they fail to take into account the signal as well as noise correlations that exist between red and green channel images. In this paper, two bivariate estimators are developed for the CWT-based denoising of microarray images using the standard maximum a posteriori and linear minimum mean squared error estimation criteria. The proposed denoising methods are capable of taking into account both the interchannel signal and noise correlations. Significance of the proposed denoising methods is assessed by examining the effect of noise reduction on the estimation of the log-intensity ratio. Extensive experimentations are carried out to show that the proposed methods provide better noise reduction of microarray images leading to more accurate estimation of the log-intensity ratios as compared to the other CWT-based denoising methods.

  18. Segmentation of neuroanatomy in magnetic resonance images

    Simmons, Andrew; Arridge, Simon R.; Barker, G. J.; Tofts, Paul S.


    Segmentation in neurological magnetic resonance imaging (MRI) is necessary for feature extraction, volume measurement and for the three-dimensional display of neuroanatomy. Automated and semi-automated methods offer considerable advantages over manual methods because of their lack of subjectivity, their data reduction capabilities, and the time savings they give. We have used dual echo multi-slice spin-echo data sets which take advantage of the intrinsically multispectral nature of MRI. As a pre-processing step, a rf non-uniformity correction is applied and if the data is noisy the images are smoothed using a non-isotropic blurring method. Edge-based processing is used to identify the skin (the major outer contour) and the eyes. Edge-focusing has been used to significantly simplify edge images and thus allow simple postprocessing to pick out the brain contour in each slice of the data set. Edge- focusing is a technique which locates significant edges using a high degree of smoothing at a coarse level and tracks these edges to a fine level where the edges can be determined with high positional accuracy. Both 2-D and 3-D edge-detection methods have been compared. Once isolated, the brain is further processed to identify CSF, and, depending upon the MR pulse sequence used, the brain itself may be sub-divided into gray matter and white matter using semi-automatic contrast enhancement and clustering methods.

  19. Image Segmentation by Hierarchical Spatial and Color Spaces Clustering

    YU Wei


    Image segmentation, as a basic building block for many high-level image analysis problems, has attracted many research attentions over years. Existing approaches, however, are mainly focusing on the clustering analysis in the single channel information, i.e., either in color or spatial space, which may lead to unsatisfactory segmentation performance. Considering the spatial and color spaces jointly, this paper proposes a new hierarchical image segmentation algorithm, which alternately clusters the image regions in color and spatial spaces in a fine to coarse manner. Without losing the perceptual consistence, the proposed algorithm achieves the segmentation result using only very few number of colors according to user specification.

  20. Applications of magnetic resonance image segmentation in neurology

    Heinonen, Tomi; Lahtinen, Antti J.; Dastidar, Prasun; Ryymin, Pertti; Laarne, Paeivi; Malmivuo, Jaakko; Laasonen, Erkki; Frey, Harry; Eskola, Hannu


    After the introduction of digital imagin devices in medicine computerized tissue recognition and classification have become important in research and clinical applications. Segmented data can be applied among numerous research fields including volumetric analysis of particular tissues and structures, construction of anatomical modes, 3D visualization, and multimodal visualization, hence making segmentation essential in modern image analysis. In this research project several PC based software were developed in order to segment medical images, to visualize raw and segmented images in 3D, and to produce EEG brain maps in which MR images and EEG signals were integrated. The software package was tested and validated in numerous clinical research projects in hospital environment.


    Anand Deshpande


    Full Text Available The iris segmentation plays a major role in an iris recognition system to increase the performance of the system. This paper proposes a novel method for segmentation of iris images to extract the iris part of long range captured eye image and an approach to select best iris frame from the iris polar image sequences by analyzing the quality of iris polar images. The quality of iris image is determined by the frequency components present in the iris polar images. The experiments are carried out on CASIA-long range captured iris image sequences. The proposed segmentation method is compared with Hough transform based segmentation and it has been determined that the proposed method gives higher accuracy for segmentation than Hough transform.

  2. A novel stepwise thresholding for fuzzy image segmentation

    HE Xiao-hai; LUO Dai-sheng; WU Xiao-qiang; JIANG Li; TENG Qi-zhi; Tao De-yuan


    A novel stepwise thresholding method for fuzzy image segmentation is proposed. Unlike the published iterative or recursive thresholding mehtods, this method segments regions into sub-regions iteratively by increasing threshold value in a stepwise manner, based on a preset intensity homogeneity criteria. The method is particularly suited to segmentation of the laser scanning confocal microscopy (LSCM) images, computerised tomography (CT) images, magnetic resonance (MR) images, fingerprint images, etc. The method has been tested on some typical fuzzy image data sets. In this paper, the novel stepwise thresholding is first addressed. Next a new method of region labelling for region extraction is introduced.Then the design of intensity homogeneity segmentation criteria is presented. Some examples of the experiment results of fuzzy image segmentation by the method are given at the end.

  3. Ontology-based, Tissue MicroArray oriented, image centered tissue bank

    Viti Federica; Merelli Ivan; Caprera Andrea; Lazzari Barbara; Stella Alessandra; Milanesi Luciano


    Abstract Background Tissue MicroArray technique is becoming increasingly important in pathology for the validation of experimental data from transcriptomic analysis. This approach produces many images which need to be properly managed, if possible with an infrastructure able to support tissue sharing between institutes. Moreover, the available frameworks oriented to Tissue MicroArray provide good storage for clinical patient, sample treatment and block construction information, but their util...

  4. A wrapper-based approach to image segmentation and classification.

    Farmer, Michael E; Jain, Anil K


    The traditional processing flow of segmentation followed by classification in computer vision assumes that the segmentation is able to successfully extract the object of interest from the background image. It is extremely difficult to obtain a reliable segmentation without any prior knowledge about the object that is being extracted from the scene. This is further complicated by the lack of any clearly defined metrics for evaluating the quality of segmentation or for comparing segmentation algorithms. We propose a method of segmentation that addresses both of these issues, by using the object classification subsystem as an integral part of the segmentation. This will provide contextual information regarding the objects to be segmented, as well as allow us to use the probability of correct classification as a metric to determine the quality of the segmentation. We view traditional segmentation as a filter operating on the image that is independent of the classifier, much like the filter methods for feature selection. We propose a new paradigm for segmentation and classification that follows the wrapper methods of feature selection. Our method wraps the segmentation and classification together, and uses the classification accuracy as the metric to determine the best segmentation. By using shape as the classification feature, we are able to develop a segmentation algorithm that relaxes the requirement that the object of interest to be segmented must be homogeneous in some low-level image parameter, such as texture, color, or grayscale. This represents an improvement over other segmentation methods that have used classification information only to modify the segmenter parameters, since these algorithms still require an underlying homogeneity in some parameter space. Rather than considering our method as, yet, another segmentation algorithm, we propose that our wrapper method can be considered as an image segmentation framework, within which existing image segmentation

  5. A Comparison of X-Ray Image Segmentation Techniques



    Full Text Available Image segmentation operation has a great importance in most medical imaging applications, by extracting anatomical structures from medical images. There are many image segmentation techniques available in the literature, each of them having advantages and disadvantages. The extraction of bone contours from X-ray images has received a considerable amount of attention in the literature recently, because they represent a vital step in the computer analysis of this kind of images. The aim of X-ray segmentation is to subdivide the image in various portions, so that it can help doctors during the study of the bone structure, for the detection of fractures in bones, or for planning the treatment before surgery. The goal of this paper is to review the most important image segmentation methods starting from a data base composed by real X-ray images. We will discuss the principle and the mathematical model for each method, highlighting the strengths and weaknesses.

  6. [Segmentation Method for Liver Organ Based on Image Sequence Context].

    Zhang, Meiyun; Fang, Bin; Wang, Yi; Zhong, Nanchang


    In view of the problems of more artificial interventions and segmentation defects in existing two-dimensional segmentation methods and abnormal liver segmentation errors in three-dimensional segmentation methods, this paper presents a semi-automatic liver organ segmentation method based on the image sequence context. The method takes advantage of the existing similarity between the image sequence contexts of the prior knowledge of liver organs, and combines region growing and level set method to carry out semi-automatic segmentation of livers, along with the aid of a small amount of manual intervention to deal with liver mutation situations. The experiment results showed that the liver segmentation algorithm presented in this paper had a high precision, and a good segmentation effect on livers which have greater variability, and can meet clinical application demands quite well.

  7. A portable interferometric micro-array reader on image sensor

    Villar Zafra, Aitor


    [ANGLÈS] Microarrays constitute a valuable analytical tool for multiplex and high-throughput analysis and are widely used in genomics and proteomics with many potential applications. During the last decades, protein chips have found increasing acceptance for diagnostic applications due to several advantages over conventional bioanalysis such as miniaturization, parallelization, real-time and sensitivity. Even though the majority of DNA-sensor systems relies on labeling of DNA, the recent prog...

  8. Fuzzy entropy image segmentation based on particle Swarm optimization

    Linyi Li; Deren Li


    Partide swaFnl optimization is a stochastic global optimization algorithm that is based on swarm intelligence.Because of its excellent performance,particle swarm optimization is introduced into fuzzy entropy image segmentation to select the optimal fuzzy parameter combination and fuzzy threshold adaptively.In this study,the particles in the swarm are constructed and the swarm search strategy is proposed to meet the needs of the segmentation application.Then fuzzy entropy image segmentation based on particle swarm opti-mization is implemented and the proposed method obtains satisfactory results in the segmentation experiments.Compared with the exhaustive search method,particle swarm optimization can give the salne optimal fuzzy parameter combination and fuzzy threshold while needing less search time in the segmentation experiments and also has good search stability in the repeated experiments.Therefore,fuzzy entropy image segmentation based on particle swarm optimization is an efficient and promising segmentation method.

  9. General Purpose Segmentation for Microorganisms in Microscopy Images

    Jensen, Sebastian H. Nesgaard; Moeslund, Thomas B.; Rankl, Christian


    In this paper, we propose an approach for achieving generalized segmentation of microorganisms in mi- croscopy images. It employs a pixel-wise classification strategy based on local features. Multilayer percep- trons are utilized for classification of the local features and is trained for each...... specific segmentation problem using supervised learning. This approach was tested on five different segmentation problems in bright field, differential interference contrast, fluorescence and laser confocal scanning microscopy. In all instance good results were achieved with the segmentation quality...

  10. Fabrication of DNA Microarrays on Polydopamine-Modified Gold Thin Films for SPR Imaging Measurements

    Wood, Jennifer B.; Szyndler, Megan W.; Halpern, Aaron R.; Cho, Kyunghee


    Polydopamine (PDA) films were fabricated on thin film gold substrates in a single-step polymerization-deposition process from dopamine solutions and then employed in the construction of robust DNA microarrays for the ultra-sensitive detection of biomolecules with nanoparticle-enhanced surface plasmon resonance (SPR) imaging. PDA multilayers with thicknesses varying from 1 to 5 nm were characterized with a combination of scanning angle SPR and AFM experiments, and 1.3 ± 0.2 nm PDA multilayers were chosen as an optimal thickness for the SPR imaging measurements. DNA microarrays were then fabricated by the reaction of amine-functionalized single-stranded DNA (ssDNA) oligonucleotides with PDA-modified gold thin film microarray elements, and were subsequently employed in SPR imaging measurements of DNA hybridization adsorption and protein-DNA binding. Concurrent control experiments with noncomplementary ssDNA sequences demonstrated that the adhesive PDA multilayer was also able to provide good resistance to the nonspecific binding of biomolecules. Finally, a series of SPR imaging measurements of the hybridization adsorption of DNA-modified gold nanoparticles onto mixed sequence DNA microarrays were used to confirm that the use of PDA multilayer films is a simple, rapid and versatile method for fabricating DNA microarrays for ultrasensitive nanoparticle-enhanced SPR imaging biosensing. PMID:23902428

  11. Fabrication of DNA microarrays on polydopamine-modified gold thin films for SPR imaging measurements.

    Wood, Jennifer B; Szyndler, Megan W; Halpern, Aaron R; Cho, Kyunghee; Corn, Robert M


    Polydopamine (PDA) films were fabricated on thin film gold substrates in a single-step polymerization-deposition process from dopamine solutions and then employed in the construction of robust DNA microarrays for the ultrasensitive detection of biomolecules with nanoparticle-enhanced surface plasmon resonance (SPR) imaging. PDA multilayers with thicknesses varying from 1 to 5 nm were characterized with a combination of scanning angle SPR and AFM experiments, and 1.3 ± 0.2 nm PDA multilayers were chosen as an optimal thickness for the SPR imaging measurements. DNA microarrays were then fabricated by the reaction of amine-functionalized single-stranded DNA (ssDNA) oligonucleotides with PDA-modified gold thin film microarray elements, and were subsequently employed in SPR imaging measurements of DNA hybridization adsorption and protein-DNA binding. Concurrent control experiments with non-complementary ssDNA sequences demonstrated that the adhesive PDA multilayer was also able to provide good resistance to the nonspecific binding of biomolecules. Finally, a series of SPR imaging measurements of the hybridization adsorption of DNA-modified gold nanoparticles onto mixed sequence DNA microarrays were used to confirm that the use of PDA multilayer films is a simple, rapid, and versatile method for fabricating DNA microarrays for ultrasensitive nanoparticle-enhanced SPR imaging biosensing.

  12. Medical image segmentation using 3D MRI data

    Voronin, V.; Marchuk, V.; Semenishchev, E.; Cen, Yigang; Agaian, S.


    Precise segmentation of three-dimensional (3D) magnetic resonance imaging (MRI) image can be a very useful computer aided diagnosis (CAD) tool in clinical routines. Accurate automatic extraction a 3D component from images obtained by magnetic resonance imaging (MRI) is a challenging segmentation problem due to the small size objects of interest (e.g., blood vessels, bones) in each 2D MRA slice and complex surrounding anatomical structures. Our objective is to develop a specific segmentation scheme for accurately extracting parts of bones from MRI images. In this paper, we use a segmentation algorithm to extract the parts of bones from Magnetic Resonance Imaging (MRI) data sets based on modified active contour method. As a result, the proposed method demonstrates good accuracy in a comparison between the existing segmentation approaches on real MRI data.

  13. Low-Level Hierarchical Multiscale Segmentation Statistics of Natural Images.

    Akbas, Emre; Ahuja, Narendra


    This paper is aimed at obtaining the statistics as a probabilistic model pertaining to the geometric, topological and photometric structure of natural images. The image structure is represented by its segmentation graph derived from the low-level hierarchical multiscale image segmentation. We first estimate the statistics of a number of segmentation graph properties from a large number of images. Our estimates confirm some findings reported in the past work, as well as provide some new ones. We then obtain a Markov random field based model of the segmentation graph which subsumes the observed statistics. To demonstrate the value of the model and the statistics, we show how its use as a prior impacts three applications: image classification, semantic image segmentation and object detection.

  14. Segmentation and learning in the quantitative analysis of microscopy images

    Ruggiero, Christy; Ross, Amy; Porter, Reid


    In material science and bio-medical domains the quantity and quality of microscopy images is rapidly increasing and there is a great need to automatically detect, delineate and quantify particles, grains, cells, neurons and other functional "objects" within these images. These are challenging problems for image processing because of the variability in object appearance that inevitably arises in real world image acquisition and analysis. One of the most promising (and practical) ways to address these challenges is interactive image segmentation. These algorithms are designed to incorporate input from a human operator to tailor the segmentation method to the image at hand. Interactive image segmentation is now a key tool in a wide range of applications in microscopy and elsewhere. Historically, interactive image segmentation algorithms have tailored segmentation on an image-by-image basis, and information derived from operator input is not transferred between images. But recently there has been increasing interest to use machine learning in segmentation to provide interactive tools that accumulate and learn from the operator input over longer periods of time. These new learning algorithms reduce the need for operator input over time, and can potentially provide a more dynamic balance between customization and automation for different applications. This paper reviews the state of the art in this area, provides a unified view of these algorithms, and compares the segmentation performance of various design choices.


    Lin Pan; Zheng Chongxun; Yang Yong; Gu Jianwen


    Objective To propose an automatic framework for segmentation of brain image in this paper. Methods The brain MRI image segmentation framework consists of three-step segmentation procedures. First, Non-brain structures removal by level set method. Then, the non-uniformity correction method is based on computing estimates of tissue intensity variation. Finally, it uses a statistical model based on Markov random filed for MRI brain image segmentation. The brain tissue can be classified into cerebrospinal fluid, white matter and gray matter. Results To evaluate the proposed our method, we performed two sets of experiments, one on simulated MR and another on real MR brain data. Conclusion The efficacy of the brain MRI image segmentation framework has been demonstrated by the extensive experiments. In the future, we are also planning on a large-scale clinical evaluation of this segmentation framework.

  16. Segmentation of knee injury swelling on infrared images

    Puentes, John; Langet, Hélène; Herry, Christophe; Frize, Monique


    Interpretation of medical infrared images is complex due to thermal noise, absence of texture, and small temperature differences in pathological zones. Acute inflammatory response is a characteristic symptom of some knee injuries like anterior cruciate ligament sprains, muscle or tendons strains, and meniscus tear. Whereas artificial coloring of the original grey level images may allow to visually assess the extent inflammation in the area, their automated segmentation remains a challenging problem. This paper presents a hybrid segmentation algorithm to evaluate the extent of inflammation after knee injury, in terms of temperature variations and surface shape. It is based on the intersection of rapid color segmentation and homogeneous region segmentation, to which a Laplacian of a Gaussian filter is applied. While rapid color segmentation enables to properly detect the observed core of swollen area, homogeneous region segmentation identifies possible inflammation zones, combining homogeneous grey level and hue area segmentation. The hybrid segmentation algorithm compares the potential inflammation regions partially detected by each method to identify overlapping areas. Noise filtering and edge segmentation are then applied to common zones in order to segment the swelling surfaces of the injury. Experimental results on images of a patient with anterior cruciate ligament sprain show the improved performance of the hybrid algorithm with respect to its separated components. The main contribution of this work is a meaningful automatic segmentation of abnormal skin temperature variations on infrared thermography images of knee injury swelling.

  17. Image mosaic method based on SIFT features of line segment.

    Zhu, Jun; Ren, Mingwu


    This paper proposes a novel image mosaic method based on SIFT (Scale Invariant Feature Transform) feature of line segment, aiming to resolve incident scaling, rotation, changes in lighting condition, and so on between two images in the panoramic image mosaic process. This method firstly uses Harris corner detection operator to detect key points. Secondly, it constructs directed line segments, describes them with SIFT feature, and matches those directed segments to acquire rough point matching. Finally, Ransac method is used to eliminate wrong pairs in order to accomplish image mosaic. The results from experiment based on four pairs of images show that our method has strong robustness for resolution, lighting, rotation, and scaling.

  18. Precise acquisition and unsupervised segmentation of multi-spectral images

    Gomez, David Delgado; Clemmensen, Line Katrine Harder; Ersbøll, Bjarne Kjær


    In this work, an integrated imaging system to obtain accurate and reproducible multi-spectral images and a novel multi-spectral image segmentation algorithm are proposed. The system collects up to 20 different spectral bands within a range that vary from 395 nm to 970 nm. The system is designed...... to acquire geometrically and chromatically corrected images in homogeneous and diffuse illumination, so images can be compared over time. The proposed segmentation algorithm combines the information provided by all the spectral bands to segment the different regions of interest. Three experiments...

  19. Deformable meshes for medical image segmentation accurate automatic segmentation of anatomical structures

    Kainmueller, Dagmar


    ? Segmentation of anatomical structures in medical image data is an essential task in clinical practice. Dagmar Kainmueller introduces methods for accurate fully automatic segmentation of anatomical structures in 3D medical image data. The author's core methodological contribution is a novel deformation model that overcomes limitations of state-of-the-art Deformable Surface approaches, hence allowing for accurate segmentation of tip- and ridge-shaped features of anatomical structures. As for practical contributions, she proposes application-specific segmentation pipelines for a range of anatom

  20. Image Segmentation and Denoising Based on Shrira-Pesenson Equation

    Pesenson, M.; Moshir, M.; Makovoz, D.; Frayer, D.; Henderson, D.


    We propose a nonlinear partial differential equation to control the trade-off between smoothing and segmentation of images. Its solutions approximate discontinuities, thus leading to detection of sharp boundaries in images. The performance of the approach is evaluated by applying it to images obtained by the Multiband Imaging Photometer for Spitzer (MIPS), 70 micron imaging band.

  1. Optimization of Segmentation Quality of Integrated Circuit Images

    Gintautas Mušketas


    Full Text Available The paper presents investigation into the application of genetic algorithms for the segmentation of the active regions of integrated circuit images. This article is dedicated to a theoretical examination of the applied methods (morphological dilation, erosion, hit-and-miss, threshold and describes genetic algorithms, image segmentation as optimization problem. The genetic optimization of the predefined filter sequence parameters is carried out. Improvement to segmentation accuracy using a non optimized filter sequence makes 6%.Artcile in Lithuanian

  2. A bio-inspired software for segmenting digital images.

    Díaz Pernil, Daniel; Molina Abril, Helena; Real Jurado, Pedro; Gutiérrez Naranjo, Miguel Ángel


    Segmentation in computer vision refers to the process of partitioning a digital image into multiple segments (sets of pixels). It has several features which make it suitable for techniques inspired by nature. It can be parallelized, locally solved and the input data can be easily encoded by bio-inspired representations. In this paper, we present a new software for performing a segmentation of 2D digital images based on Membrane Computing techniques.

  3. A new level set model for cell image segmentation

    Ma, Jing-Feng; Hou, Kai; Bao, Shang-Lian; Chen, Chun


    In this paper we first determine three phases of cell images: background, cytoplasm and nucleolus according to the general physical characteristics of cell images, and then develop a variational model, based on these characteristics, to segment nucleolus and cytoplasm from their relatively complicated backgrounds. In the meantime, the preprocessing obtained information of cell images using the OTSU algorithm is used to initialize the level set function in the model, which can speed up the segmentation and present satisfactory results in cell image processing.

  4. A new level set model for cell image segmentation

    Ma Jing-Feng; Hou Kai; Bao Shang-Lian; Chen Chun


    In this paper we first determine three phases of cell images: background, cytoplasm and nucleolus according to the general physical characteristics of cell images, and then develop a variational model, based on these characteristics, to segment nucleolus and cytoplasm from their relatively complicated backgrounds. In the meantime, the preprocessing obtained information of cell images using the OTSU algorithm is used to initialize the level set function in the model, which can speed up the segmentation and present satisfactory results in cell image processing.

  5. Adaptive image segmentation applied to plant reproduction by tissue culture

    Vazquez Rueda, Martin G.; Hahn, Federico; Zapata, Jose L.


    This paper presents that experimental results obtained on indoor tissue culture using the adaptive image segmentation system. The performance of the adaptive technique is contrasted with different non-adaptive techniques commonly used in the computer vision field to demonstrate the improvement provided by the adaptive image segmentation system.

  6. Color Image Segmentation via Improved K-Means Algorithm

    Ajay Kumar


    Full Text Available Data clustering techniques are often used to segment the real world images. Unsupervised image segmentation algorithms that are based on the clustering suffer from random initialization. There is a need for efficient and effective image segmentation algorithm, which can be used in the computer vision, object recognition, image recognition, or compression. To address these problems, the authors present a density-based initialization scheme to segment the color images. In the kernel density based clustering technique, the data sample is mapped to a high-dimensional space for the effective data classification. The Gaussian kernel is used for the density estimation and for the mapping of sample image into a high- dimensional color space. The proposed initialization scheme for the k-means clustering algorithm can homogenously segment an image into the regions of interest with the capability of avoiding the dead centre and the trapped centre by local minima phenomena. The performance of the experimental result indicates that the proposed approach is more effective, compared to the other existing clustering-based image segmentation algorithms. In the proposed approach, the Berkeley image database has been used for the comparison analysis with the recent clustering-based image segmentation algorithms like k-means++, k-medoids and k-mode.

  7. A fast and efficient segmentation scheme for cell microscopic image.

    Lebrun, G; Charrier, C; Lezoray, O; Meurie, C; Cardot, H


    Microscopic cellular image segmentation schemes must be efficient for reliable analysis and fast to process huge quantity of images. Recent studies have focused on improving segmentation quality. Several segmentation schemes have good quality but processing time is too expensive to deal with a great number of images per day. For segmentation schemes based on pixel classification, the classifier design is crucial since it is the one which requires most of the processing time necessary to segment an image. The main contribution of this work is focused on how to reduce the complexity of decision functions produced by support vector machines (SVM) while preserving recognition rate. Vector quantization is used in order to reduce the inherent redundancy present in huge pixel databases (i.e. images with expert pixel segmentation). Hybrid color space design is also used in order to improve data set size reduction rate and recognition rate. A new decision function quality criterion is defined to select good trade-off between recognition rate and processing time of pixel decision function. The first results of this study show that fast and efficient pixel classification with SVM is possible. Moreover posterior class pixel probability estimation is easy to compute with Platt method. Then a new segmentation scheme using probabilistic pixel classification has been developed. This one has several free parameters and an automatic selection must dealt with, but criteria for evaluate segmentation quality are not well adapted for cell segmentation, especially when comparison with expert pixel segmentation must be achieved. Another important contribution in this paper is the definition of a new quality criterion for evaluation of cell segmentation. The results presented here show that the selection of free parameters of the segmentation scheme by optimisation of the new quality cell segmentation criterion produces efficient cell segmentation.

  8. Segmentation algorithms for ear image data towards biomechanical studies.

    Ferreira, Ana; Gentil, Fernanda; Tavares, João Manuel R S


    In recent years, the segmentation, i.e. the identification, of ear structures in video-otoscopy, computerised tomography (CT) and magnetic resonance (MR) image data, has gained significant importance in the medical imaging area, particularly those in CT and MR imaging. Segmentation is the fundamental step of any automated technique for supporting the medical diagnosis and, in particular, in biomechanics studies, for building realistic geometric models of ear structures. In this paper, a review of the algorithms used in ear segmentation is presented. The review includes an introduction to the usually biomechanical modelling approaches and also to the common imaging modalities. Afterwards, several segmentation algorithms for ear image data are described, and their specificities and difficulties as well as their advantages and disadvantages are identified and analysed using experimental examples. Finally, the conclusions are presented as well as a discussion about possible trends for future research concerning the ear segmentation.

  9. Segmentation of Natural Images by Texture and Boundary Compression

    Mobahi, Hossein; Yang, Allen Y; Sastry, Shankar S; Ma, Yi


    We present a novel algorithm for segmentation of natural images that harnesses the principle of minimum description length (MDL). Our method is based on observations that a homogeneously textured region of a natural image can be well modeled by a Gaussian distribution and the region boundary can be effectively coded by an adaptive chain code. The optimal segmentation of an image is the one that gives the shortest coding length for encoding all textures and boundaries in the image, and is obtained via an agglomerative clustering process applied to a hierarchy of decreasing window sizes as multi-scale texture features. The optimal segmentation also provides an accurate estimate of the overall coding length and hence the true entropy of the image. We test our algorithm on the publicly available Berkeley Segmentation Dataset. It achieves state-of-the-art segmentation results compared to other existing methods.

  10. GPU accelerated fuzzy connected image segmentation by using CUDA.

    Zhuge, Ying; Cao, Yong; Miller, Robert W


    Image segmentation techniques using fuzzy connectedness principles have shown their effectiveness in segmenting a variety of objects in several large applications in recent years. However, one problem of these algorithms has been their excessive computational requirements when processing large image datasets. Nowadays commodity graphics hardware provides high parallel computing power. In this paper, we present a parallel fuzzy connected image segmentation algorithm on Nvidia's Compute Unified Device Architecture (CUDA) platform for segmenting large medical image data sets. Our experiments based on three data sets with small, medium, and large data size demonstrate the efficiency of the parallel algorithm, which achieves a speed-up factor of 7.2x, 7.3x, and 14.4x, correspondingly, for the three data sets over the sequential implementation of fuzzy connected image segmentation algorithm on CPU.

  11. Cellular image segmentation using n-agent cooperative game theory

    Dimock, Ian B.; Wan, Justin W. L.


    Image segmentation is an important problem in computer vision and has significant applications in the segmentation of cellular images. Many different imaging techniques exist and produce a variety of image properties which pose difficulties to image segmentation routines. Bright-field images are particularly challenging because of the non-uniform shape of the cells, the low contrast between cells and background, and imaging artifacts such as halos and broken edges. Classical segmentation techniques often produce poor results on these challenging images. Previous attempts at bright-field imaging are often limited in scope to the images that they segment. In this paper, we introduce a new algorithm for automatically segmenting cellular images. The algorithm incorporates two game theoretic models which allow each pixel to act as an independent agent with the goal of selecting their best labelling strategy. In the non-cooperative model, the pixels choose strategies greedily based only on local information. In the cooperative model, the pixels can form coalitions, which select labelling strategies that benefit the entire group. Combining these two models produces a method which allows the pixels to balance both local and global information when selecting their label. With the addition of k-means and active contour techniques for initialization and post-processing purposes, we achieve a robust segmentation routine. The algorithm is applied to several cell image datasets including bright-field images, fluorescent images and simulated images. Experiments show that the algorithm produces good segmentation results across the variety of datasets which differ in cell density, cell shape, contrast, and noise levels.

  12. Fingerprint Image Segmentation Using Haar Wavelet and Self Organizing Map

    Sri Suwarno


    Full Text Available Fingerprint image segmentation is one of the important preprocessing steps in Automatic Fingerprint Identification Systems (AFIS. Segmentation separates image background from image foreground, removing unnecessary information from the image. This paper proposes a new fingerprint segmentation method using Haar wavelet and Kohonen’s Self Organizing Map (SOM. Fingerprint image was decomposed using 2D Haar wavelet in two levels. To generate features vectors, the decomposed image was divided into nonoverlapping blocks of 2x2 pixels and converted into four elements vectors. These vectors were then fed into SOM network that grouped them into foreground and background clusters. Finally, blocks in the background area were removed based on indexes of blocks in the background cluster. From the research that has been carried out, we conclude that the proposed method is effective to segment background from fingerprint images.

  13. Flotation bubble image segmentation based on seed region boundary growing

    Zhang Guoying; Zhu Hong; Xu Ning


    Segmenting blurred and conglutinated bubbles in a flotation image is done using a new segmentation method based on Seed Region and Boundary Growing (SRBG). Bright pixels located on bubble tops were extracted as the seed regions. Seed boundaries are divided into four curves: left-top, right-top, rightbottom, and left-bottom. Bubbles are segmented from the seed boundary by moving these curves to the bubble boundaries along the corresponding directions. The SRBG method can remove noisy areas and it avoids over- and under-segmentation problems. Each bubble is segmented separately rather than segmenting the entire flotation image. The segmentation results from the SRBG method are more accurate than those from the Watershed algorithm.

  14. Graph Based Segmentation in Content Based Image Retrieval

    P. S. Suhasini


    Full Text Available Problem statement: Traditional image retrieval systems are content based image retrieval systems which rely on low-level features for indexing and retrieval of images. CBIR systems fail to meet user expectations because of the gap between the low level features used by such systems and the high level perception of images by humans. To meet the requirement as a preprocessing step Graph based segmentation is used in Content Based Image Retrieval (CBIR. Approach: Graph based segmentation is has the ability to preserve detail in low-variability image regions while ignoring detail in high-variability regions. After segmentation the features are extracted for the segmented images, texture features using wavelet transform and color features using histogram model and the segmented query image features are compared with the features of segmented data base images. The similarity measure used for texture features is Euclidean distance measure and for color features Quadratic distance approach. Results: The experimental results demonstrate about 12% improvement in the performance for color feature with segmentation. Conclusions/Recommendations: Along with this improvement Neural network learning can be embedded in this system to reduce the semantic gap.

  15. Segmentation of stochastic images with a stochastic random walker method.

    Pätz, Torben; Preusser, Tobias


    We present an extension of the random walker segmentation to images with uncertain gray values. Such gray-value uncertainty may result from noise or other imaging artifacts or more general from measurement errors in the image acquisition process. The purpose is to quantify the influence of the gray-value uncertainty onto the result when using random walker segmentation. In random walker segmentation, a weighted graph is built from the image, where the edge weights depend on the image gradient between the pixels. For given seed regions, the probability is evaluated for a random walk on this graph starting at a pixel to end in one of the seed regions. Here, we extend this method to images with uncertain gray values. To this end, we consider the pixel values to be random variables (RVs), thus introducing the notion of stochastic images. We end up with stochastic weights for the graph in random walker segmentation and a stochastic partial differential equation (PDE) that has to be solved. We discretize the RVs and the stochastic PDE by the method of generalized polynomial chaos, combining the recent developments in numerical methods for the discretization of stochastic PDEs and an interactive segmentation algorithm. The resulting algorithm allows for the detection of regions where the segmentation result is highly influenced by the uncertain pixel values. Thus, it gives a reliability estimate for the resulting segmentation, and it furthermore allows determining the probability density function of the segmented object volume.

  16. A Latent Source Model for Patch-Based Image Segmentation.

    Chen, George H; Shah, Devavrat; Golland, Polina


    Despite the popularity and empirical success of patch-based nearest-neighbor and weighted majority voting approaches to medical image segmentation, there has been no theoretical development on when, why, and how well these nonparametric methods work. We bridge this gap by providing a theoretical performance guarantee for nearest-neighbor and weighted majority voting segmentation under a new probabilistic model for patch-based image segmentation. Our analysis relies on a new local property for how similar nearby patches are, and fuses existing lines of work on modeling natural imagery patches and theory for nonparametric classification. We use the model to derive a new patch-based segmentation algorithm that iterates between inferring local label patches and merging these local segmentations to produce a globally consistent image segmentation. Many existing patch-based algorithms arise as special cases of the new algorithm.

  17. A Novel Multiresolution Fuzzy Segmentation Method on MR Image

    ZHANG HongMei(张红梅); BIAN ZhengZhong(卞正中); YUAN ZeJian(袁泽剑); YE Min(叶敏); JI Feng(冀峰)


    Multiresolution-based magnetic resonance (MR) image segmentation has attractedattention for its ability to capture rich information across scales compared with the conventionalsegmentation methods. In this paper, a new scale-space-based segmentation model is presented,where both the intra-scale and inter-scale properties are considered and formulated as two fuzzyenergy functions. Meanwhile, a control parameter is introduced to adjust the contribution of thesimilarity character across scales and the clustering character within the scale. By minimizing thecombined inter/intra energy function, the multiresolution fuzzy segmentation algorithm is derived.Then the coarse to fine leading segmentation is performed automatically and iteratively on a set ofmultiresolution images. The validity of the proposed algorithm is demonstrated by the test imageand pathological MR images. Experiments show that by this approach the segmentation results,especially in the tumor area delineation, are more precise than those of the conventional fuzzy segmentation methods.

  18. Automatic segmentation of HeLa cell images

    Urban, Jan


    In this work, the possibilities for segmentation of cells from their background and each other in digital image were tested, combined and improoved. Lot of images with young, adult and mixture cells were able to prove the quality of described algorithms. Proper segmentation is one of the main task of image analysis and steps order differ from work to work, depending on input images. Reply for biologicaly given question was looking for in this work, including filtration, details emphasizing, segmentation and sphericity computing. Order of algorithms and way to searching for them was also described. Some questions and ideas for further work were mentioned in the conclusion part.


    Liang Tang


    Full Text Available An automatic multilevel image segmentation method based on sup-star fuzzy reasoning (SSFR is presented. Using the well-known sup-star fuzzy reasoning technique, the proposed algorithm combines the global statistical information implied in the histogram with the local information represented by the fuzzy sets of gray-levels, and aggregates all the gray-levels into several classes characterized by the local maximum values of the histogram. The presented method has the merits of determining the number of the segmentation classes automatically, and avoiding to calculating thresholds of segmentation. Emulating and real image segmentation experiments demonstrate that the SSFR is effective.

  20. Object Recognition Algorithm Utilizing Graph Cuts Based Image Segmentation

    Zhaofeng Li


    Full Text Available This paper concentrates on designing an object recognition algorithm utilizing image segmentation. The main innovations of this paper lie in that we convert the image segmentation problem into graph cut problem, and then the graph cut results can be obtained by calculating the probability of intensity for a given pixel which is belonged to the object and the background intensity. After the graph cut process, the pixels in a same component are similar, and the pixels in different components are dissimilar. To detect the objects in the test image, the visual similarity between the segments of the testing images and the object types deduced from the training images is estimated. Finally, a series of experiments are conducted to make performance evaluation. Experimental results illustrate that compared with existing methods, the proposed scheme can effectively detect the salient objects. Particularly, we testify that, in our scheme, the precision of object recognition is proportional to image segmentation accuracy

  1. Variational segmentation problems using prior knowledge in imaging and vision

    Fundana, Ketut

    -manifold of pose-invariant planar contours into both the Chan-Vese model and its convex formulation to segment an object of interest in a sequence of images. We apply the models to track the viewpoint onto 3D rigid object. The prior-based object segmentation models encounter the problem of shape alignment, where......This dissertation addresses variational formulation of segmentation problems using prior knowledge. Variational models are among the most successful approaches for solving many Computer Vision and Image Processing problems. The models aim at finding the solution to a given energy functional defined...... to describe a Computer Vision task through energy minimization. Image segmentation, as an ill-posed problem, is still a major challenge in Computer Vision. Due to the presence of noise, clutter and occlusion, the use of image information alone often gives poor segmentation results. To overcome this problem...

  2. Multi-resolution image segmentation based on Gaussian mixture model

    Tang Yinggan; Liu Dong; Guan Xinping


    Mixture model based image segmentation method, which assumes that image pixels are independent and do not consider the position relationship between pixels, is not robust to noise and usually leads to misclassification. A new segmentation method, called multi-resolution Gaussian mixture model method, is proposed. First, an image pyramid is constructed and son-father link relationship is built between each level of pyramid. Then the mixture model segmentation method is applied to the top level. The segmentation result on the top level is passed top-down to the bottom level according to the son-father link relationship between levels. The proposed method considers not only local but also global information of image, it overcomes the effect of noise and can obtain better segmentation result. Experimental result demonstrates its effectiveness.

  3. Fast spectral color image segmentation based on filtering and clustering

    Xing, Min; Li, Hongyu; Jia, Jinyuan; Parkkinen, Jussi


    This paper proposes a fast approach to spectral image segmentation. In the algorithm, two popular techniques are extended and applied to spectral color images: the mean-shift filtering and the kernel-based clustering. We claim that segmentation should be completed under illuminant F11 rather than directly using the original spectral reflectance, because such illumination can reduce data variability and expedite the following filtering. The modes obtained in the mean-shift filtering represent the local features of spectral images, and will be applied to segmentation in place of pixels. Since the modes are generally small in number, the eigendecomposition of kernel matrices, the crucial step in the kernelbased clustering, becomes much easier. The combination of these two techniques can efficiently enhance the performance of segmentation. Experiments show that the proposed segmentation method is feasible and very promising for spectral color images.

  4. Multiscale Segmentation of Polarimetric SAR Image Based on Srm Superpixels

    Lang, F.; Yang, J.; Wu, L.; Li, D.


    Multi-scale segmentation of remote sensing image is more systematic and more convenient for the object-oriented image analysis compared to single-scale segmentation. However, the existing pixel-based polarimetric SAR (PolSAR) image multi-scale segmentation algorithms are usually inefficient and impractical. In this paper, we proposed a superpixel-based binary partition tree (BPT) segmentation algorithm by combining the generalized statistical region merging (GSRM) algorithm and the BPT algorithm. First, superpixels are obtained by setting a maximum region number threshold to GSRM. Then, the region merging process of the BPT algorithm is implemented based on superpixels but not pixels. The proposed algorithm inherits the advantages of both GSRM and BPT. The operation efficiency is obviously improved compared to the pixel-based BPT segmentation. Experiments using the Lband ESAR image over the Oberpfaffenhofen test site proved the effectiveness of the proposed method.

  5. Image segmentation on adaptive edge-preserving smoothing

    He, Kun; Wang, Dan; Zheng, Xiuqing


    Nowadays, typical active contour models are widely applied in image segmentation. However, they perform badly on real images with inhomogeneous subregions. In order to overcome the drawback, this paper proposes an edge-preserving smoothing image segmentation algorithm. At first, this paper analyzes the edge-preserving smoothing conditions for image segmentation and constructs an edge-preserving smoothing model inspired by total variation. The proposed model has the ability to smooth inhomogeneous subregions and preserve edges. Then, a kind of clustering algorithm, which reasonably trades off edge-preserving and subregion-smoothing according to the local information, is employed to learn the edge-preserving parameter adaptively. At last, according to the confidence level of segmentation subregions, this paper constructs a smoothing convergence condition to avoid oversmoothing. Experiments indicate that the proposed algorithm has superior performance in precision, recall, and F-measure compared with other segmentation algorithms, and it is insensitive to noise and inhomogeneous-regions.

  6. Comparison of Model-Based Segmentation Algorithms for Color Images.


    image. Hunt and Kubler [Ref. 3] found that for image restoration, Karhunen-Loive transformation followed by single channel image processing worked...Algorithm for Segmentation of Multichannel Images. M.S.Thesis, Naval Postgraduate School, Monterey, CaliFornia, December 1993. 3. Hunt, B.R., Kubler 0

  7. Real-time planar segmentation of depth images: from three-dimensional edges to segmented planes

    Javan Hemmat, Hani; Bondarev, Egor; de With, Peter H. N.


    Real-time execution of processing algorithms for handling depth images in a three-dimensional (3-D) data framework is a major challenge. More specifically, considering depth images as point clouds and performing planar segmentation requires heavy computation, because available planar segmentation algorithms are mostly based on surface normals and/or curvatures, and, consequently, do not provide real-time performance. Aiming at the reconstruction of indoor environments, the spaces mainly consist of planar surfaces, so that a possible 3-D application would strongly benefit from a real-time algorithm. We introduce a real-time planar segmentation method for depth images avoiding any surface normal calculation. First, we detect 3-D edges in a depth image and generate line segments between the identified edges. Second, we fuse all the points on each pair of intersecting line segments into a plane candidate. Third and finally, we implement a validation phase to select planes from the candidates. Furthermore, various enhancements are applied to improve the segmentation quality. The GPU implementation of the proposed algorithm segments depth images into planes at the rate of 58 fps. Our pipeline-interleaving technique increases this rate up to 100 fps. With this throughput rate improvement, the application benefit of our algorithm may be further exploited in terms of quality and enhancing the localization.


    纳瑟; 刘重庆


    This paper presented a method that incorporates Markov Random Field(MRF), watershed segmentation and merging techniques for performing image segmentation and edge detection tasks. MRF is used to obtain an initial estimate of x regions in the image under process where in MRF model, gray level x, at pixel location i, in an image X, depends on the gray levels of neighboring pixels. The process needs an initial segmented result. An initial segmentation is got based on K-means clustering technique and the minimum distance, then the region process in modeled by MRF to obtain an image contains different intensity regions. Starting from this we calculate the gradient values of that image and then employ a watershed technique. When using MRF method it obtains an image that has different intensity regions and has all the edge and region information, then it improves the segmentation result by superimpose closed and an accurate boundary of each region using watershed algorithm. After all pixels of the segmented regions have been processed, a map of primitive region with edges is generated. Finally, a merge process based on averaged mean values is employed. The final segmentation and edge detection result is one closed boundary per actual region in the image.

  9. Graph run-length matrices for histopathological image segmentation.

    Tosun, Akif Burak; Gunduz-Demir, Cigdem


    The histopathological examination of tissue specimens is essential for cancer diagnosis and grading. However, this examination is subject to a considerable amount of observer variability as it mainly relies on visual interpretation of pathologists. To alleviate this problem, it is very important to develop computational quantitative tools, for which image segmentation constitutes the core step. In this paper, we introduce an effective and robust algorithm for the segmentation of histopathological tissue images. This algorithm incorporates the background knowledge of the tissue organization into segmentation. For this purpose, it quantifies spatial relations of cytological tissue components by constructing a graph and uses this graph to define new texture features for image segmentation. This new texture definition makes use of the idea of gray-level run-length matrices. However, it considers the runs of cytological components on a graph to form a matrix, instead of considering the runs of pixel intensities. Working with colon tissue images, our experiments demonstrate that the texture features extracted from "graph run-length matrices" lead to high segmentation accuracies, also providing a reasonable number of segmented regions. Compared with four other segmentation algorithms, the results show that the proposed algorithm is more effective in histopathological image segmentation.

  10. FCM Clustering Algorithms for Segmentation of Brain MR Images

    Yogita K. Dubey


    Full Text Available The study of brain disorders requires accurate tissue segmentation of magnetic resonance (MR brain images which is very important for detecting tumors, edema, and necrotic tissues. Segmentation of brain images, especially into three main tissue types: Cerebrospinal Fluid (CSF, Gray Matter (GM, and White Matter (WM, has important role in computer aided neurosurgery and diagnosis. Brain images mostly contain noise, intensity inhomogeneity, and weak boundaries. Therefore, accurate segmentation of brain images is still a challenging area of research. This paper presents a review of fuzzy c-means (FCM clustering algorithms for the segmentation of brain MR images. The review covers the detailed analysis of FCM based algorithms with intensity inhomogeneity correction and noise robustness. Different methods for the modification of standard fuzzy objective function with updating of membership and cluster centroid are also discussed.

  11. Unsupervised texture image segmentation using multilayer data condensation spectral clustering

    Liu, Hanqiang; Jiao, Licheng; Zhao, Feng


    A novel unsupervised texture image segmentation using a multilayer data condensation spectral clustering algorithm is presented. First, the texture features of each image pixel are extracted by the stationary wavelet transform and a multilayer data condensation method is performed on this texture features data set to obtain a condensation subset. Second, the spectral clustering algorithm based on the manifold similarity measure is used to cluster the condensation subset. Finally, according to the clustering result of the condensation subset, the nearest-neighbor method is adopted to obtain the original image-segmentation result. In the experiments, we apply our method to solve the texture and synthetic aperture radar image segmentation and take self-tuning k-nearest-neighbor spectral clustering and Nyström methods for baseline comparisons. The experimental results show that the proposed method is more robust and effective for texture image segmentation.

  12. Gaussian Mixture Model and Rjmcmc Based RS Image Segmentation

    Shi, X.; Zhao, Q. H.


    For the image segmentation method based on Gaussian Mixture Model (GMM), there are some problems: 1) The number of component was usually a fixed number, i.e., fixed class and 2) GMM is sensitive to image noise. This paper proposed a RS image segmentation method that combining GMM with reversible jump Markov Chain Monte Carlo (RJMCMC). In proposed algorithm, GMM was designed to model the distribution of pixel intensity in RS image. Assume that the number of component was a random variable. Respectively build the prior distribution of each parameter. In order to improve noise resistance, used Gibbs function to model the prior distribution of GMM weight coefficient. According to Bayes' theorem, build posterior distribution. RJMCMC was used to simulate the posterior distribution and estimate its parameters. Finally, an optimal segmentation is obtained on RS image. Experimental results show that the proposed algorithm can converge to the optimal number of class and get an ideal segmentation results.

  13. The Watershed Algorithm for Image Segmentation

    OU Yan; LIN Nan


    This article introduced the watershed algorithm for the segmentation, illustrated the segmation process by implementing this algorithm. By comparing with another three related algorithm, this article revealed both the advantages and drawbacks of the watershed algorithm.

  14. Multilevel segmentation of intracranial aneurysms in CT angiography images

    Wang, Yan [Radiology and Biomedical Imaging, University of California, San Francisco, San Francisco, California 94122 and University of Lyon, CREATIS, CNRS UMR 5220, INSERM U1206, UCB Lyon1, INSA Lyon, Lyon 69100 (France); Zhang, Yue, E-mail: [Veterans Affairs Medical Center, San Francisco, California 94121 and University of Lyon, CREATIS, CNRS UMR 5220, INSERM U1206, UCB Lyon1, INSA Lyon, Lyon 69100 (France); Navarro, Laurent [Ecole Nationale Superieure des Mines de Saint-Etienne, Saint-Etienne 42015 (France); Eker, Omer Faruk [CHU Montpellier, Neuroradiologie, Montpellier 34000 (France); Corredor Jerez, Ricardo A. [Ecole Polytechnique Federale de Lausanne, Lausanne 1015 (Switzerland); Chen, Yu; Zhu, Yuemin; Courbebaisse, Guy [University of Lyon, CREATIS, CNRS UMR 5220, INSERM U1206, UCB Lyon1, INSA Lyon, Lyon 69100 (France)


    Purpose: Segmentation of aneurysms plays an important role in interventional planning. Yet, the segmentation of both the lumen and the thrombus of an intracranial aneurysm in computed tomography angiography (CTA) remains a challenge. This paper proposes a multilevel segmentation methodology for efficiently segmenting intracranial aneurysms in CTA images. Methods: The proposed methodology first uses the lattice Boltzmann method (LBM) to extract the lumen part directly from the original image. Then, the LBM is applied again on an intermediate image whose lumen part is filled by the mean gray-level value outside the lumen, to yield an image region containing part of the aneurysm boundary. After that, an expanding disk is introduced to estimate the complete contour of the aneurysm. Finally, the contour detected is used as the initial contour of the level set with ellipse to refine the aneurysm. Results: The results obtained on 11 patients from different hospitals showed that the proposed segmentation was comparable with manual segmentation, and that quantitatively, the average segmentation matching factor (SMF) reached 86.99%, demonstrating good segmentation accuracy. Chan–Vese method, Sen’s model, and Luca’s model were used to compare the proposed method and their average SMF values were 39.98%, 40.76%, and 77.11%, respectively. Conclusions: The authors have presented a multilevel segmentation method based on the LBM and level set with ellipse for accurate segmentation of intracranial aneurysms. Compared to three existing methods, for all eleven patients, the proposed method can successfully segment the lumen with the highest SMF values for nine patients and second highest SMF values for the two. It also segments the entire aneurysm with the highest SMF values for ten patients and second highest SMF value for the one. This makes it potential for clinical assessment of the volume and aspect ratio of the intracranial aneurysms.


    A.A. Haseena Thasneem


    Full Text Available This paper compares different algorithms for the segmentation of skin lesions in dermoscopic images. The basic segmentation algorithms compared are Thresholding techniques (Global and Adaptive, Region based techniques (K-means, Fuzzy C means, Expectation Maximization and Statistical Region Merging, Contour models (Active Contour Model and Chan - Vese Model and Spectral Clustering. Accuracy, sensitivity, specificity, Border error, Hammoude distance, Hausdorff distance, MSE, PSNR and elapsed time metrices were used to evaluate various segmentation techniques.

  16. Unsupervised Neural Techniques Applied to MR Brain Image Segmentation

    A. Ortiz


    Full Text Available The primary goal of brain image segmentation is to partition a given brain image into different regions representing anatomical structures. Magnetic resonance image (MRI segmentation is especially interesting, since accurate segmentation in white matter, grey matter and cerebrospinal fluid provides a way to identify many brain disorders such as dementia, schizophrenia or Alzheimer’s disease (AD. Then, image segmentation results in a very interesting tool for neuroanatomical analyses. In this paper we show three alternatives to MR brain image segmentation algorithms, with the Self-Organizing Map (SOM as the core of the algorithms. The procedures devised do not use any a priori knowledge about voxel class assignment, and results in fully-unsupervised methods for MRI segmentation, making it possible to automatically discover different tissue classes. Our algorithm has been tested using the images from the Internet Brain Image Repository (IBSR outperforming existing methods, providing values for the average overlap metric of 0.7 for the white and grey matter and 0.45 for the cerebrospinal fluid. Furthermore, it also provides good results for high-resolution MR images provided by the Nuclear Medicine Service of the “Virgen de las Nieves” Hospital (Granada, Spain.

  17. A Bayesian Approach for Image Segmentation with Shape Priors

    Chang, Hang; Yang, Qing; Parvin, Bahram


    Color and texture have been widely used in image segmentation; however, their performance is often hindered by scene ambiguities, overlapping objects, or missingparts. In this paper, we propose an interactive image segmentation approach with shape prior models within a Bayesian framework. Interactive features, through mouse strokes, reduce ambiguities, and the incorporation of shape priors enhances quality of the segmentation where color and/or texture are not solely adequate. The novelties of our approach are in (i) formulating the segmentation problem in a well-de?ned Bayesian framework with multiple shape priors, (ii) ef?ciently estimating parameters of the Bayesian model, and (iii) multi-object segmentation through user-speci?ed priors. We demonstrate the effectiveness of our method on a set of natural and synthetic images.

  18. CT image segmentation using FEM with optimized boundary condition.

    Hiroyuki Hishida

    Full Text Available The authors propose a CT image segmentation method using structural analysis that is useful for objects with structural dynamic characteristics. Motivation of our research is from the area of genetic activity. In order to reveal the roles of genes, it is necessary to create mutant mice and measure differences among them by scanning their skeletons with an X-ray CT scanner. The CT image needs to be manually segmented into pieces of the bones. It is a very time consuming to manually segment many mutant mouse models in order to reveal the roles of genes. It is desirable to make this segmentation procedure automatic. Although numerous papers in the past have proposed segmentation techniques, no general segmentation method for skeletons of living creatures has been established. Against this background, the authors propose a segmentation method based on the concept of destruction analogy. To realize this concept, structural analysis is performed using the finite element method (FEM, as structurally weak areas can be expected to break under conditions of stress. The contribution of the method is its novelty, as no studies have so far used structural analysis for image segmentation. The method's implementation involves three steps. First, finite elements are created directly from the pixels of a CT image, and then candidates are also selected in areas where segmentation is thought to be appropriate. The second step involves destruction analogy to find a single candidate with high strain chosen as the segmentation target. The boundary conditions for FEM are also set automatically. Then, destruction analogy is implemented by replacing pixels with high strain as background ones, and this process is iterated until object is decomposed into two parts. Here, CT image segmentation is demonstrated using various types of CT imagery.

  19. Development of a biosensor microarray towards food screening using imaging surface plasmon resonance

    Rebe, S.; Bremer, M.G.E.G.; Giesbers, M.; Norde, W.


    In this study we examined the possibilities of implementing direct and competitive immunoassay formats for small and large molecule detection on a microarray, using IBIS imaging surface plasmon resonance (iSPR) system. First, IBIS iSPR optics performance was evaluated. Using a glycerol calibration c

  20. Development of a biosensor microarray towards food screening, using imaging surface plasmon resonance

    Raz, Sabina Rebe; Bremer, Maria G. E. G.; Giesbers, Marcel; Norde, Willem


    In this study we examined the possibilities of implementing direct and competitive immunoassay formats for small and large molecule detection on a microarray, using IBIS imaging surface plasmon resonance (iSPR) system. First, IBIS iSPR optics performance was evaluated. Using a glycerol calibration c

  1. Ontology-based, Tissue MicroArray oriented, image centered tissue bank

    Viti Federica


    Full Text Available Abstract Background Tissue MicroArray technique is becoming increasingly important in pathology for the validation of experimental data from transcriptomic analysis. This approach produces many images which need to be properly managed, if possible with an infrastructure able to support tissue sharing between institutes. Moreover, the available frameworks oriented to Tissue MicroArray provide good storage for clinical patient, sample treatment and block construction information, but their utility is limited by the lack of data integration with biomolecular information. Results In this work we propose a Tissue MicroArray web oriented system to support researchers in managing bio-samples and, through the use of ontologies, enables tissue sharing aimed at the design of Tissue MicroArray experiments and results evaluation. Indeed, our system provides ontological description both for pre-analysis tissue images and for post-process analysis image results, which is crucial for information exchange. Moreover, working on well-defined terms it is then possible to query web resources for literature articles to integrate both pathology and bioinformatics data. Conclusions Using this system, users associate an ontology-based description to each image uploaded into the database and also integrate results with the ontological description of biosequences identified in every tissue. Moreover, it is possible to integrate the ontological description provided by the user with a full compliant gene ontology definition, enabling statistical studies about correlation between the analyzed pathology and the most commonly related biological processes.

  2. A comparative study of Image Region-Based Segmentation Algorithms

    Lahouaoui LALAOUI


    Full Text Available Image segmentation has recently become an essential step in image processing as it mainly conditions the interpretation which is done afterwards. It is still difficult to justify the accuracy of a segmentation algorithm, regardless of the nature of the treated image. In this paper we perform an objective comparison of region-based segmentation techniques such as supervised and unsupervised deterministic classification, non-parametric and parametric probabilistic classification. Eight methods among the well-known and used in the scientific community have been selected and compared. The Martin’s(GCE, LCE, probabilistic Rand Index (RI, Variation of Information (VI and Boundary Displacement Error (BDE criteria are used to evaluate the performance of these algorithms on Magnetic Resonance (MR brain images, synthetic MR image, and synthetic images. MR brain image are composed of the gray matter (GM, white matter (WM and cerebrospinal fluid (CSF and others, and the synthetic MR image composed of the same for real image and the plus edema, and the tumor. Results show that segmentation is an image dependent process and that some of the evaluated methods are well suited for a better segmentation.

  3. Remote Sensing Image Registration with Line Segments and Their Intersections

    Chengjin Lyu


    Full Text Available Image registration is a basic but essential step for remote sensing image processing, and finding stable features in multitemporal images is one of the most considerable challenges in the field. The main shape contours of artificial objects (e.g., roads, buildings, farmlands, and airports can be generally described as a group of line segments, which are stable features, even in images with evident background changes (e.g., images taken before and after a disaster. In this study, a registration method that uses line segments and their intersections is proposed for multitemporal remote sensing images. First, line segments are extracted in image pyramids to unify the scales of the reference image and the test image. Then, a line descriptor based on the gradient distribution of local areas is constructed, and the segments are matched in image pyramids. Lastly, triplets of intersections of matching lines are selected to estimate affine transformation between two images. Additional corresponding intersections are provided based on the estimated transformation, and an iterative process is adopted to remove outliers. The performance of the proposed method is tested on a variety of optical remote sensing image pairs, including synthetic and real data. Compared with existing methods, our method can provide more accurate registration results, even in images with significant background changes.

  4. Interactive co-segmentation of objects in image collections

    Batra, Dhruv; Parikh, Devi


    The authors survey a recent technique in computer vision called Interactive Co-segmentation, which is the task of simultaneously extracting common foreground objects from multiple related images. They survey several of the algorithms, present underlying common ideas, and give an overview of applications of object co-segmentation.

  5. Comparison of automated and manual segmentation of hippocampus MR images

    Haller, John W.; Christensen, Gary E.; Miller, Michael I.; Joshi, Sarang C.; Gado, Mokhtar; Csernansky, John G.; Vannier, Michael W.


    The precision and accuracy of area estimates from magnetic resonance (MR) brain images and using manual and automated segmentation methods are determined. Areas of the human hippocampus were measured to compare a new automatic method of segmentation with regions of interest drawn by an expert. MR images of nine normal subjects and nine schizophrenic patients were acquired with a 1.5-T unit (Siemens Medical Systems, Inc., Iselin, New Jersey). From each individual MPRAGE 3D volume image a single comparable 2-D slice (matrix equals 256 X 256) was chosen which corresponds to the same coronal slice of the hippocampus. The hippocampus was first manually segmented, then segmented using high dimensional transformations of a digital brain atlas to individual brain MR images. The repeatability of a trained rater was assessed by comparing two measurements from each individual subject. Variability was also compared within and between subject groups of schizophrenics and normal subjects. Finally, the precision and accuracy of automated segmentation of hippocampal areas were determined by comparing automated measurements to manual segmentation measurements made by the trained rater on MR and brain slice images. The results demonstrate the high repeatability of area measurement from MR images of the human hippocampus. Automated segmentation using high dimensional transformations from a digital brain atlas provides repeatability superior to that of manual segmentation. Furthermore, the validity of automated measurements was demonstrated by a high correlation with manual segmentation measurements made by a trained rater. Quantitative morphometry of brain substructures (e.g. hippocampus) is feasible by use of a high dimensional transformation of a digital brain atlas to an individual MR image. This method automates the search for neuromorphological correlates of schizophrenia by a new mathematically robust method with unprecedented sensitivity to small local and regional differences.

  6. Image segmentation evaluation for very-large datasets

    Reeves, Anthony P.; Liu, Shuang; Xie, Yiting


    With the advent of modern machine learning methods and fully automated image analysis there is a need for very large image datasets having documented segmentations for both computer algorithm training and evaluation. Current approaches of visual inspection and manual markings do not scale well to big data. We present a new approach that depends on fully automated algorithm outcomes for segmentation documentation, requires no manual marking, and provides quantitative evaluation for computer algorithms. The documentation of new image segmentations and new algorithm outcomes are achieved by visual inspection. The burden of visual inspection on large datasets is minimized by (a) customized visualizations for rapid review and (b) reducing the number of cases to be reviewed through analysis of quantitative segmentation evaluation. This method has been applied to a dataset of 7,440 whole-lung CT images for 6 different segmentation algorithms designed to fully automatically facilitate the measurement of a number of very important quantitative image biomarkers. The results indicate that we could achieve 93% to 99% successful segmentation for these algorithms on this relatively large image database. The presented evaluation method may be scaled to much larger image databases.

  7. Comparison of algorithms for ultrasound image segmentation without ground truth

    Sikka, Karan; Deserno, Thomas M.


    Image segmentation is a pre-requisite to medical image analysis. A variety of segmentation algorithms have been proposed, and most are evaluated on a small dataset or based on classification of a single feature. The lack of a gold standard (ground truth) further adds to the discrepancy in these comparisons. This work proposes a new methodology for comparing image segmentation algorithms without ground truth by building a matrix called region-correlation matrix. Subsequently, suitable distance measures are proposed for quantitative assessment of similarity. The first measure takes into account the degree of region overlap or identical match. The second considers the degree of splitting or misclassification by using an appropriate penalty term. These measures are shown to satisfy the axioms of a quasi-metric. They are applied for a comparative analysis of synthetic segmentation maps to show their direct correlation with human intuition of similar segmentation. Since ultrasound images are difficult to segment and usually lack a ground truth, the measures are further used to compare the recently proposed spectral clustering algorithm (encoding spatial and edge information) with standard k-means over abdominal ultrasound images. Improving the parameterization and enlarging the feature space for k-means steadily increased segmentation quality to that of spectral clustering.

  8. Automatic Image Segmentation Using Active Contours with Univariate Marginal Distribution

    I. Cruz-Aceves


    Full Text Available This paper presents a novel automatic image segmentation method based on the theory of active contour models and estimation of distribution algorithms. The proposed method uses the univariate marginal distribution model to infer statistical dependencies between the control points on different active contours. These contours have been generated through an alignment process of reference shape priors, in order to increase the exploration and exploitation capabilities regarding different interactive segmentation techniques. This proposed method is applied in the segmentation of the hollow core in microscopic images of photonic crystal fibers and it is also used to segment the human heart and ventricular areas from datasets of computed tomography and magnetic resonance images, respectively. Moreover, to evaluate the performance of the medical image segmentations compared to regions outlined by experts, a set of similarity measures has been adopted. The experimental results suggest that the proposed image segmentation method outperforms the traditional active contour model and the interactive Tseng method in terms of segmentation accuracy and stability.

  9. Spectral segmentation of polygonized images with normalized cuts

    Matsekh, Anna [Los Alamos National Laboratory; Skurikhin, Alexei [Los Alamos National Laboratory; Rosten, Edward [UNIV OF CAMBRIDGE


    We analyze numerical behavior of the eigenvectors corresponding to the lowest eigenvalues of the generalized graph Laplacians arising in the Normalized Cuts formulations of the image segmentation problem on coarse polygonal grids.

  10. Skin lesion image segmentation using Delaunay Triangulation for melanoma detection.

    Pennisi, Andrea; Bloisi, Domenico D; Nardi, Daniele; Giampetruzzi, Anna Rita; Mondino, Chiara; Facchiano, Antonio


    Developing automatic diagnostic tools for the early detection of skin cancer lesions in dermoscopic images can help to reduce melanoma-induced mortality. Image segmentation is a key step in the automated skin lesion diagnosis pipeline. In this paper, a fast and fully-automatic algorithm for skin lesion segmentation in dermoscopic images is presented. Delaunay Triangulation is used to extract a binary mask of the lesion region, without the need of any training stage. A quantitative experimental evaluation has been conducted on a publicly available database, by taking into account six well-known state-of-the-art segmentation methods for comparison. The results of the experimental analysis demonstrate that the proposed approach is highly accurate when dealing with benign lesions, while the segmentation accuracy significantly decreases when melanoma images are processed. This behavior led us to consider geometrical and color features extracted from the binary masks generated by our algorithm for classification, achieving promising results for melanoma detection.

  11. Segmentation techniques for extracting humans from thermal images

    Dickens, JS


    Full Text Available A pedestrian detection system for underground mine vehicles is being developed that requires the segmentation of people from thermal images in underground mine tunnels. A number of thresholding techniques are outlined and their performance on a...

  12. Software Agent with Reinforcement Learning Approach for Medical Image Segmentation

    Mahsa Chitsaz; Chaw Seng Woo


    Many image segmentation solutions are problem-based. Medical images have very similar grey level and texture among the interested objects. Therefore, medical image segmentation requires improvements although there have been researches done since the last few decades. We design a self-learning framework to extract several objects of interest simultaneously from Computed Tomography (CT) images. Our segmentation method has a learning phase that is based on reinforcement learning (RL) system. Each RL agent works on a particular sub-image of an input image to find a suitable value for each object in it. The RL system is define by state, action and reward. We defined some actions for each state in the sub-image. A reward function computes reward for each action of the RL agent. Finally, the valuable information, from discovering all states of the interest objects, will be stored in a Q-matrix and the final result can be applied in segmentation of similar images. The experimental results for cranial CT images demonstrated segmentation accuracy above 95%.

  13. Segmentation of Fingerprint Images Using Linear Classifier

    Xinjian Chen


    Full Text Available An algorithm for the segmentation of fingerprints and a criterion for evaluating the block feature are presented. The segmentation uses three block features: the block clusters degree, the block mean information, and the block variance. An optimal linear classifier has been trained for the classification per block and the criteria of minimal number of misclassified samples are used. Morphology has been applied as postprocessing to reduce the number of classification errors. The algorithm is tested on FVC2002 database, only 2.45% of the blocks are misclassified, while the postprocessing further reduces this ratio. Experiments have shown that the proposed segmentation method performs very well in rejecting false fingerprint features from the noisy background.

  14. Local and global evaluation for remote sensing image segmentation

    Su, Tengfei; Zhang, Shengwei


    In object-based image analysis, how to produce accurate segmentation is usually a very important issue that needs to be solved before image classification or target recognition. The study for segmentation evaluation method is key to solving this issue. Almost all of the existent evaluation strategies only focus on the global performance assessment. However, these methods are ineffective for the situation that two segmentation results with very similar overall performance have very different local error distributions. To overcome this problem, this paper presents an approach that can both locally and globally quantify segmentation incorrectness. In doing so, region-overlapping metrics are utilized to quantify each reference geo-object's over and under-segmentation error. These quantified error values are used to produce segmentation error maps which have effective illustrative power to delineate local segmentation error patterns. The error values for all of the reference geo-objects are aggregated through using area-weighted summation, so that global indicators can be derived. An experiment using two scenes of very different high resolution images showed that the global evaluation part of the proposed approach was almost as effective as other two global evaluation methods, and the local part was a useful complement to comparing different segmentation results.

  15. Fuzzy local Gaussian mixture model for brain MR image segmentation.

    Ji, Zexuan; Xia, Yong; Sun, Quansen; Chen, Qiang; Xia, Deshen; Feng, David Dagan


    Accurate brain tissue segmentation from magnetic resonance (MR) images is an essential step in quantitative brain image analysis. However, due to the existence of noise and intensity inhomogeneity in brain MR images, many segmentation algorithms suffer from limited accuracy. In this paper, we assume that the local image data within each voxel's neighborhood satisfy the Gaussian mixture model (GMM), and thus propose the fuzzy local GMM (FLGMM) algorithm for automated brain MR image segmentation. This algorithm estimates the segmentation result that maximizes the posterior probability by minimizing an objective energy function, in which a truncated Gaussian kernel function is used to impose the spatial constraint and fuzzy memberships are employed to balance the contribution of each GMM. We compared our algorithm to state-of-the-art segmentation approaches in both synthetic and clinical data. Our results show that the proposed algorithm can largely overcome the difficulties raised by noise, low contrast, and bias field, and substantially improve the accuracy of brain MR image segmentation.

  16. Medical image segmentation using level set and watershed transform

    Zhu, Fuping; Tian, Jie


    One of the most popular level set algorithms is the so-called fast marching method. In this paper, a medical image segmentation algorithm is proposed based on the combination of fast marching method and watershed transformation. First, the original image is smoothed using nonlinear diffusion filter, then the smoothed image is over-segmented by the watershed algorithm. Last, the image is segmented automatically using the modified fast marching method. Due to introducing over-segmentation, the arrival time the seeded point to the boundary of region should be calculated. For other pixels inside the region of the seeded point, the arrival time is not calculated because of the region homogeneity. So the algorithm"s speed improves greatly. Moreover, the speed function is redefined based on the statistical similarity degree of the nearby regions. We also extend our algorithm to 3D circumstance and segment medical image series. Experiments show that the algorithm can fast and accurately obtain segmentation results of medical images.

  17. Automatic Image Segmentation based on MRF-MAP

    Qiyang, Zhao


    Solving the Maximum a Posteriori on Markov Random Field, MRF-MAP, is a prevailing method in recent interactive image segmentation tools. Although mathematically explicit in its computational targets, and impressive for the segmentation quality, MRF-MAP is hard to accomplish without the interactive information from users. So it is rarely adopted in the automatic style up to today. In this paper, we present an automatic image segmentation algorithm, NegCut, based on the approximation to MRF-MAP. First we prove MRF-MAP is NP-hard when the probabilistic models are unknown, and then present an approximation function in the form of minimum cuts on graphs with negative weights. Finally, the binary segmentation is taken from the largest eigenvector of the target matrix, with a tuned version of the Lanczos eigensolver. It is shown competitive at the segmentation quality in our experiments.

  18. Unsupervised fuzzy segmentation of 3D magnetic resonance brain images

    Velthuizen, Robert P.; Hall, Lawrence O.; Clarke, Laurence P.; Bensaid, Amine M.; Arrington, J. A.; Silbiger, Martin L.


    Unsupervised fuzzy methods are proposed for segmentation of 3D Magnetic Resonance images of the brain. Fuzzy c-means (FCM) has shown promising results for segmentation of single slices. FCM has been investigated for volume segmentations, both by combining results of single slices and by segmenting the full volume. Different strategies and initializations have been tried. In particular, two approaches have been used: (1) a method by which, iteratively, the furthest sample is split off to form a new cluster center, and (2) the traditional FCM in which the membership grade matrix is initialized in some way. Results have been compared with volume segmentations by k-means and with two supervised methods, k-nearest neighbors and region growing. Results of individual segmentations are presented as well as comparisons on the application of the different methods to a number of tumor patient data sets.

  19. Overlapping image segmentation for context-dependent anomaly detection

    Theiler, James; Prasad, Lakshman


    The challenge of finding small targets in big images lies in the characterization of the background clutter. The more homogeneous the background, the more distinguishable a typical target will be from its background. One way to homogenize the background is to segment the image into distinct regions, each of which is individually homogeneous, and then to treat each region separately. In this paper we will report on experiments in which the target is unspecified (it is an anomaly), and various segmentation strategies are employed, including an adaptive hierarchical tree-based scheme. We find that segmentations that employ overlap achieve better performance in the low false alarm rate regime.

  20. Road Scene Segmentation from a Single Image

    J.M. Alvarez; T. Gevers; Y. LeCun; A.M. Lopez


    Road scene segmentation is important in computer vision for different applications such as autonomous driving and pedestrian detection. Recovering the 3D structure of road scenes provides relevant contextual information to improve their understanding. In this paper, we use a convolutional neural net

  1. Road Scene Segmentation from a Single Image

    Alvarez, J.M.; Gevers, T.; LeCun, Y.; Lopez, A.M.


    Road scene segmentation is important in computer vision for different applications such as autonomous driving and pedestrian detection. Recovering the 3D structure of road scenes provides relevant contextual information to improve their understanding. In this paper, we use a convolutional neural

  2. Clustering based segmentation of text in complex color images

    毛文革; 王洪滨; 张田文


    We propose a novel scheme based on clustering analysis in color space to solve text segmentation in complex color images. Text segmentation includes automatic clustering of color space and foreground image generation. Two methods are also proposed for automatic clustering: The first one is to determine the optimal number of clusters and the second one is the fuzzy competitively clustering method based on competitively learning techniques. Essential foreground images obtained from any of the color clusters are combined into foreground images. Further performance analysis reveals the advantages of the proposed methods.

  3. Segmentation of Bacteria Image Based on Level Set Method

    WANG Hua; CHEN Chun-xiao; HU Yong-hong; YANG Wen-ge


    In biology ferment engineering, accurate statistics of the quantity of bacte-ria is one of the most important subjects. In this paper, the quantity of bacteria which was observed traditionally manuauy can be detected automatically. Image acquisition and pro-cessing system is designed to accomplish image preprocessing, image segmentation and statistics of the quantity of bacteria. Segmentation of bacteria images is successfully real-ized by means of a region-based level set method and then the quantity of bacteria is com-puted precisely, which plays an important role in optimizing the growth conditions of bac-teria.

  4. Image Segmentation by Discounted Cumulative Ranking on Maximal Cliques

    Carreira, Joao; Sminchisescu, Cristian


    We propose a mid-level image segmentation framework that combines multiple figure-ground hypothesis (FG) constrained at different locations and scales, into interpretations that tile the entire image. The problem is cast as optimization over sets of maximal cliques sampled from the graph connecting non-overlapping, putative figure-ground segment hypotheses. Potential functions over cliques combine unary Gestalt-based figure quality scores and pairwise compatibilities among spatially neighboring segments, constrained by T-junctions and the boundary interface statistics resulting from projections of real 3d scenes. Learning the model parameters is formulated as rank optimization, alternating between sampling image tilings and optimizing their potential function parameters. State of the art results are reported on both the Berkeley and the VOC2009 segmentation dataset, where a 28% improvement was achieved.

  5. The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS)

    Menze, Bjoern H.; Jakab, Andras; Bauer, Stefan


    In this paper we report the set-up and results of the Multimodal Brain Tumor Image Segmentation Benchmark (BRATS) organized in conjunction with the MICCAI 2012 and 2013 conferences. Twenty state-of-the-art tumor segmentation algorithms were applied to a set of 65 multi-contrast MR scans of low......- and high-grade glioma patients – manually annotated by up to four raters – and to 65 comparable scans generated using tumor image simulation software. Quantitative evaluations revealed considerable disagreement between the human raters in segmenting various tumor sub-regions (Dice scores in the range 74...... a hierarchical majority vote yielded segmentations that consistently ranked above all individual algorithms, indicating remaining opportunities for further methodological improvements. The BRATS image data and manual annotations continue to be publicly available through an online evaluation system as an ongoing...

  6. Image Segmentation using Multi-Coloured Active Illumination

    Tze Ki Koh


    Full Text Available In this paper, the use of active illumination is extended to image segmentation, specifically in the case of overlapping particles. This work is based on Multi-Flash Imaging (MFI, originally developed by Mitsubishi Electric Labs, to detect depth discontinuities. Illuminations of different wavelengths are projected from multiple positions, providing additional information about a scene compared to conventional segmentation techniques. Shadows are used to identify true object edges. The identification of nonoccluded particles is made possible by exploiting the fact that shadows are cast on underlying particles. Implementation issues such as selecting the appropriate colour model and number of illuminations are discussed. Image segmentation using the proposed method, canny edge detection and watershed transform are performed on overlapping beach pebbles and granite. Evaluation results confirm that the proposed method is a successful extension of the original method and reveals its increased accuracy when compared with conventional segmentation techniques.

  7. Multiphase Image Segmentation Using the Deformable Simplicial Complex Method

    Dahl, Vedrana Andersen; Christiansen, Asger Nyman; Bærentzen, Jakob Andreas


    The deformable simplicial complex method is a generic method for tracking deformable interfaces. It provides explicit interface representation, topological adaptivity, and multiphase support. As such, the deformable simplicial complex method can readily be used for representing active contours in...... in image segmentation based on deformable models. We show the benefits of using the deformable simplicial complex method for image segmentation by segmenting an image into a known number of segments characterized by distinct mean pixel intensities.......The deformable simplicial complex method is a generic method for tracking deformable interfaces. It provides explicit interface representation, topological adaptivity, and multiphase support. As such, the deformable simplicial complex method can readily be used for representing active contours...


    Li Yuancheng; Zhao Liujun; Jiao Runhai


    Abstract This paper proposes a novel phishing web image segmentation algorithm which based on improving spectral clustering.Firstly,we construct a set of points which are composed of spatial location pixels and gray levels from a given image.Secondly,the data is clustered in spectral space of the similar matrix of the set points,in order to avoid the drawbacks of K-means algorithm in the conventional spectral clustering method that is sensitive to initial clustering centroids and convergence to local optimal solution,we introduce the clone operator,Cauthy mutation to enlarge the scale of clustering centers,quantum-inspired evolutionary algorithm to find the global optimal clustering centroids.Compared with phishing web image segmentation based on K-means,experimental results show that the segmentation performance of our method gains much improvement.Moreover,our method can convergence to global optimal solution and is better in accuracy of phishing web segmentation.

  9. Vehicles Recognition Using Fuzzy Descriptors of Image Segments

    Płaczek, Bartłomiej


    In this paper a vision-based vehicles recognition method is presented. Proposed method uses fuzzy description of image segments for automatic recognition of vehicles recorded in image data. The description takes into account selected geometrical properties and shape coefficients determined for segments of reference image (vehicle model). The proposed method was implemented using reasoning system with fuzzy rules. A vehicles recognition algorithm was developed based on the fuzzy rules describing shape and arrangement of the image segments that correspond to visible parts of a vehicle. An extension of the algorithm with set of fuzzy rules defined for different reference images (and various vehicle shapes) enables vehicles classification in traffic scenes. The devised method is suitable for application in video sensors for road traffic control and surveillance systems.

  10. Image Mosaic Method Based on SIFT Features of Line Segment

    Jun Zhu


    Full Text Available This paper proposes a novel image mosaic method based on SIFT (Scale Invariant Feature Transform feature of line segment, aiming to resolve incident scaling, rotation, changes in lighting condition, and so on between two images in the panoramic image mosaic process. This method firstly uses Harris corner detection operator to detect key points. Secondly, it constructs directed line segments, describes them with SIFT feature, and matches those directed segments to acquire rough point matching. Finally, Ransac method is used to eliminate wrong pairs in order to accomplish image mosaic. The results from experiment based on four pairs of images show that our method has strong robustness for resolution, lighting, rotation, and scaling.

  11. Evaluating the impact of image preprocessing on iris segmentation

    José F. Valencia-Murillo


    Full Text Available Segmentation is one of the most important stages in iris recognition systems. In this paper, image preprocessing algorithms are applied in order to evaluate their impact on successful iris segmentation. The preprocessing algorithms are based on histogram adjustment, Gaussian filters and suppression of specular reflections in human eye images. The segmentation method introduced by Masek is applied on 199 images acquired under unconstrained conditions, belonging to the CASIA-irisV3 database, before and after applying the preprocessing algorithms. Then, the impact of image preprocessing algorithms on the percentage of successful iris segmentation is evaluated by means of a visual inspection of images in order to determine if circumferences of iris and pupil were detected correctly. An increase from 59% to 73% in percentage of successful iris segmentation is obtained with an algorithm that combine elimination of specular reflections, followed by the implementation of a Gaussian filter having a 5x5 kernel. The results highlight the importance of a preprocessing stage as a previous step in order to improve the performance during the edge detection and iris segmentation processes.

  12. A New Approach to Lung Image Segmentation using Fuzzy Possibilistic C-Means Algorithm

    Gomathi, M


    Image segmentation is a vital part of image processing. Segmentation has its application widespread in the field of medical images in order to diagnose curious diseases. The same medical images can be segmented manually. But the accuracy of image segmentation using the segmentation algorithms is more when compared with the manual segmentation. In the field of medical diagnosis an extensive diversity of imaging techniques is presently available, such as radiography, computed tomography (CT) and magnetic resonance imaging (MRI). Medical image segmentation is an essential step for most consequent image analysis tasks. Although the original FCM algorithm yields good results for segmenting noise free images, it fails to segment images corrupted by noise, outliers and other imaging artifact. This paper presents an image segmentation approach using Modified Fuzzy C-Means (FCM) algorithm and Fuzzy Possibilistic c-means algorithm (FPCM). This approach is a generalized version of standard Fuzzy CMeans Clustering (FCM) ...

  13. Detection and analysis system for hybridization images of lab-in-a-tube microarray

    LIU Quanjun; ZHOU Qin; BAI Yunfei; GE Qinyu; LU Zuhong


    A lab-in-a-tube microarray system is developed for sample inspection and signal detection by fabricating a flat transparent window cap of the Eppendorf tube. The oli- gonucleotide microarray is immobilized on the inner surface of the cap. A small vessel is placed in an Eppendorf tube for storing hybridization solutions. With the microarray system, the full biochemical processes, including gene fragment amplification, fluorescence labeling, hybridization, and fluorescence detection, have been performed in the sealed tube without opening the cap. The images are obtained from a fluorescence microscope and captured by a CCD, and the data are transported to a computer through the universal serial bus (USB). After noise reduction, signal intensity is determined from hybridization image and the presence of gene fragments is identified. The final data output includes sample information, process steps, and hybridization results. A lab-in- a-tube microarray system for detecting ten respiratory viruses at a single detection is designed. High detection throug- hput and accuracy have been demonstrated with the system.

  14. Deep learning for tissue microarray image-based outcome prediction in patients with colorectal cancer

    Bychkov, Dmitrii; Turkki, Riku; Haglund, Caj; Linder, Nina; Lundin, Johan


    Recent advances in computer vision enable increasingly accurate automated pattern classification. In the current study we evaluate whether a convolutional neural network (CNN) can be trained to predict disease outcome in patients with colorectal cancer based on images of tumor tissue microarray samples. We compare the prognostic accuracy of CNN features extracted from the whole, unsegmented tissue microarray spot image, with that of CNN features extracted from the epithelial and non-epithelial compartments, respectively. The prognostic accuracy of visually assessed histologic grade is used as a reference. The image data set consists of digitized hematoxylin-eosin (H and E) stained tissue microarray samples obtained from 180 patients with colorectal cancer. The patient samples represent a variety of histological grades, have data available on a series of clinicopathological variables including long-term outcome and ground truth annotations performed by experts. The CNN features extracted from images of the epithelial tissue compartment significantly predicted outcome (hazard ratio (HR) 2.08; CI95% 1.04-4.16; area under the curve (AUC) 0.66) in a test set of 60 patients, as compared to the CNN features extracted from unsegmented images (HR 1.67; CI95% 0.84-3.31, AUC 0.57) and visually assessed histologic grade (HR 1.96; CI95% 0.99-3.88, AUC 0.61). As a conclusion, a deep-learning classifier can be trained to predict outcome of colorectal cancer based on images of H and E stained tissue microarray samples and the CNN features extracted from the epithelial compartment only resulted in a prognostic discrimination comparable to that of visually determined histologic grade.

  15. A new prostate segmentation approach using multispectral magnetic resonance imaging and a statistical pattern classifier

    Maan, Bianca; van der Heijden, Ferdinand; Fütterer, Jurgen J.


    Prostate segmentation is essential for calculating prostate volume, creating patient-specific prostate anatomical models and image fusion. Automatic segmentation methods are preferable because manual segmentation is timeconsuming and highly subjective. Most of the currently available segmentation

  16. Automatic segmentation of the striatum and globus pallidus using MIST: Multimodal Image Segmentation Tool

    Visser, Eelke; Keuken, Max C.; Douaud, Gwenaëlle; Gaura, Veronique; Bachoud-Levi, Anne-Catherine; Remy, Philippe; Forstmann, Birte U.; Jenkinson, Mark


    Accurate segmentation of the subcortical structures is frequently required in neuroimaging studies. Most existing methods use only a T1-weighted MRI volume to segment all supported structures and usually rely on a database of training data. We propose a new method that can use multiple image modalities simultaneously and a single reference segmentation for initialisation, without the need for a manually labelled training set. The method models intensity profiles in multiple images around the boundaries of the structure after nonlinear registration. It is trained using a set of unlabelled training data, which may be the same images that are to be segmented, and it can automatically infer the location of the physical boundary using user-specified priors. We show that the method produces high-quality segmentations of the striatum, which is clearly visible on T1-weighted scans, and the globus pallidus, which has poor contrast on such scans. The method compares favourably to existing methods, showing greater overlap with manual segmentations and better consistency. PMID:26477650

  17. An entropy-based approach to automatic image segmentation of satellite images

    Barbieri, A L; Rodrigues, F A; Bruno, O M; Costa, L da F


    An entropy-based image segmentation approach is introduced and applied to color images obtained from Google Earth. Segmentation refers to the process of partitioning a digital image in order to locate different objects and regions of interest. The application to satellite images paves the way to automated monitoring of ecological catastrophes, urban growth, agricultural activity, maritime pollution, climate changing and general surveillance. Regions representing aquatic, rural and urban areas are identified and the accuracy of the proposed segmentation methodology is evaluated. The comparison with gray level images revealed that the color information is fundamental to obtain an accurate segmentation.

  18. Laplacian forests: semantic image segmentation by guided bagging.

    Lombaert, Herve; Zikic, Darko; Criminisi, Antonio; Ayache, Nicholas


    This paper presents a new, efficient and accurate technique for the semantic segmentation of medical images. The paper builds upon the successful random decision forests model and improves on it by modifying the way in which randomness is injected into the tree training process. The contribution of this paper is two-fold. First, we replace the conventional bagging procedure (the uniform sampling of training images) with a guided bagging approach, which exploits the inherent structure and organization of the training image set. This allows the creation of decision trees that are specialized to a specific sub-type of images in the training set. Second, the segmentation of a previously unseen image happens via selection and application of only the trees that are relevant to the given test image. Tree selection is done automatically, via the learned image embedding, with more precisely a Laplacian eigenmap. We, therefore, call the proposed approach Laplacian Forests. We validate Laplacian Forests on a dataset of 256, manually segmented 3D CT scans of patients showing high variability in scanning protocols, resolution, body shape and anomalies. Compared with conventional decision forests, Laplacian Forests yield both higher training efficiency, due to the local analysis of the training image space, as well as higher segmentation accuracy, due to the specialization of the forest to image sub-types.

  19. Learning evaluation of ultrasound image segmentation using combined measures

    Fang, Mengjie; Luo, Yongkang; Ding, Mingyue


    Objective evaluation of medical image segmentation is one of the important steps for proving its validity and clinical applicability. Although there are many researches presenting segmentation methods on medical image, while with few studying the evaluation methods on their results, this paper presents a learning evaluation method with combined measures to make it as close as possible to the clinicians' judgment. This evaluation method is more quantitative and precise for the clinical diagnose. In our experiment, the same data sets include 120 segmentation results of lumen-intima boundary (LIB) and media-adventitia boundary (MAB) of carotid ultrasound images respectively. And the 15 measures of goodness method and discrepancy method are used to evaluate the different segmentation results alone. Furthermore, the experimental results showed that compared with the discrepancy method, the accuracy with the measures of goodness method is poor. Then, by combining with the measures of two methods, the average accuracy and the area under the receiver operating characteristic (ROC) curve of 2 segmentation groups are higher than 93% and 0.9 respectively. And the results of MAB are better than LIB, which proved that this novel method can effectively evaluate the segmentation results. Moreover, it lays the foundation for the non-supervised segmentation evaluation system.

  20. Automated Segmentation and Retrieval System for CT Head Images

    Tong, Hau-Lee; Ahmad Fauzi, Mohammad Faizal; Komiya, Ryoichi

    In this paper, automatic segmentation and retrieval of medical images are presented. For the segmentation, different unsupervised clustering techniques are employed to partition the Computed Tomography (CT) brain images into three regions, which are the abnormalities, cerebrospinal fluids (CSF) and brain matters. The novel segmentation method proposed is a dual level segmentation approach. The first level segmentation, which purpose is to acquire abnormal regions, uses the combination of fuzzy c-means (FCM) and k-means clustering. The second level segmentation performs either the expectation-maximization (EM) technique or the modified FCM with population-diameter independent (PDI) to segment the remaining intracranial area into CSF and brain matters. The system automatically determines which algorithm to be utilized in order to produce optimum results. The retrieval of the medical images is based on keywords such as "no abnormal region", "abnormal region(s) adjacent to the skull" and "abnormal region(s) not adjacent to the skull". Medical data from collaborating hospital are experimented and promising results are observed.

  1. Image Segmentation for Food Quality Evaluation Using Computer Vision System

    Nandhini. P


    Full Text Available Quality evaluation is an important factor in food processing industries using the computer vision system where human inspection systems provide high variability. In many countries food processing industries aims at producing defect free food materials to the consumers. Human evaluation techniques suffer from high labour costs, inconsistency and variability. Thus this paper provides various steps for identifying defects in the food material using the computer vision systems. Various steps in computer vision system are image acquisition, Preprocessing, image segmentation, feature identification and classification. The proposed framework provides the comparison of various filters where the hybrid median filter was selected as the filter with the high PSNR value and is used in preprocessing. Image segmentation techniques such as Colour based binary Image segmentation, Particle swarm optimization are compared and image segmentation parameters such as accuracy, sensitivity , specificity are calculated and found that colour based binary image segmentation is well suited for food quality evaluation. Finally this paper provides an efficient method for identifying the defected parts in food materials.

  2. Image segmentation by hierarchial agglomeration of polygons using ecological statistics

    Prasad, Lakshman; Swaminarayan, Sriram


    A method for rapid hierarchical image segmentation based on perceptually driven contour completion and scene statistics is disclosed. The method begins with an initial fine-scale segmentation of an image, such as obtained by perceptual completion of partial contours into polygonal regions using region-contour correspondences established by Delaunay triangulation of edge pixels as implemented in VISTA. The resulting polygons are analyzed with respect to their size and color/intensity distributions and the structural properties of their boundaries. Statistical estimates of granularity of size, similarity of color, texture, and saliency of intervening boundaries are computed and formulated into logical (Boolean) predicates. The combined satisfiability of these Boolean predicates by a pair of adjacent polygons at a given segmentation level qualifies them for merging into a larger polygon representing a coarser, larger-scale feature of the pixel image and collectively obtains the next level of polygonal segments in a hierarchy of fine-to-coarse segmentations. The iterative application of this process precipitates textured regions as polygons with highly convolved boundaries and helps distinguish them from objects which typically have more regular boundaries. The method yields a multiscale decomposition of an image into constituent features that enjoy a hierarchical relationship with features at finer and coarser scales. This provides a traversable graph structure from which feature content and context in terms of other features can be derived, aiding in automated image understanding tasks. The method disclosed is highly efficient and can be used to decompose and analyze large images.

  3. Weakly supervised histopathology cancer image segmentation and classification.

    Xu, Yan; Zhu, Jun-Yan; Chang, Eric I-Chao; Lai, Maode; Tu, Zhuowen


    Labeling a histopathology image as having cancerous regions or not is a critical task in cancer diagnosis; it is also clinically important to segment the cancer tissues and cluster them into various classes. Existing supervised approaches for image classification and segmentation require detailed manual annotations for the cancer pixels, which are time-consuming to obtain. In this paper, we propose a new learning method, multiple clustered instance learning (MCIL) (along the line of weakly supervised learning) for histopathology image segmentation. The proposed MCIL method simultaneously performs image-level classification (cancer vs. non-cancer image), medical image segmentation (cancer vs. non-cancer tissue), and patch-level clustering (different classes). We embed the clustering concept into the multiple instance learning (MIL) setting and derive a principled solution to performing the above three tasks in an integrated framework. In addition, we introduce contextual constraints as a prior for MCIL, which further reduces the ambiguity in MIL. Experimental results on histopathology colon cancer images and cytology images demonstrate the great advantage of MCIL over the competing methods.

  4. 3D Medical Image Segmentation Based on Rough Set Theory

    CHEN Shi-hao; TIAN Yun; WANG Yi; HAO Chong-yang


    This paper presents a method which uses multiple types of expert knowledge together in 3D medical image segmentation based on rough set theory. The focus of this paper is how to approximate a ROI (region of interest) when there are multiple types of expert knowledge. Based on rough set theory, the image can be split into three regions:positive regions; negative regions; boundary regions. With multiple knowledge we refine ROI as an intersection of all of the expected shapes with single knowledge. At last we show the results of implementing a rough 3D image segmentation and visualization system.

  5. Image segmentation by using the localized subspace iteration algorithm


    An image segmentation algorithm called"segmentation based on the localized subspace iterations"(SLSI)is proposed in this paper.The basic idea is to combine the strategies in Ncut algorithm by Shi and Malik in 2000 and the LSI by E,Li and Lu in 2007.The LSI is applied to solve an eigenvalue problem associated with the affinity matrix of an image,which makes the overall algorithm linearly scaled.The choices of the partition number,the supports and weight functions in SLSI are discussed.Numerical experiments for real images show the applicability of the algorithm.

  6. An image segmentation based method for iris feature extraction

    XU Guang-zhu; ZHANG Zai-feng; MA Yi-de


    In this article, the local anomalistic blocks such ascrypts, furrows, and so on in the iris are initially used directly asiris features. A novel image segmentation method based onintersecting cortical model (ICM) neural network was introducedto segment these anomalistic blocks. First, the normalized irisimage was put into ICM neural network after enhancement.Second, the iris features were segmented out perfectly and wereoutput in binary image type by the ICM neural network. Finally,the fourth output pulse image produced by ICM neural networkwas chosen as the iris code for the convenience of real timeprocessing. To estimate the performance of the presentedmethod, an iris recognition platform was produced and theHamming Distance between two iris codes was computed tomeasure the dissimilarity between them. The experimentalresults in CASIA vl.0 and Bath iris image databases show thatthe proposed iris feature extraction algorithm has promisingpotential in iris recognition.

  7. Medical image segmentation based on cellular neural network


    The application of cellular neural network (CNN) has made great progress in image processing. When the selected objects extraction (SOE) CNN is applied to gray scale images, its effects depend on the choice of initial points. In this paper, we take medical images as an example to analyze this limitation. Then an improved algorithm is proposed in which we can segment any gray level objects regardless of the limitation stated above. We also use the gradient information and contour detection CNN to determine the contour and ensure the veracity of segmentation effectively. Finally, we apply the improved algorithm to tumor segmentation of the human brain MR image. The experimental results show that the algorithm is practical and effective.

  8. Automated Segmentation of Cardiac Magnetic Resonance Images

    Stegmann, Mikkel Bille; Nilsson, Jens Chr.; Grønning, Bjørn A.


    Magnetic resonance imaging (MRI) has been shown to be an accurate and precise technique to assess cardiac volumes and function in a non-invasive manner and is generally considered to be the current gold-standard for cardiac imaging [1]. Measurement of ventricular volumes, muscle mass and function...

  9. Semiautomatic segmentation of liver metastases on volumetric CT images

    Yan, Jiayong [Department of Biomedical Engineering, Shanghai University of Medicine & Health Sciences, 101 Yingkou Road, Yang Pu District, Shanghai 200093 (China); Schwartz, Lawrence H.; Zhao, Binsheng, E-mail: [Department of Radiology, Columbia University Medical Center, 630 West 168th Street, New York, New York 10032 (United States)


    Purpose: Accurate segmentation and quantification of liver metastases on CT images are critical to surgery/radiation treatment planning and therapy response assessment. To date, there are no reliable methods to perform such segmentation automatically. In this work, the authors present a method for semiautomatic delineation of liver metastases on contrast-enhanced volumetric CT images. Methods: The first step is to manually place a seed region-of-interest (ROI) in the lesion on an image. This ROI will (1) serve as an internal marker and (2) assist in automatically identifying an external marker. With these two markers, lesion contour on the image can be accurately delineated using traditional watershed transformation. Density information will then be extracted from the segmented 2D lesion and help determine the 3D connected object that is a candidate of the lesion volume. The authors have developed a robust strategy to automatically determine internal and external markers for marker-controlled watershed segmentation. By manually placing a seed region-of-interest in the lesion to be delineated on a reference image, the method can automatically determine dual threshold values to approximately separate the lesion from its surrounding structures and refine the thresholds from the segmented lesion for the accurate segmentation of the lesion volume. This method was applied to 69 liver metastases (1.1–10.3 cm in diameter) from a total of 15 patients. An independent radiologist manually delineated all lesions and the resultant lesion volumes served as the “gold standard” for validation of the method’s accuracy. Results: The algorithm received a median overlap, overestimation ratio, and underestimation ratio of 82.3%, 6.0%, and 11.5%, respectively, and a median average boundary distance of 1.2 mm. Conclusions: Preliminary results have shown that volumes of liver metastases on contrast-enhanced CT images can be accurately estimated by a semiautomatic segmentation

  10. From MIP image to MRA segmentation using fuzzy set theory.

    Vermandel, Maximilien; Betrouni, Nacim; Taschner, Christian; Vasseur, Christian; Rousseau, Jean


    The aim of this paper is to describe a semi-automatic method of segmentation in magnetic resonance angiography (MRA). This method, based on fuzzy set theory, uses the information (gray levels) contained in the maximum intensity projection (MIP) image to segment the 3D vascular structure from slices. Tests have been carried out on vascular phantom and on clinical MRA images. This 3D segmentation method has proved to be satisfactory for the detection of vascular structures even for very complex shapes. Finally, this MIP-based approach is semi-automatic and produces a robust segmentation thanks to the contrast-to-noise ratio and to the slice profile which are taken into account to determine the membership of a voxel to the vascular structure.

  11. Sparse representation-based spectral clustering for SAR image segmentation

    Zhang, Xiangrong; Wei, Zhengli; Feng, Jie; Jiao, Licheng


    A new method, sparse representation based spectral clustering (SC) with Nyström method, is proposed for synthetic aperture radar (SAR) image segmentation. Different from the conventional SC, this proposed technique is developed by using the sparse coefficients which obtained by solving l1 minimization problem to construct the affinity matrix and the Nyström method is applied to alleviate the segmentation process. The advantage of our proposed method is that we do not need to select the scaling parameter in the Gaussian kernel function artificially. We apply the proposed method, k-means and the classic spectral clustering algorithm with Nyström method to SAR image segmentation. The results show that compared with the other two methods, the proposed method can obtain much better segmentation results.

  12. FBIH financial market segmentation on the basis of image factors

    Arnela Bevanda


    Full Text Available The aim of the study is to recognize, single out and define market segments useful for future marketing strategies, using certain statistical techniques on the basis of influence of various image factors of financial institutions. The survey included a total of 500 interviewees: 250 bank clients and 250 clients of insurance companies. Starting from the problem area and research goal, the following hypothesis has been formulated: Basic preferences of clients in regard of image factors while selecting financial institutions are different enough to be used as such for differentiating significant market segments of clients. Two segments have been singled out by cluster analysis and named, respectively, traditionalists and visualists. Results of the research confirmed the established hypothesis and pointed to the fact that managers in the financial institutions of the Federation of Bosnia and Herzegovina (FBIH must undertake certain corrective actions, especially when planning and implementing communication strategies, if they wish to maintain their competitiveness in serving both selected segments.

  13. A New Algorithm for Interactive Structural Image Segmentation

    Noma, Alexandre; Consularo, Luis Augusto; Cesar, Roberto M Jr; Bloch, Isabelle


    This paper proposes a novel algorithm for the problem of structural image segmentation through an interactive model-based approach. Interaction is expressed in the model creation, which is done according to user traces drawn over a given input image. Both model and input are then represented by means of attributed relational graphs derived on the fly. Appearance features are taken into account as object attributes and structural properties are expressed as relational attributes. To cope with possible topological differences between both graphs, a new structure called the deformation graph is introduced. The segmentation process corresponds to finding a labelling of the input graph that minimizes the deformations introduced in the model when it is updated with input information. This approach has shown to be faster than other segmentation methods, with competitive output quality. Therefore, the method solves the problem of multiple label segmentation in an efficient way. Encouraging results on both natural and...

  14. Variational segmentation problems using prior knowledge in imaging and vision

    Fundana, Ketut

    This dissertation addresses variational formulation of segmentation problems using prior knowledge. Variational models are among the most successful approaches for solving many Computer Vision and Image Processing problems. The models aim at finding the solution to a given energy functional defined......, prior knowledge is needed to obtain the desired solution. The introduction of shape priors in particular, has proven to be an effective way to segment objects of interests. Firstly, we propose a prior-based variational segmentation model to segment objects of interest in image sequences, that can deal...... pose invariant parameters complicate the optimization of the model. To overcome the common numerical problems associated with the step size of the pose parameters in the discretization of the pose model, we propose a novel gradient procedure for the pose estimation based on the construction...

  15. Polarization image segmentation of radiofrequency ablated porcine myocardial tissue

    Ahmad, Iftikhar; Gribble, Adam; Murtza, Iqbal; Ikram, Masroor; Pop, Mihaela; Vitkin, Alex


    Optical polarimetry has previously imaged the spatial extent of a typical radiofrequency ablated (RFA) lesion in myocardial tissue, exhibiting significantly lower total depolarization at the necrotic core compared to healthy tissue, and intermediate values at the RFA rim region. Here, total depolarization in ablated myocardium was used to segment the total depolarization image into three (core, rim and healthy) zones. A local fuzzy thresholding algorithm was used for this multi-region segmentation, and then compared with a ground truth segmentation obtained from manual demarcation of RFA core and rim regions on the histopathology image. Quantitative comparison of the algorithm segmentation results was performed with evaluation metrics such as dice similarity coefficient (DSC = 0.78 ± 0.02 and 0.80 ± 0.02), sensitivity (Sn = 0.83 ± 0.10 and 0.91 ± 0.08), specificity (Sp = 0.76 ± 0.17 and 0.72 ± 0.17) and accuracy (Acc = 0.81 ± 0.09 and 0.71 ± 0.10) for RFA core and rim regions, respectively. This automatic segmentation of parametric depolarization images suggests a novel application of optical polarimetry, namely its use in objective RFA image quantification. PMID:28380013

  16. Ultra-Fast Processing of Gigapixel Tissue MicroArray Images Using High Performance Computing

    Yinhai Wang; David McCleary; Ching-Wei Wang; Paul Kelly; Jackie James; Fennell, Dean A; Peter Hamilton


    Background: Tissue MicroArrays (TMAs) are a valuable platform for tissue based translational research and the discovery of tissue biomarkers. The digitised TMA slides or TMA Virtual Slides, are ultra-large digital images, and can contain several hundred samples. The processing of such slides is time-consuming, bottlenecking a potentially high throughput platform. Methods: A High Performance Computing (HPC) platform for the rapid analysis of TMA virtual slides is presented in this study. Using...

  17. Fabrication of DNA Microarrays on Polydopamine-Modified Gold Thin Films for SPR Imaging Measurements

    Wood, Jennifer B.; Szyndler, Megan W.; Halpern, Aaron R.; Cho, Kyunghee; Corn, Robert M.


    Polydopamine (PDA) films were fabricated on thin film gold substrates in a single-step polymerization-deposition process from dopamine solutions and then employed in the construction of robust DNA microarrays for the ultra-sensitive detection of biomolecules with nanoparticle-enhanced surface plasmon resonance (SPR) imaging. PDA multilayers with thicknesses varying from 1 to 5 nm were characterized with a combination of scanning angle SPR and AFM experiments, and 1.3 ± 0.2 nm PDA multilayers ...

  18. Breast image pre-processing for mammographic tissue segmentation.

    He, Wenda; Hogg, Peter; Juette, Arne; Denton, Erika R E; Zwiggelaar, Reyer


    During mammographic image acquisition, a compression paddle is used to even the breast thickness in order to obtain optimal image quality. Clinical observation has indicated that some mammograms may exhibit abrupt intensity change and low visibility of tissue structures in the breast peripheral areas. Such appearance discrepancies can affect image interpretation and may not be desirable for computer aided mammography, leading to incorrect diagnosis and/or detection which can have a negative impact on sensitivity and specificity of screening mammography. This paper describes a novel mammographic image pre-processing method to improve image quality for analysis. An image selection process is incorporated to better target problematic images. The processed images show improved mammographic appearances not only in the breast periphery but also across the mammograms. Mammographic segmentation and risk/density classification were performed to facilitate a quantitative and qualitative evaluation. When using the processed images, the results indicated more anatomically correct segmentation in tissue specific areas, and subsequently better classification accuracies were achieved. Visual assessments were conducted in a clinical environment to determine the quality of the processed images and the resultant segmentation. The developed method has shown promising results. It is expected to be useful in early breast cancer detection, risk-stratified screening, and aiding radiologists in the process of decision making prior to surgery and/or treatment.

  19. Nanoparticle probes and mid-infrared chemical imaging for DNA microarray detection.

    Mossoba, Magdi M; Al-Khaldi, Sufian F; Schoen, Brianna; Yakes, Betsy Jean


    To date most mid-infrared spectroscopic studies have been limited, due to lack of sensitivity, to the structural characterization of a single oligonucleotide probe immobilized over the entire surface of a gold-coated slide or other infrared substrate. By contrast, widely used and commercially available glass slides and a microarray spotter that prints approximately 120-μm-diameter DNA spots were employed in the present work. To our knowledge, mid-infrared chemical imaging (IRCI) in the external reflection mode has been applied in the present study for the first time to the detection of nanostructure-based DNA microarrays spotted on glass slides. Alkyl amine-modified oligonucleotide probes were immobilized on glass slides that had been prefunctionalized with succinimidyl ester groups. This molecular fluorophore-free method entailed the binding of gold-nanoparticle-streptavidin conjugates to biotinylated DNA targets. Hybridization was visualized by the silver enhancement of gold nanoparticles. The adlayer of silver, selectively bound only to hybridized spots in a microarray, formed the external reflective infrared substrate that was necessary for the detection of DNA hybridization by IRCI in the present proof-of-concept study. IRCI made it possible to discriminate between diffuse and specular external reflection modes. The promising qualitative results are presented herein, and the implications for quantitative determination of DNA microarrays are discussed.

  20. A simple shape prior model for iris image segmentation

    Bishop, Daniel A.; Yezzi, Anthony, Jr.


    In order to make biometric systems faster and more user-friendly, lower-quality images must be accepted. A major hurdle in this task is accurate segmentation of the boundaries of the iris in these images. Quite commonly, circle-fitting is used to approximate the boundaries of the inner (pupil) and outer (limbic) boundaries of the iris, but this assumption does not hold for off-axis or otherwise non-circular boundaries. In this paper we present a novel, foundational method for elliptical segmentation of off-axis iris images. This method uses active contours with constrained flow to achieve a simplified form of shape prior active contours. This is done by calculating a region-based contour evolution and projecting it upon a properly chosen set of vectors to confine it to a class of shapes. In this case, that class of shapes is ellipses. This serves to regularize the contour, simplifying the curve evolution and preventing the development of irregularities that present challenges in iris segmentation. The proposed method is tested using images from the UBIRIS v.1 and CASIA-IrisV3 image data sets, with both near-ideal and off-axis images. Additional testing has been performed using the WVU Off Axis/Angle Iris Dataset, Release 1. By avoiding many of the assumptions commonly used in iris segmentation methods, the proposed method is able to accurately fit elliptical boundaries to off-axis images.

  1. Dynamic Programming Using Polar Variance for Image Segmentation.

    Rosado-Toro, Jose A; Altbach, Maria I; Rodriguez, Jeffrey J


    When using polar dynamic programming (PDP) for image segmentation, the object size is one of the main features used. This is because if size is left unconstrained the final segmentation may include high-gradient regions that are not associated with the object. In this paper, we propose a new feature, polar variance, which allows the algorithm to segment objects of different sizes without the need for training data. The polar variance is the variance in a polar region between a user-selected origin and a pixel we want to analyze. We also incorporate a new technique that allows PDP to segment complex shapes by finding low-gradient regions and growing them. The experimental analysis consisted on comparing our technique with different active contour segmentation techniques on a series of tests. The tests consisted on robustness to additive Gaussian noise, segmentation accuracy with different grayscale images and finally robustness to algorithm-specific parameters. Experimental results show that our technique performs favorably when compared to other segmentation techniques.

  2. Interactive Image Segmentation Framework Based On Control Theory.

    Zhu, Liangjia; Kolesov, Ivan; Karasev, Peter; Tannenbaum, Allen


    Segmentation of anatomical structures in medical imagery is a key step in a variety of clinical applications. Designing a generic, automated method that works for various structures and imaging modalities is a daunting task. Instead of proposing a new specific segmentation algorithm, in this paper, we present a general design principle on how to integrate user interactions from the perspective of control theory. In this formulation, Lyapunov stability analysis is employed to design and analyze an interactive segmentation system. The effectiveness and robustness of the proposed method are demonstrated.

  3. Cardiac MR image segmentation using CHNN and level set method

    王洪元; 周则明; 王平安; 夏德深


    Although cardiac magnetic resonance imaging (MRI) can provide high spatial resolution image, the area gray level inhomogenization, weak boundary and artifact often can be found in MR images. So, the MR images segmentation using the gradient-based methods is poor in quality and efficiency. An algorithm, based on the competitive hopfield neural network (CHNN) and the curve propagation, is proposed for cardiac MR images segmentation in this paper. The algorithm is composed of two phases. In first phase, a CHNN is used to classify the image objects, and to make gray level homogenization and to recognize weak boundaries in objects. In second phase, based on the classified results, the level set velocity function is created and the object boundaries are extracted with the curve propagation algorithm of the narrow band-based level set. The test results are promising and encouraging.

  4. Medical image segmentation on GPUs--a comprehensive review.

    Smistad, Erik; Falch, Thomas L; Bozorgi, Mohammadmehdi; Elster, Anne C; Lindseth, Frank


    Segmentation of anatomical structures, from modalities like computed tomography (CT), magnetic resonance imaging (MRI) and ultrasound, is a key enabling technology for medical applications such as diagnostics, planning and guidance. More efficient implementations are necessary, as most segmentation methods are computationally expensive, and the amount of medical imaging data is growing. The increased programmability of graphic processing units (GPUs) in recent years have enabled their use in several areas. GPUs can solve large data parallel problems at a higher speed than the traditional CPU, while being more affordable and energy efficient than distributed systems. Furthermore, using a GPU enables concurrent visualization and interactive segmentation, where the user can help the algorithm to achieve a satisfactory result. This review investigates the use of GPUs to accelerate medical image segmentation methods. A set of criteria for efficient use of GPUs are defined and each segmentation method is rated accordingly. In addition, references to relevant GPU implementations and insight into GPU optimization are provided and discussed. The review concludes that most segmentation methods may benefit from GPU processing due to the methods' data parallel structure and high thread count. However, factors such as synchronization, branch divergence and memory usage can limit the speedup. Copyright © 2014 The Authors. Published by Elsevier B.V. All rights reserved.

  5. Image Segmentation of Historical Handwriting from Palm Leaf Manuscripts

    Surinta, Olarik; Chamchong, Rapeeporn

    Palm leaf manuscripts were one of the earliest forms of written media and were used in Southeast Asia to store early written knowledge about subjects such as medicine, Buddhist doctrine and astrology. Therefore, historical handwritten palm leaf manuscripts are important for people who like to learn about historical documents, because we can learn more experience from them. This paper presents an image segmentation of historical handwriting from palm leaf manuscripts. The process is composed of three steps: 1) background elimination to separate text and background by Otsu's algorithm 2) line segmentation and 3) character segmentation by histogram of image. The end result is the character's image. The results from this research may be applied to optical character recognition (OCR) in the future.

  6. Sub-Markov Random Walk for Image Segmentation.

    Dong, Xingping; Shen, Jianbing; Shao, Ling; Van Gool, Luc


    A novel sub-Markov random walk (subRW) algorithm with label prior is proposed for seeded image segmentation, which can be interpreted as a traditional random walker on a graph with added auxiliary nodes. Under this explanation, we unify the proposed subRW and other popular random walk (RW) algorithms. This unifying view will make it possible for transferring intrinsic findings between different RW algorithms, and offer new ideas for designing novel RW algorithms by adding or changing auxiliary nodes. To verify the second benefit, we design a new subRW algorithm with label prior to solve the segmentation problem of objects with thin and elongated parts. The experimental results on both synthetic and natural images with twigs demonstrate that the proposed subRW method outperforms previous RW algorithms for seeded image segmentation.

  7. Segmentation of the mouse hippocampal formation in magnetic resonance images.

    Richards, Kay; Watson, Charles; Buckley, Rachel F; Kurniawan, Nyoman D; Yang, Zhengyi; Keller, Marianne D; Beare, Richard; Bartlett, Perry F; Egan, Gary F; Galloway, Graham J; Paxinos, George; Petrou, Steven; Reutens, David C


    The hippocampal formation plays an important role in cognition, spatial navigation, learning, and memory. High resolution magnetic resonance (MR) imaging makes it possible to study in vivo changes in the hippocampus over time and is useful for comparing hippocampal volume and structure in wild type and mutant mice. Such comparisons demand a reliable way to segment the hippocampal formation. We have developed a method for the systematic segmentation of the hippocampal formation using the perfusion-fixed C57BL/6 mouse brain for application in longitudinal and comparative studies. Our aim was to develop a guide for segmenting over 40 structures in an adult mouse brain using 30 μm isotropic resolution images acquired with a 16.4 T MR imaging system and combined using super-resolution reconstruction.

  8. An Improved Image Segmentation Algorithm Based on MET Method

    Z. A. Abo-Eleneen


    Full Text Available Image segmentation is a basic component of many computer vision systems and pattern recognition. Thresholding is a simple but effective method to separate objects from the background. A commonly used method, Kittler and Illingworth's minimum error thresholding (MET, improves the image segmentation effect obviously. Its simpler and easier to implement. However, it fails in the presence of skew and heavy-tailed class-conditional distributions or if the histogram is unimodal or close to unimodal. The Fisher information (FI measure is an important concept in statistical estimation theory and information theory. Employing the FI measure, an improved threshold image segmentation algorithm FI-based extension of MET is developed. Comparing with the MET method, the improved method in general can achieve more robust performance when the data for either class is skew and heavy-tailed.

  9. Anterior Segment Imaging in Ocular Surface Squamous Neoplasia

    Sally S. Ong


    Full Text Available Recent advances in anterior segment imaging have transformed the way ocular surface squamous neoplasia (OSSN is diagnosed and monitored. Ultrasound biomicroscopy (UBM has been reported to be useful primarily in the assessment of intraocular invasion and metastasis. In vivo confocal microscopy (IVCM shows enlarged and irregular nuclei with hyperreflective cells in OSSN lesions and this has been found to correlate with histopathology findings. Anterior segment optical coherence tomography (AS-OCT demonstrates thickened hyperreflective epithelium with an abrupt transition between abnormal and normal epithelium in OSSN lesions and this has also been shown to mimic histopathology findings. Although there are limitations to each of these imaging modalities, they can be useful adjunctive tools in the diagnosis of OSSN and could greatly assist the clinician in the management of OSSN patients. Nevertheless, anterior segment imaging has not replaced histopathology’s role as the gold standard in confirming diagnosis.

  10. Automatic Segmentation of Dermoscopic Images by Iterative Classification

    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.

  11. An adaptive multi-feature segmentation model for infrared image

    Zhang, Tingting; Han, Jin; Zhang, Yi; Bai, Lianfa


    Active contour models (ACM) have been extensively applied to image segmentation, conventional region-based active contour models only utilize global or local single feature information to minimize the energy functional to drive the contour evolution. Considering the limitations of original ACMs, an adaptive multi-feature segmentation model is proposed to handle infrared images with blurred boundaries and low contrast. In the proposed model, several essential local statistic features are introduced to construct a multi-feature signed pressure function (MFSPF). In addition, we draw upon the adaptive weight coefficient to modify the level set formulation, which is formed by integrating MFSPF with local statistic features and signed pressure function with global information. Experimental results demonstrate that the proposed method can make up for the inadequacy of the original method and get desirable results in segmenting infrared images.

  12. Automated Segmentability Index for Layer Segmentation of Macular SD-OCT Images

    Lee, K.; Buitendijk, G.H.; Bogunovic, H.; Springelkamp, H.; Hofman, A.; Wahle, A.; Sonka, M.; Vingerling, J.R.; Klaver, C.C.W.; Abramoff, M.D.


    PURPOSE: To automatically identify which spectral-domain optical coherence tomography (SD-OCT) scans will provide reliable automated layer segmentations for more accurate layer thickness analyses in population studies. METHODS: Six hundred ninety macular SD-OCT image volumes (6.0 x 6.0 x 2.3 mm3) we

  13. SAR image segmentation using MSER and improved spectral clustering

    Gui, Yang; Zhang, Xiaohu; Shang, Yang


    A novel approach is presented for synthetic aperture radar (SAR) image segmentation. By incorporating the advantages of maximally stable extremal regions (MSER) algorithm and spectral clustering (SC) method, the proposed approach provides effective and robust segmentation. First, the input image is transformed from a pixel-based to a region-based model by using the MSER algorithm. The input image after MSER procedure is composed of some disjoint regions. Then the regions are treated as nodes in the image plane, and a graph structure is applied to represent them. Finally, the improved SC is used to perform globally optimal clustering, by which the result of image segmentation can be generated. To avoid some incorrect partitioning when considering each region as one graph node, we assign different numbers of nodes to represent the regions according to area ratios among the regions. In addition, K-harmonic means instead of K-means is applied in the improved SC procedure in order to raise its stability and performance. Experimental results show that the proposed approach is effective on SAR image segmentation and has the advantage of calculating quickly.

  14. Computer Based Melanocytic and Nevus Image Enhancement and Segmentation

    Jamil, Uzma; Khalid, Shehzad; Abbas, Sarmad; Saleem, Kashif


    Digital dermoscopy aids dermatologists in monitoring potentially cancerous skin lesions. Melanoma is the 5th common form of skin cancer that is rare but the most dangerous. Melanoma is curable if it is detected at an early stage. Automated segmentation of cancerous lesion from normal skin is the most critical yet tricky part in computerized lesion detection and classification. The effectiveness and accuracy of lesion classification are critically dependent on the quality of lesion segmentation. In this paper, we have proposed a novel approach that can automatically preprocess the image and then segment the lesion. The system filters unwanted artifacts including hairs, gel, bubbles, and specular reflection. A novel approach is presented using the concept of wavelets for detection and inpainting the hairs present in the cancer images. The contrast of lesion with the skin is enhanced using adaptive sigmoidal function that takes care of the localized intensity distribution within a given lesion's images. We then present a segmentation approach to precisely segment the lesion from the background. The proposed approach is tested on the European database of dermoscopic images. Results are compared with the competitors to demonstrate the superiority of the suggested approach.

  15. Computer Based Melanocytic and Nevus Image Enhancement and Segmentation

    Uzma Jamil


    Full Text Available Digital dermoscopy aids dermatologists in monitoring potentially cancerous skin lesions. Melanoma is the 5th common form of skin cancer that is rare but the most dangerous. Melanoma is curable if it is detected at an early stage. Automated segmentation of cancerous lesion from normal skin is the most critical yet tricky part in computerized lesion detection and classification. The effectiveness and accuracy of lesion classification are critically dependent on the quality of lesion segmentation. In this paper, we have proposed a novel approach that can automatically preprocess the image and then segment the lesion. The system filters unwanted artifacts including hairs, gel, bubbles, and specular reflection. A novel approach is presented using the concept of wavelets for detection and inpainting the hairs present in the cancer images. The contrast of lesion with the skin is enhanced using adaptive sigmoidal function that takes care of the localized intensity distribution within a given lesion’s images. We then present a segmentation approach to precisely segment the lesion from the background. The proposed approach is tested on the European database of dermoscopic images. Results are compared with the competitors to demonstrate the superiority of the suggested approach.

  16. Hybrid Method for 3D Segmentation of Magnetic Resonance Images

    ZHANGXiang; ZHANGDazhi; TIANJinwen; LIUJian


    Segmentation of some complex images, especially in magnetic resonance brain images, is often difficult to perform satisfactory results using only single approach of image segmentation. An approach towards the integration of several techniques seems to be the best solution. In this paper a new hybrid method for 3-dimension segmentation of the whole brain is introduced, based on fuzzy region growing, edge detection and mathematical morphology, The gray-level threshold, controlling the process of region growing, is determined by fuzzy technique. The image gradient feature is obtained by the 3-dimension sobel operator considering a 3×3×3 data block with the voxel to be evaluated at the center, while the gradient magnitude threshold is defined by the gradient magnitude histogram of brain magnetic resonance volume. By the combined methods of edge detection and region growing, the white matter volume of human brain is segmented perfectly. By the post-processing using mathematical morphological techniques, the whole brain region is obtained. In order to investigate the validity of the hybrid method, two comparative experiments, the region growing method using only gray-level feature and the thresholding method by combining gray-level and gradient features, are carried out. Experimental results indicate that the proposed method provides much better results than the traditional method using a single technique in the 3-dimension segmentation of human brain magnetic resonance data sets.

  17. Pixel Intensity Clustering Algorithm for Multilevel Image Segmentation

    Oludayo O. Olugbara


    Full Text Available Image segmentation is an important problem that has received significant attention in the literature. Over the last few decades, a lot of algorithms were developed to solve image segmentation problem; prominent amongst these are the thresholding algorithms. However, the computational time complexity of thresholding exponentially increases with increasing number of desired thresholds. A wealth of alternative algorithms, notably those based on particle swarm optimization and evolutionary metaheuristics, were proposed to tackle the intrinsic challenges of thresholding. In codicil, clustering based algorithms were developed as multidimensional extensions of thresholding. While these algorithms have demonstrated successful results for fewer thresholds, their computational costs for a large number of thresholds are still a limiting factor. We propose a new clustering algorithm based on linear partitioning of the pixel intensity set and between-cluster variance criterion function for multilevel image segmentation. The results of testing the proposed algorithm on real images from Berkeley Segmentation Dataset and Benchmark show that the algorithm is comparable with state-of-the-art multilevel segmentation algorithms and consistently produces high quality results. The attractive properties of the algorithm are its simplicity, generalization to a large number of clusters, and computational cost effectiveness.

  18. Visual Attention Shift based on Image Segmentation Using Neurodynamic System

    Lijuan Duan


    Full Text Available A method of predicting visual attention shift is proposed based on image segmentation using neurodynamic system in this paper. The input image is mapped to a neural oscillator network. Each oscillator corresponding to a pixel is modeled by means of simplified Wilson-Cowan equations, and is coupled with its 8-nearest neighbors. Then the image is segmented by classifying the oscillation curves of the excitatory groups of all the oscillators. The classifier is constructed based on features of frequency, offset, phase and amplitude of the curves. The visual attention shift between the regions on the image is predicted according to the saliency strength of each region. Referring to the mechanism of winner-take-all competition, the saliency of a region is the aggregation of the dissimilarities between this region and all the other ones. Experimental results on images show the effectiveness of our method.

  19. Automatic Segmentation and Inpainting of Specular Highlights for Endoscopic Imaging

    Arnold Mirko


    Full Text Available Minimally invasive medical procedures have become increasingly common in today's healthcare practice. Images taken during such procedures largely show tissues of human organs, such as the mucosa of the gastrointestinal tract. These surfaces usually have a glossy appearance showing specular highlights. For many visual analysis algorithms, these distinct and bright visual features can become a significant source of error. In this article, we propose two methods to address this problem: (a a segmentation method based on nonlinear filtering and colour image thresholding and (b an efficient inpainting method. The inpainting algorithm eliminates the negative effect of specular highlights on other image analysis algorithms and also gives a visually pleasing result. The methods compare favourably to the existing approaches reported for endoscopic imaging. Furthermore, in contrast to the existing approaches, the proposed segmentation method is applicable to the widely used sequential RGB image acquisition systems.

  20. A dendritic lattice neural network for color image segmentation

    Urcid, Gonzalo; Lara-Rodríguez, Luis David; López-Meléndez, Elizabeth


    A two-layer dendritic lattice neural network is proposed to segment color images in the Red-Green-Blue (RGB) color space. The two layer neural network is a fully interconnected feed forward net consisting of an input layer that receives color pixel values, an intermediate layer that computes pixel interdistances, and an output layer used to classify colors by hetero-association. The two-layer net is first initialized with a finite small subset of the colors present in the input image. These colors are obtained by means of an automatic clustering procedure such as k-means or fuzzy c-means. In the second stage, the color image is scanned on a pixel by pixel basis where each picture element is treated as a vector and feeded into the network. For illustration purposes we use public domain color images to show the performance of our proposed image segmentation technique.

  1. Neuron Segmentation in Electron Microscopy Images Using Partial Differential Equations.

    Jones, Cory; Sayedhosseini, Mojtaba; Ellisman, Mark; Tasdizen, Tolga


    In connectomics, neuroscientists seek to identify the synaptic connections between neurons. Segmentation of cell membranes using supervised learning algorithms on electron microscopy images of brain tissue is often done to assist in this effort. Here we present a partial differential equation with a novel growth term to improve the results of a supervised learning algorithm. We also introduce a new method for representing the resulting image that allows for a more dynamic thresholding to further improve the result. Using these two processes we are able to close small to medium sized gaps in the cell membrane detection and improve the Rand error by as much as 9% over the initial supervised segmentation.

  2. Topography Image Segmentation Based on Improved Chan-Vese Model

    ZHAO Min-rong; ZHANG Xi-wen; JIANG Juan-na


    Aiming to solve the inefficient segmentation in traditional C-V model for complex topography image and time-consuming process caused by the level set function solving with partial differential, an improved Chan-Vese model is presented in this paper. With the good performances of maintaining topological properties of the traditional level set method and avoiding the numerical so-lution of partial differential, the same segmentation results could be easily obtained. Thus, a stable foundation for rapid segmenta-tion-based on image reconstruction identification is established.

  3. Constrained segmentation of cardiac MR image sequences

    Üzümcü, Mehmet


    Cardiovascular diseases are highly prevalent in the western world. With the aging of the population, the number of people suffering from CVD is still increasing. Therefore, the amount of diagnostic assessments and thus, the number of image acquisitions will increase accordingly. Considering the high

  4. Image Segmentation for Improvised Explosive Devices


    Soltani and Wong in 1988 [23]. Also, Sezgin and Sankur 2004 and Shapiro 2001 12 Figure 2.3: Comparing the usefulness of histograms to define the threshold...S. Soltani , and A. K. Wong. A survey of thresholding techniques. Computer Vision, Graphics, and Image Processing, 41(2):233–260, 1988. [24] M

  5. Automatic image segmentation for treatment planning in radiotherapy; Segmentation automatique des images pour la planifi cation dosimetrique en radiotherapie

    Pasquiera, D. [Centre Galilee, polyclinique de la Louviere, 59 - Lille (France); Peyrodie, L. [Ecole des hautes etudes d' ingenieur, 59 - Lille (France); Laboratoire d' automatique, genie informatique et signal (LAGIS), Cite scientifi que, 59 - Villeneuve d' Ascq (France); Denis, F. [Centre Jean-Bernard, 72 - Le Mans (France); Pointreau, Y.; Bera, G. [Clinique d' oncologie radiotherapie, Centre Henry-S.-Kaplan, CHU Bretonneau, 37 - Tours (France); Lartigau, E. [Departement universitaire de radiotherapie, Centre O. Lambret, Universite Lille 2, 59 - Lille (France)


    One drawback of the growth in conformal radiotherapy and image-guided radiotherapy is the increased time needed to define the volumes of interest. This also results in inter- and intra-observer variability. However, developments in computing and image processing have enabled these tasks to be partially or totally automated. This article will provide a detailed description of the main principles of image segmentation in radiotherapy, its applications and the most recent results in a clinical context. (authors)

  6. Image Segmentation Analysis for NASA Earth Science Applications

    Tilton, James C.


    NASA collects large volumes of imagery data from satellite-based Earth remote sensing sensors. Nearly all of the computerized image analysis of this data is performed pixel-by-pixel, in which an algorithm is applied directly to individual image pixels. While this analysis approach is satisfactory in many cases, it is usually not fully effective in extracting the full information content from the high spatial resolution image data that s now becoming increasingly available from these sensors. The field of object-based image analysis (OBIA) has arisen in recent years to address the need to move beyond pixel-based analysis. The Recursive Hierarchical Segmentation (RHSEG) software developed by the author is being used to facilitate moving from pixel-based image analysis to OBIA. The key unique aspect of RHSEG is that it tightly intertwines region growing segmentation, which produces spatially connected region objects, with region object classification, which groups sets of region objects together into region classes. No other practical, operational image segmentation approach has this tight integration of region growing object finding with region classification This integration is made possible by the recursive, divide-and-conquer implementation utilized by RHSEG, in which the input image data is recursively subdivided until the image data sections are small enough to successfully mitigat the combinatorial explosion caused by the need to compute the dissimilarity between each pair of image pixels. RHSEG's tight integration of region growing object finding and region classification is what enables the high spatial fidelity of the image segmentations produced by RHSEG. This presentation will provide an overview of the RHSEG algorithm and describe how it is currently being used to support OBIA or Earth Science applications such as snow/ice mapping and finding archaeological sites from remotely sensed data.

  7. Segmentation of fluorescence microscopy cell images using unsupervised mining.

    Du, Xian; Dua, Sumeet


    The accurate measurement of cell and nuclei contours are critical for the sensitive and specific detection of changes in normal cells in several medical informatics disciplines. Within microscopy, this task is facilitated using fluorescence cell stains, and segmentation is often the first step in such approaches. Due to the complex nature of cell issues and problems inherent to microscopy, unsupervised mining approaches of clustering can be incorporated in the segmentation of cells. In this study, we have developed and evaluated the performance of multiple unsupervised data mining techniques in cell image segmentation. We adapt four distinctive, yet complementary, methods for unsupervised learning, including those based on k-means clustering, EM, Otsu's threshold, and GMAC. Validation measures are defined, and the performance of the techniques is evaluated both quantitatively and qualitatively using synthetic and recently published real data. Experimental results demonstrate that k-means, Otsu's threshold, and GMAC perform similarly, and have more precise segmentation results than EM. We report that EM has higher recall values and lower precision results from under-segmentation due to its Gaussian model assumption. We also demonstrate that these methods need spatial information to segment complex real cell images with a high degree of efficacy, as expected in many medical informatics applications.

  8. Adaptive geodesic transform for segmentation of vertebrae on CT images

    Gaonkar, Bilwaj; Shu, Liao; Hermosillo, Gerardo; Zhan, Yiqiang


    Vertebral segmentation is a critical first step in any quantitative evaluation of vertebral pathology using CT images. This is especially challenging because bone marrow tissue has the same intensity profile as the muscle surrounding the bone. Thus simple methods such as thresholding or adaptive k-means fail to accurately segment vertebrae. While several other algorithms such as level sets may be used for segmentation any algorithm that is clinically deployable has to work in under a few seconds. To address these dual challenges we present here, a new algorithm based on the geodesic distance transform that is capable of segmenting the spinal vertebrae in under one second. To achieve this we extend the theory of the geodesic distance transforms proposed in1 to incorporate high level anatomical knowledge through adaptive weighting of image gradients. Such knowledge may be provided by the user directly or may be automatically generated by another algorithm. We incorporate information 'learnt' using a previously published machine learning algorithm2 to segment the L1 to L5 vertebrae. While we present a particular application here, the adaptive geodesic transform is a generic concept which can be applied to segmentation of other organs as well.

  9. Automated segmentation of three-dimensional MR brain images

    Park, Jonggeun; Baek, Byungjun; Ahn, Choong-Il; Ku, Kyo Bum; Jeong, Dong Kyun; Lee, Chulhee


    Brain segmentation is a challenging problem due to the complexity of the brain. In this paper, we propose an automated brain segmentation method for 3D magnetic resonance (MR) brain images which are represented as a sequence of 2D brain images. The proposed method consists of three steps: pre-processing, removal of non-brain regions (e.g., the skull, meninges, other organs, etc), and spinal cord restoration. In pre-processing, we perform adaptive thresholding which takes into account variable intensities of MR brain images corresponding to various image acquisition conditions. In segmentation process, we iteratively apply 2D morphological operations and masking for the sequences of 2D sagittal, coronal, and axial planes in order to remove non-brain tissues. Next, final 3D brain regions are obtained by applying OR operation for segmentation results of three planes. Finally we reconstruct the spinal cord truncated during the previous processes. Experiments are performed with fifteen 3D MR brain image sets with 8-bit gray-scale. Experiment results show the proposed algorithm is fast, and provides robust and satisfactory results.

  10. Automatic comic page image understanding based on edge segment analysis

    Liu, Dong; Wang, Yongtao; Tang, Zhi; Li, Luyuan; Gao, Liangcai


    Comic page image understanding aims to analyse the layout of the comic page images by detecting the storyboards and identifying the reading order automatically. It is the key technique to produce the digital comic documents suitable for reading on mobile devices. In this paper, we propose a novel comic page image understanding method based on edge segment analysis. First, we propose an efficient edge point chaining method to extract Canny edge segments (i.e., contiguous chains of Canny edge points) from the input comic page image; second, we propose a top-down scheme to detect line segments within each obtained edge segment; third, we develop a novel method to detect the storyboards by selecting the border lines and further identify the reading order of these storyboards. The proposed method is performed on a data set consisting of 2000 comic page images from ten printed comic series. The experimental results demonstrate that the proposed method achieves satisfactory results on different comics and outperforms the existing methods.

  11. Multiscale stochastic hierarchical image segmentation by spectral clustering

    LI XiaoBin; TIAN Zheng


    This paper proposes a sampling based hierarchical approach for solving the computational demands of the spectral clustering methods when applied to the problem of image segmentation. The authors first define the distance between a pixel and a cluster, and then derive a new theorem to estimate the number of samples needed for clustering. Finally, by introducing a scale parameter into the similarity function, a novel spectral clustering based image segmentation method has been developed. An important characteristic of the approach is that in the course of image segmentation one needs not only to tune the scale parameter to merge the small size clusters or split the large size clusters but also take samples from the data set at the different scales. The multiscale and stochastic nature makes it feasible to apply the method to very large grouping problem. In addition, it also makes the segmentation compute in time that is linear in the size of the image. The experimental results on various synthetic and real world images show the effectiveness of the approach.

  12. Remote sensing images segmentation by Deriche's filter and neural network

    Koffi, Raphael K.; Solaiman, Basel; Mouchot, Marie-Catherine


    An image segmentation method for remote sensing data using hybride techniques is proposed. Edge detection approach for segmentation is considered in our study. Our aim is to integrate segmentation results in further processing namely classification. Images of the land from satellite are often corrupted by noise. On one hand, optimal edge detectors insure good noise immunity. On the other hand, the multi-layer perceptron (MLP) neural network has been found to be suited for classification. So we propose to combine these two techniques to improve segmentation process. Satellites for remote sensing provide several images for the same area, coded differently according to spectral bands. In order to bear in mind spectral and spatial information, neighborhood relation of pixels and different bands are taken into consideration during the classification realized by the neural network. Samples which constituate the training set for the MLP are selected from the third, fourth and fifth band and represent edge and non-edge patterns. Each sample vector is composed of the value of a current pixel in the local maxima image (enhancement image obtained by Deriche's filter) and its 8 nearest neighbors. The proposed method provides satisfactory results for our application and compared to other similar methods.

  13. Automatic segmentation of lumbar vertebrae in CT images

    Kulkarni, Amruta; Raina, Akshita; Sharifi Sarabi, Mona; Ahn, Christine S.; Babayan, Diana; Gaonkar, Bilwaj; Macyszyn, Luke; Raghavendra, Cauligi


    Lower back pain is one of the most prevalent disorders in the developed/developing world. However, its etiology is poorly understood and treatment is often determined subjectively. In order to quantitatively study the emergence and evolution of back pain, it is necessary to develop consistently measurable markers for pathology. Imaging based measures offer one solution to this problem. The development of imaging based on quantitative biomarkers for the lower back necessitates automated techniques to acquire this data. While the problem of segmenting lumbar vertebrae has been addressed repeatedly in literature, the associated problem of computing relevant biomarkers on the basis of the segmentation has not been addressed thoroughly. In this paper, we propose a Random-Forest based approach that learns to segment vertebral bodies in CT images followed by a biomarker evaluation framework that extracts vertebral heights and widths from the segmentations obtained. Our dataset consists of 15 CT sagittal scans obtained from General Electric Healthcare. Our main approach is divided into three parts: the first stage is image pre-processing which is used to correct for variations in illumination across all the images followed by preparing the foreground and background objects from images; the next stage is Machine Learning using Random-Forests, which distinguishes the interest-point vectors between foreground or background; and the last step is image post-processing, which is crucial to refine the results of classifier. The Dice coefficient was used as a statistical validation metric to evaluate the performance of our segmentations with an average value of 0.725 for our dataset.

  14. Background adjustment of cDNA microarray images by Maximum Entropy distributions.

    Argyropoulos, Christos; Daskalakis, Antonis; Nikiforidis, George C; Sakellaropoulos, George C


    Many empirical studies have demonstrated the exquisite sensitivity of both traditional and novel statistical and machine intelligence algorithms to the method of background adjustment used to analyze microarray datasets. In this paper we develop a statistical framework that approaches background adjustment as a classic stochastic inverse problem, whose noise characteristics are given in terms of Maximum Entropy distributions. We derive analytic closed form approximations to the combined problem of estimating the magnitude of the background in microarray images and adjusting for its presence. The proposed method reduces standardized measures of log expression variability across replicates in situations of known differential and non-differential gene expression without increasing the bias. Additionally, it results in computationally efficient procedures for estimation and learning based on sufficient statistics and can filter out spot measures with intensities that are numerically close to the background level resulting in a noise reduction of about 7%.

  15. Statistical Segmentation of Regions of Interest on a Mammographic Image

    Adel, Mouloud; Rasigni, Monique; Bourennane, Salah; Juhan, Valerie


    This paper deals with segmentation of breast anatomical regions, pectoral muscle, fatty and fibroglandular regions, using a Bayesian approach. This work is a part of a computer aided diagnosis project aiming at evaluating breast cancer risk and its association with characteristics (density, texture, etc.) of regions of interest on digitized mammograms. Novelty in this paper consists in applying and adapting Markov random field for detecting breast anatomical regions on digitized mammograms whereas most of previous works were focused on masses and microcalcifications. The developed method was tested on 50 digitized mammograms of the mini-MIAS database. Computer segmentation is compared to manual one made by a radiologist. A good agreement is obtained on 68% of the mini-MIAS mammographic image database used in this study. Given obtained segmentation results, the proposed method could be considered as a satisfying first approach for segmenting regions of interest in a breast.

  16. Superpixel Segmentation for Endmember Detection in Hyperspectral Images

    Thompson, D. R.; de Granville, C.; Gilmore, M. S.; Castano, R.


    "Superpixel segmentation" is a novel approach to facilitate statistical analyses of hyperspectral image data with high spatial resolution and subtle spectral features. The method oversegments the image into homogeneous regions each comprised of several contiguous pixels. This can reduce noise by exploiting scene features' spatial contiguity: isolated spectral features are likely to be noise, but spectral features that appear in several adjacent pixels probably indicate real materials in the scene. The mean spectra from each superpixel define a smaller, noise-reduced dataset. This preprocessing step improves endmember detection for the images in our study. Our endmember detection approach presumes a linear (geographic) mixing model for image spectra. We generate superpixels with the Felzenszwalb/Huttenlocher graph-based segmentation [1] with a Euclidean distance metric. This segmentation shatters the image into thousands of superpixels, each with an area of approximately 20 image pixels. We then apply Symmetric Maximum Angle Convex Cone (SMACC) endmember detection algorithm to the data set consisting of the mean spectrum from all superpixels. We evaluated the approach for several images from the Compact Reconnaissance Imaging Spectrometer (CRISM) [2]. We used the 1000-2500nm wavelengths of images frt00003e12 and frt00003fb9. We cleaned the images with atmospheric correction based on Olympus Mons spectra [3] and preprocessed with a radius-1 median filter in the spectral domain. Endmembers produced with and without the superpixel reduction are compared to the representative (mean) spectra of five representative mineral classes identified in an expert analysis of each scene. Expert-identified minerals include mafic minerals and phyllosilicate deposits that in some cases subtended just a few tens of pixels. Only the endmembers from the superpixel approach reflected all major mineral constituents in the images. Additionally, the superpixel endmembers are more

  17. Filter Design and Performance Evaluation for Fingerprint Image Segmentation.

    Duy Hoang Thai

    Full Text Available Fingerprint recognition plays an important role in many commercial applications and is used by millions of people every day, e.g. for unlocking mobile phones. Fingerprint image segmentation is typically the first processing step of most fingerprint algorithms and it divides an image into foreground, the region of interest, and background. Two types of error can occur during this step which both have a negative impact on the recognition performance: 'true' foreground can be labeled as background and features like minutiae can be lost, or conversely 'true' background can be misclassified as foreground and spurious features can be introduced. The contribution of this paper is threefold: firstly, we propose a novel factorized directional bandpass (FDB segmentation method for texture extraction based on the directional Hilbert transform of a Butterworth bandpass (DHBB filter interwoven with soft-thresholding. Secondly, we provide a manually marked ground truth segmentation for 10560 images as an evaluation benchmark. Thirdly, we conduct a systematic performance comparison between the FDB method and four of the most often cited fingerprint segmentation algorithms showing that the FDB segmentation method clearly outperforms these four widely used methods. The benchmark and the implementation of the FDB method are made publicly available.

  18. Quantitative measure in image segmentation for skin lesion images: A preliminary study

    Azmi, Nurulhuda Firdaus Mohd; Ibrahim, Mohd Hakimi Aiman; Keng, Lau Hui; Ibrahim, Nuzulha Khilwani; Sarkan, Haslina Md


    Automatic Skin Lesion Diagnosis (ASLD) allows skin lesion diagnosis by using a computer or mobile devices. The idea of using a computer to assist in diagnosis of skin lesions was first proposed in the literature around 1985. Images of skin lesions are analyzed by the computer to capture certain features thought to be characteristic of skin diseases. These features (expressed as numeric values) are then used to classify the image and report a diagnosis. Image segmentation is often a critical step in image analysis and it may use statistical classification, thresholding, edge detection, region detection, or any combination of these techniques. Nevertheless, image segmentation of skin lesion images is yet limited to superficial evaluations which merely display images of the segmentation results and appeal to the reader's intuition for evaluation. There is a consistent lack of quantitative measure, thus, it is difficult to know which segmentation present useful results and in which situations they do so. If segmentation is done well, then, all other stages in image analysis are made simpler. If significant features (that are crucial for diagnosis) are not extracted from images, it will affect the accuracy of the automated diagnosis. This paper explore the existing quantitative measure in image segmentation ranging in the application of pattern recognition for example hand writing, plat number, and colour. Selecting the most suitable segmentation measure is highly important so that as much relevant features can be identified and extracted.

  19. A Level Set Approach to Image Segmentation With Intensity Inhomogeneity.

    Zhang, Kaihua; Zhang, Lei; Lam, Kin-Man; Zhang, David


    It is often a difficult task to accurately segment images with intensity inhomogeneity, because most of representative algorithms are region-based that depend on intensity homogeneity of the interested object. In this paper, we present a novel level set method for image segmentation in the presence of intensity inhomogeneity. The inhomogeneous objects are modeled as Gaussian distributions of different means and variances in which a sliding window is used to map the original image into another domain, where the intensity distribution of each object is still Gaussian but better separated. The means of the Gaussian distributions in the transformed domain can be adaptively estimated by multiplying a bias field with the original signal within the window. A maximum likelihood energy functional is then defined on the whole image region, which combines the bias field, the level set function, and the piecewise constant function approximating the true image signal. The proposed level set method can be directly applied to simultaneous segmentation and bias correction for 3 and 7T magnetic resonance images. Extensive evaluation on synthetic and real-images demonstrate the superiority of the proposed method over other representative algorithms.

  20. Effect of image scaling and segmentation in digital rock characterisation

    Jones, B. D.; Feng, Y. T.


    Digital material characterisation from microstructural geometry is an emerging field in computer simulation. For permeability characterisation, a variety of studies exist where the lattice Boltzmann method (LBM) has been used in conjunction with computed tomography (CT) imaging to simulate fluid flow through microscopic rock pores. While these previous works show that the technique is applicable, the use of binary image segmentation and the bounceback boundary condition results in a loss of grain surface definition when the modelled geometry is compared to the original CT image. We apply the immersed moving boundary (IMB) condition of Noble and Torczynski as a partial bounceback boundary condition which may be used to better represent the geometric definition provided by a CT image. The IMB condition is validated against published work on idealised porous geometries in both 2D and 3D. Following this, greyscale image segmentation is applied to a CT image of Diemelstadt sandstone. By varying the mapping of CT voxel densities to lattice sites, it is shown that binary image segmentation may underestimate the true permeability of the sample. A CUDA-C-based code, LBM-C, was developed specifically for this work and leverages GPU hardware in order to carry out computations.

  1. Segmentation and separation of venous vasculatures in liver CT images

    Wang, Lei; Hansen, Christian; Zidowitz, Stephan; Hahn, Horst K.


    Computer-aided analysis of venous vasculatures including hepatic veins and portal veins is important in liver surgery planning. The analysis normally consists of two important pre-processing tasks: segmenting both vasculatures and separating them from each other by assigning different labels. During the acquisition of multi-phase CT images, both of the venous vessels are enhanced by injected contrast agent and acquired either in a common phase or in two individual phases. The enhanced signals established by contrast agent are often not stably acquired due to non-optimal acquisition time. Inadequate contrast and the presence of large lesions in oncological patients, make the segmentation task quite challenging. To overcome these diffculties, we propose a framework with minimal user interactions to analyze venous vasculatures in multi-phase CT images. Firstly, presented vasculatures are automatically segmented adopting an efficient multi-scale Hessian-based vesselness filter. The initially segmented vessel trees are then converted to a graph representation, on which a series of graph filters are applied in post-processing steps to rule out irrelevant structures. Eventually, we develop a semi-automatic workow to refine the segmentation in the areas of inferior vena cava and entrance of portal veins, and to simultaneously separate hepatic veins from portal veins. Segmentation quality was evaluated with intensive tests enclosing 60 CT images from both healthy liver donors and oncological patients. To quantitatively measure the similarities between segmented and reference vessel trees, we propose three additional metrics: skeleton distance, branch coverage, and boundary surface distance, which are dedicated to quantifying the misalignment induced by both branching patterns and radii of two vessel trees.

  2. Enhanced Image Segmentation Using Fuzzy Logic

    Manpreet singh


    This research work proposed an improved edge detection techniques using fuzzy sets. The problem is to find edges in the image, as a first step in the process of scene reconstruction. Edges are scale-dependent and an edge may comprise other edges, but at a definite scale, an edge still has no width. This paper has presented different edge detection operators and their benefit when they merge with fuzzy logic theory. This paper has achieved the accuracy of edge detection up to 94.89 %. The prop...

  3. Segmentation of MR images using multiple-feature vectors

    Cole, Orlean I. B.; Daemi, Mohammad F.


    Segmentation is an important step in the analysis of MR images (MRI). Considerable progress has been made in this area, and numerous reports on 3D segmentation, volume measurement and visualization have been published in recent years. The main purpose of our study is to investigate the power and use of fractal techniques in extraction of features from MR images of the human brain. These features which are supplemented by other features are used for segmentation, and ultimately for the extraction of a known pathology, in our case multiple- sclerosis (MS) lesions. We are particularly interested in the progress of the lesions and occurrence of new lesions which in a typical case are scattered within the image and are sometimes difficult to identify visually. We propose a technique for multi-channel segmentation of MR images using multiple feature vectors. The channels are proton density, T1-weighted and T2-weighted images containing multiple-sclerosis (MS) lesions at various stages of development. We first represent each image as a set of feature vectors which are estimated using fractal techniques, and supplemented by micro-texture features and features from the gray-level co-occurrence matrix (GLCM). These feature vectors are then used in a feature selection algorithm to reduce the dimension of the feature space. The next stage is segmentation and clustering. The selected feature vectors now form the input to the segmentation and clustering routines and are used as the initial clustering parameters. For this purpose, we have used the classical K-means as the initial clustering method. The clustered image is then passed into a probabilistic classifier to further classify and validate each region, taking into account the spatial properties of the image. Initially, segmentation results were obtained using the fractal dimension features alone. Subsequently, a combination of the fractal dimension features and the supplementary features mentioned above were also obtained

  4. Multiscale MRF-based Texture Segmentation of SAR Image

    XUXin; LIDeren; SUNHong


    We propose a multiscale Bayesian segmentation algorithm for SAR image in this paper. A hierarchical two-level Markov random field (MRF) is applied to represent both texture and region label over the wavelet lattice. The high level uses an isotropic Multi-level logistic (MLL) random field to characterize the blob-like region formation process at each scale and the interscale dependencies over the corresponding multiresolution region. At lower level a novel Causal Gaussian autoregressive (CGAR) process is proposed to describe the fill-in of multiresolution region. Once the multiscale double MRFs model is established, in term of Sequential maximum a posteriori (SMAP), model parameter estimate and region segmentation are performed alternately from coarse to fine scale. Our segmentation method is tested on both synthetic and ERS-1 SAR images.


    Liu Yajing; Yang Fan; Yang Ruixia; Jia Kejin; Zhang Hongtao


    In this letter, a segment algorithm based on color feature of images is proposed. The algorithm separates the weed area from soil background according to the color eigenvalue, which is obtained by analyzing the color difference between the weeds and background in three color spaces RGB, rgb and HSI. The results of the experiment show that it can get notable effect in segmentation according to the color feature, and the possibility of successful segmentation is 87%-93%. This method can also be widely used in other fields which are complicated in the background of the image and facilely influenced in illumination, such as weed identification, tree species discrimination, fruit picking and so on.

  6. Medical image segmentation using object atlas versus object cloud models

    Phellan, Renzo; Falcão, Alexandre X.; Udupa, Jayaram K.


    Medical image segmentation is crucial for quantitative organ analysis and surgical planning. Since interactive segmentation is not practical in a production-mode clinical setting, automatic methods based on 3D object appearance models have been proposed. Among them, approaches based on object atlas are the most actively investigated. A key drawback of these approaches is that they require a time-costly image registration process to build and deploy the atlas. Object cloud models (OCM) have been introduced to avoid registration, considerably speeding up the whole process, but they have not been compared to object atlas models (OAM). The present paper fills this gap by presenting a comparative analysis of the two approaches in the task of individually segmenting nine anatomical structures of the human body. Our results indicate that OCM achieve a statistically significant better accuracy for seven anatomical structures, in terms of Dice Similarity Coefficient and Average Symmetric Surface Distance.

  7. Statistical Characterization and Segmentation of Drusen in Fundus Images

    Santos-Villalobos, Hector J [ORNL; Karnowski, Thomas Paul [ORNL; Aykac, Deniz [ORNL; Giancardo, Luca [ORNL; Li, Yaquin [University of Tennessee, Knoxville (UTK); Nichols, Trent L [ORNL; Tobin Jr, Kenneth William [ORNL; Chaum, Edward [University of Tennessee, Knoxville (UTK)


    Age related Macular Degeneration (AMD) is a disease of the retina associated with aging. AMD progression in patients is characterized by drusen, pigmentation changes, and geographic atrophy, which can be seen using fundus imagery. The level of AMD is characterized by standard scaling methods, which can be somewhat subjective in practice. In this work we propose a statistical image processing approach to segment drusen with the ultimate goal of characterizing the AMD progression in a data set of longitudinal images. The method characterizes retinal structures with a statistical model of the colors in the retina image. When comparing the segmentation results of the method between longitudinal images with known AMD progression and those without, the method detects progression in our longitudinal data set with an area under the receiver operating characteristics curve of 0.99.

  8. Message Segmentation to Enhance the Security of LSB Image Steganography

    Dr. Mohammed Abbas Fadhil Al-Husainy


    Full Text Available Classic Least Significant Bit (LSB steganography technique is the most used technique to hide secret information in the least significant bit of the pixels in the stego-image. This paper proposed a technique by splitting the secret message into set of segments, that have same length (number of characters, and find the best LSBs of pixels in the stego-image that are matched to each segment. The main goal of this technique is to minimize the number of LSBs that are changed when substituting them with the bits of characters in the secret message. This will lead to decrease the distortion (noise that is occurred in the pixels of the stego-image and as result increase the immunity of the stego-image against the visual attack. The experiment shows that the proposed technique gives good enhancement to the Classic Least Significant Bit (LSB technique

  9. Crowdsourcing the creation of image segmentation algorithms for connectomics

    Ignacio eArganda-Carreras


    Full Text Available To stimulate progress in automating the reconstruction of neural circuits,we organized the first international challenge on 2D segmentationof electron microscopic (EM images of the brain. Participants submittedboundary maps predicted for a test set of images, and were scoredbased on their agreement with ground truth from human experts. Thewinning team had no prior experience with EM images, and employeda convolutional network. This ``deep learning'' approach has sincebecome accepted as a standard for segmentation of EM images. The challengehas continued to accept submissions, and the best so far has resultedfrom cooperation between two teams. The challenge has probably saturated,as algorithms cannot progress beyond limits set by ambiguities inherentin 2D scoring. Retrospective evaluation of the challenge scoring systemreveals that it was not sufficiently robust to variations in the widthsof neurite borders. We propose a solution to this problem, which shouldbe useful for a future 3D segmentation challenge.

  10. Fingerprint Image Segmentation Algorithm Based on Contourlet Transform Technology

    Guanghua Zhang


    Full Text Available This paper briefly introduces two classic algorithms for fingerprint image processing, which include the soft threshold denoise algorithm of wavelet domain based on wavelet domain and the fingerprint image enhancement algorithm based on Gabor function. Contourlet transform has good texture sensitivity and can be used for the segmentation enforcement of the fingerprint image. The method proposed in this paper has attained the final fingerprint segmentation image through utilizing a modified denoising for a high-frequency coefficient after Contourlet decomposition, highlighting the fingerprint ridge line through modulus maxima detection and finally connecting the broken fingerprint line using a value filter in direction. It can attain richer direction information than the method based on wavelet transform and Gabor function and can make the positioning of detailed features more accurate. However, its ridge should be more coherent. Experiments have shown that this algorithm is obviously superior in fingerprint features detection.

  11. Statistical characterization and segmentation of drusen in fundus images.

    Santos-Villalobos, H; Karnowski, T P; Aykac, D; Giancardo, L; Li, Y; Nichols, T; Tobin, K W; Chaum, E


    Age related Macular Degeneration (AMD) is a disease of the retina associated with aging. AMD progression in patients is characterized by drusen, pigmentation changes, and geographic atrophy, which can be seen using fundus imagery. The level of AMD is characterized by standard scaling methods, which can be somewhat subjective in practice. In this work we propose a statistical image processing approach to segment drusen with the ultimate goal of characterizing the AMD progression in a data set of longitudinal images. The method characterizes retinal structures with a statistical model of the colors in the retina image. When comparing the segmentation results of the method between longitudinal images with known AMD progression and those without, the method detects progression in our longitudinal data set with an area under the receiver operating characteristics curve of 0.99.


    Yang Yong; Lin Pan; Zheng Chongxun; Gu Jianwen


    Objective To present a novel modified level set algorithm for medical image segmentation. Methods The algorithm is developed by substituting the speed function of level set algorithm with the region and gradient information of the image instead of the conventional gradient information. This new algorithm has been tested by a series of different modality medical images. Results We present various examples and also evaluate and compare the performance of our method with the classical level set method on weak boundaries and noisy images. Conclusion Experimental results show the proposed algorithm is effective and robust.

  13. Image Segmentation Based on Period Difference of the Oscillation

    王直杰; 张珏; 范宏; 柯克峰


    A new method for image segmentation based on pulse neural network is proposed. Every neuron in the network represents one pixel in the image and the network is locally connected.Each group of the neurons that correspond to each object synchronizes while different gronps of the neurons oscillate at different period. Applying this period difference,different objects are divided. In addition to simulation, an analysis of the mechanism of the method is presented in this paper.

  14. Color Image Segmentation Method Based on Improved Spectral Clustering Algorithm

    Dong Qin


    Contraposing to the features of image data with high sparsity of and the problems on determination of clustering numbers, we try to put forward an color image segmentation algorithm, combined with semi-supervised machine learning technology and spectral graph theory. By the research of related theories and methods of spectral clustering algorithms, we introduce information entropy conception to design a method which can automatically optimize the scale parameter value. So it avoids the unstab...

  15. Ontology-Based Knowledge Organization for the Radiograph Images Segmentation

    MATEI, O.


    Full Text Available The quantity of thoracic radiographies in the medical field is ever growing. An automated system for segmenting the images would help doctors enormously. Some approaches are knowledge-based; therefore we propose here an ontology for this purpose. Thus it is machine oriented, rather than human-oriented. That is all the structures visible on a thoracic image are described from a technical point of view.

  16. Segmentation of Camera Captured Business Card Images for Mobile Devices

    Mollah, Ayatullah Faruk; Nasipuri, Mita


    Due to huge deformation in the camera captured images, variety in nature of the business cards and the computational constraints of the mobile devices, design of an efficient Business Card Reader (BCR) is challenging to the researchers. Extraction of text regions and segmenting them into characters is one of such challenges. In this paper, we have presented an efficient character segmentation technique for business card images captured by a cell-phone camera, designed in our present work towards developing an efficient BCR. At first, text regions are extracted from the card images and then the skewed ones are corrected using a computationally efficient skew correction technique. At last, these skew corrected text regions are segmented into lines and characters based on horizontal and vertical histogram. Experiments show that the present technique is efficient and applicable for mobile devices, and the mean segmentation accuracy of 97.48% is achieved with 3 mega-pixel (500-600 dpi) images. It takes only 1.1 se...

  17. Contourlet-based active contour model for PET image segmentation

    Abdoli, M.; Dierckx, R. A. J. O.; Zaidi, H.

    Purpose: PET-guided radiation therapy treatment planning, clinical diagnosis, assessment of tumor growth, and therapy response rely on the accurate delineation of the tumor volume and quantification of tracer uptake. Most PET image segmentation techniques proposed thus far are suboptimal in the

  18. Image segmentation by connectivity preserving relinking in hierarchical graph structures

    Nacken, P.F.M.


    The method of image segmentation by pyramid relinking is extended to the formalism of hierarchies of region adjacency graphs. This approach has a number of advantages: (1) resulting regions are connected; (2) the method is adaptive, and therefore artifacts caused by a regular grid are avoided; and (

  19. Unsupervised segmentation of predefined shapes in multivariate images

    Noordam, J.C.; Broek, van den W.H.A.M.; Buydens, L.M.C.


    Fuzzy C-means (FCM) is an unsupervised clustering technique that is often used for the unsupervised segmentation of multivariate images. In traditional FCM the clustering is based on spectral information only and the geometrical relationship between neighbouring pixels is not used in the clustering

  20. Contourlet-based active contour model for PET image segmentation

    Abdoli, M.; Dierckx, R. A. J. O.; Zaidi, H.


    Purpose: PET-guided radiation therapy treatment planning, clinical diagnosis, assessment of tumor growth, and therapy response rely on the accurate delineation of the tumor volume and quantification of tracer uptake. Most PET image segmentation techniques proposed thus far are suboptimal in the pres

  1. Hierarchical stochastic image grammars for classification and segmentation.

    Wang, Wiley; Pollak, Ilya; Wong, Tak-Shing; Bouman, Charles A; Harper, Mary P; Siskind, Jeffrey M


    We develop a new class of hierarchical stochastic image models called spatial random trees (SRTs) which admit polynomial-complexity exact inference algorithms. Our framework of multitree dictionaries is the starting point for this construction. SRTs are stochastic hidden tree models whose leaves are associated with image data. The states at the tree nodes are random variables, and, in addition, the structure of the tree is random and is generated by a probabilistic grammar. We describe an efficient recursive algorithm for obtaining the maximum a posteriori estimate of both the tree structure and the tree states given an image. We also develop an efficient procedure for performing one iteration of the expectation-maximization algorithm and use it to estimate the model parameters from a set of training images. We address other inference problems arising in applications such as maximization of posterior marginals and hypothesis testing. Our models and algorithms are illustrated through several image classification and segmentation experiments, ranging from the segmentation of synthetic images to the classification of natural photographs and the segmentation of scanned documents. In each case, we show that our method substantially improves accuracy over a variety of existing methods.

  2. Optimization-Based Image Segmentation by Genetic Algorithms

    H. Laurent


    Full Text Available Many works in the literature focus on the definition of evaluation metrics and criteria that enable to quantify the performance of an image processing algorithm. These evaluation criteria can be used to define new image processing algorithms by optimizing them. In this paper, we propose a general scheme to segment images by a genetic algorithm. The developed method uses an evaluation criterion which quantifies the quality of an image segmentation result. The proposed segmentation method can integrate a local ground truth when it is available in order to set the desired level of precision of the final result. A genetic algorithm is then used in order to determine the best combination of information extracted by the selected criterion. Then, we show that this approach can either be applied for gray-levels or multicomponents images in a supervised context or in an unsupervised one. Last, we show the efficiency of the proposed method through some experimental results on several gray-levels and multicomponents images.

  3. Optimization-Based Image Segmentation by Genetic Algorithms

    Rosenberger C


    Full Text Available Abstract Many works in the literature focus on the definition of evaluation metrics and criteria that enable to quantify the performance of an image processing algorithm. These evaluation criteria can be used to define new image processing algorithms by optimizing them. In this paper, we propose a general scheme to segment images by a genetic algorithm. The developed method uses an evaluation criterion which quantifies the quality of an image segmentation result. The proposed segmentation method can integrate a local ground truth when it is available in order to set the desired level of precision of the final result. A genetic algorithm is then used in order to determine the best combination of information extracted by the selected criterion. Then, we show that this approach can either be applied for gray-levels or multicomponents images in a supervised context or in an unsupervised one. Last, we show the efficiency of the proposed method through some experimental results on several gray-levels and multicomponents images.

  4. A New Wavelet-Based Document Image Segmentation Scheme

    赵健; 李道京; 俞卞章; 耿军平


    The document image segmentation is very useful for printing, faxing and data processing. An algorithm is developed for segmenting and classifying document image. Feature used for classification is based on the histogram distribution pattern of different image classes. The important attribute of the algorithm is using wavelet correlation image to enhance raw image's pattern, so the classification accuracy is improved. In this paper document image is divided into four types: background, photo, text and graph. Firstly, the document image background has been distingusished easily by former normally method; secondly, three image types will be distinguished by their typical histograms, in order to make histograms feature clearer, each resolution' s HH wavelet subimage is used to add to the raw image at their resolution. At last, the photo, text and praph have been devided according to how the feature fit to the Laplacian distrbution by -X2 and L. Simulations show that classification accuracy is significantly improved. The comparison with related shows that our algorithm provides both lower classification error rates and better visual results.

  5. Embryonic Heart Morphogenesis from Confocal Microscopy Imaging and Automatic Segmentation

    Hongda Mao


    Full Text Available Embryonic heart morphogenesis (EHM is a complex and dynamic process where the heart transforms from a single tube into a four-chambered pump. This process is of great biological and clinical interest but is still poorly understood for two main reasons. On the one hand, the existing imaging modalities for investigating EHM suffered from either limited penetration depth or limited spatial resolution. On the other hand, current works typically adopted manual segmentation, which was tedious, subjective, and time consuming considering the complexity of developing heart geometry and the large size of images. In this paper, we propose to utilize confocal microscopy imaging with tissue optical immersion clearing technique to image the heart at different stages of development for EHM study. The imaging method is able to produce high spatial resolution images and achieve large penetration depth at the same time. Furthermore, we propose a novel convex active contour model for automatic image segmentation. The model has the ability to deal with intensity fall-off in depth which is characterized by confocal microscopy images. We acquired the images of embryonic quail hearts from day 6 to day 14 of incubation for EHM study. The experimental results were promising and provided us with an insight view of early heart growth pattern and also paved the road for data-driven heart growth modeling.

  6. Deep convolutional networks for pancreas segmentation in CT imaging

    Roth, Holger R.; Farag, Amal; Lu, Le; Turkbey, Evrim B.; Summers, Ronald M.


    Automatic organ segmentation is an important prerequisite for many computer-aided diagnosis systems. The high anatomical variability of organs in the abdomen, such as the pancreas, prevents many segmentation methods from achieving high accuracies when compared to state-of-the-art segmentation of organs like the liver, heart or kidneys. Recently, the availability of large annotated training sets and the accessibility of affordable parallel computing resources via GPUs have made it feasible for "deep learning" methods such as convolutional networks (ConvNets) to succeed in image classification tasks. These methods have the advantage that used classification features are trained directly from the imaging data. We present a fully-automated bottom-up method for pancreas segmentation in computed tomography (CT) images of the abdomen. The method is based on hierarchical coarse-to-fine classification of local image regions (superpixels). Superpixels are extracted from the abdominal region using Simple Linear Iterative Clustering (SLIC). An initial probability response map is generated, using patch-level confidences and a two-level cascade of random forest classifiers, from which superpixel regions with probabilities larger 0.5 are retained. These retained superpixels serve as a highly sensitive initial input of the pancreas and its surroundings to a ConvNet that samples a bounding box around each superpixel at different scales (and random non-rigid deformations at training time) in order to assign a more distinct probability of each superpixel region being pancreas or not. We evaluate our method on CT images of 82 patients (60 for training, 2 for validation, and 20 for testing). Using ConvNets we achieve maximum Dice scores of an average 68% +/- 10% (range, 43-80%) in testing. This shows promise for accurate pancreas segmentation, using a deep learning approach and compares favorably to state-of-the-art methods.

  7. From acoustic segmentation to language processing: evidence from optical imaging.

    Obrig, Hellmuth; Rossi, Sonja; Telkemeyer, Silke; Wartenburger, Isabell


    During language acquisition in infancy and when learning a foreign language, the segmentation of the auditory stream into words and phrases is a complex process. Intuitively, learners use "anchors" to segment the acoustic speech stream into meaningful units like words and phrases. Regularities on a segmental (e.g., phonological) or suprasegmental (e.g., prosodic) level can provide such anchors. Regarding the neuronal processing of these two kinds of linguistic cues a left-hemispheric dominance for segmental and a right-hemispheric bias for suprasegmental information has been reported in adults. Though lateralization is common in a number of higher cognitive functions, its prominence in language may also be a key to understanding the rapid emergence of the language network in infants and the ease at which we master our language in adulthood. One question here is whether the hemispheric lateralization is driven by linguistic input per se or whether non-linguistic, especially acoustic factors, "guide" the lateralization process. Methodologically, functional magnetic resonance imaging provides unsurpassed anatomical detail for such an enquiry. However, instrumental noise, experimental constraints and interference with EEG assessment limit its applicability, pointedly in infants and also when investigating the link between auditory and linguistic processing. Optical methods have the potential to fill this gap. Here we review a number of recent studies using optical imaging to investigate hemispheric differences during segmentation and basic auditory feature analysis in language development.

  8. Lung tumor segmentation in PET images using graph cuts.

    Ballangan, Cherry; Wang, Xiuying; Fulham, Michael; Eberl, Stefan; Feng, David Dagan


    The aim of segmentation of tumor regions in positron emission tomography (PET) is to provide more accurate measurements of tumor size and extension into adjacent structures, than is possible with visual assessment alone and hence improve patient management decisions. We propose a segmentation energy function for the graph cuts technique to improve lung tumor segmentation with PET. Our segmentation energy is based on an analysis of the tumor voxels in PET images combined with a standardized uptake value (SUV) cost function and a monotonic downhill SUV feature. The monotonic downhill feature avoids segmentation leakage into surrounding tissues with similar or higher PET tracer uptake than the tumor and the SUV cost function improves the boundary definition and also addresses situations where the lung tumor is heterogeneous. We evaluated the method in 42 clinical PET volumes from patients with non-small cell lung cancer (NSCLC). Our method improves segmentation and performs better than region growing approaches, the watershed technique, fuzzy-c-means, region-based active contour and tumor customized downhill.

  9. A general approach to liver lesion segmentation in CT images

    Cao, Li; Udupa, Jayaram K.; Odhner, Dewey; Huang, Lidong; Tong, Yubing; Torigian, Drew A.


    Lesion segmentation has remained a challenge in different body regions. Generalizability is lacking in published methods as variability in results is common, even for a given organ and modality, such that it becomes difficult to establish standardized methods of disease quantification and reporting. This paper makes an attempt at a generalizable method based on classifying lesions along with their background into groups using clinically used visual attributes. Using an Iterative Relative Fuzzy Connectedness (IRFC) delineation engine, the ideas are implemented for the task of liver lesion segmentation in computed tomography (CT) images. For lesion groups with the same background properties, a few subjects are chosen as the training set to obtain the optimal IRFC parameters for the background tissue components. For lesion groups with similar foreground properties, optimal foreground parameters for IRFC are set as the median intensity value of the training lesion subset. To segment liver lesions belonging to a certain group, the devised method requires manual loading of the corresponding parameters, and correct setting of the foreground and background seeds. The segmentation is then completed in seconds. Segmentation accuracy and repeatability with respect to seed specification are evaluated. Accuracy is assessed by the assignment of a delineation quality score (DQS) to each case. Inter-operator repeatability is assessed by the difference between segmentations carried out independently by two operators. Experiments on 80 liver lesion cases show that the proposed method achieves a mean DQS score of 4.03 and inter-operator repeatability of 92.3%.

  10. Segmentation of multiple sclerosis lesions in MR images: a review

    Mortazavi, Daryoush; Kouzani, Abbas Z. [Deakin University, School of Engineering, Geelong, Victoria (Australia); Soltanian-Zadeh, Hamid [Henry Ford Health System, Image Analysis Laboratory, Radiology Department, Detroit, MI (United States); University of Tehran, Control and Intelligent Processing Center of Excellence (CIPCE), School of Electrical and Computer Engineering, Tehran (Iran, Islamic Republic of); School of Cognitive Sciences, Institute for Studies in Theoretical Physics and Mathematics (IPM), Tehran (Iran, Islamic Republic of)


    Multiple sclerosis (MS) is an inflammatory demyelinating disease that the parts of the nervous system through the lesions generated in the white matter of the brain. It brings about disabilities in different organs of the body such as eyes and muscles. Early detection of MS and estimation of its progression are critical for optimal treatment of the disease. For diagnosis and treatment evaluation of MS lesions, they may be detected and segmented in Magnetic Resonance Imaging (MRI) scans of the brain. However, due to the large amount of MRI data to be analyzed, manual segmentation of the lesions by clinical experts translates into a very cumbersome and time consuming task. In addition, manual segmentation is subjective and prone to human errors. Several groups have developed computerized methods to detect and segment MS lesions. These methods are not categorized and compared in the past. This paper reviews and compares various MS lesion segmentation methods proposed in recent years. It covers conventional methods like multilevel thresholding and region growing, as well as more recent Bayesian methods that require parameter estimation algorithms. It also covers parameter estimation methods like expectation maximization and adaptive mixture model which are among unsupervised techniques as well as kNN and Parzen window methods that are among supervised techniques. Integration of knowledge-based methods such as atlas-based approaches with Bayesian methods increases segmentation accuracy. In addition, employing intelligent classifiers like Fuzzy C-Means, Fuzzy Inference Systems, and Artificial Neural Networks reduces misclassified voxels. (orig.)

  11. Image Segmentation Using Two Step Splitting Function

    Gopal Kumar Jha


    Full Text Available Image processing and computer vision is widely using Level Set Method (LSM. In conventional level set formulation, irregularities are developed during evolution of level set function, which cause numerical errors and eventually destroy the stability of the evolution. Therefore a numerical remedy called re-initialization is typically applied periodically to replace the degraded level set function. However re –initialization raises serious problem that is when and how it should be performed and also affects numerical accuracy in an undesirable way. To overcome this drawback of re-initialization process, a new variation level set formulation called Distance regularization level set evolution (DRLSE is introduced in which the regularity of the level set function is internally maintained during the level set evolution. DRLSE allows more general and effective initialization of the level set function. But DRLSE uses relatively large number of steps to ensure efficient numerical accuracy. Here in this thesis we are implementing faster and equally efficient computation technique called two step splitting method (TSSM. TSSM is physio-chemical reaction diffusion equation in which firstly LSE equation get iterated and then regularize the level set function from the first step to ensure the stability and hence re-initialization is completely eliminated from LSE which also satisfy DRLSE.

  12. Automated 3D renal segmentation based on image partitioning

    Yeghiazaryan, Varduhi; Voiculescu, Irina D.


    Despite several decades of research into segmentation techniques, automated medical image segmentation is barely usable in a clinical context, and still at vast user time expense. This paper illustrates unsupervised organ segmentation through the use of a novel automated labelling approximation algorithm followed by a hypersurface front propagation method. The approximation stage relies on a pre-computed image partition forest obtained directly from CT scan data. We have implemented all procedures to operate directly on 3D volumes, rather than slice-by-slice, because our algorithms are dimensionality-independent. The results picture segmentations which identify kidneys, but can easily be extrapolated to other body parts. Quantitative analysis of our automated segmentation compared against hand-segmented gold standards indicates an average Dice similarity coefficient of 90%. Results were obtained over volumes of CT data with 9 kidneys, computing both volume-based similarity measures (such as the Dice and Jaccard coefficients, true positive volume fraction) and size-based measures (such as the relative volume difference). The analysis considered both healthy and diseased kidneys, although extreme pathological cases were excluded from the overall count. Such cases are difficult to segment both manually and automatically due to the large amplitude of Hounsfield unit distribution in the scan, and the wide spread of the tumorous tissue inside the abdomen. In the case of kidneys that have maintained their shape, the similarity range lies around the values obtained for inter-operator variability. Whilst the procedure is fully automated, our tools also provide a light level of manual editing.

  13. Comparison of perceptual color spaces for natural image segmentation tasks

    Correa-Tome, Fernando E.; Sanchez-Yanez, Raul E.; Ayala-Ramirez, Victor


    Color image segmentation largely depends on the color space chosen. Furthermore, spaces that show perceptual uniformity seem to outperform others due to their emulation of the human perception of color. We evaluate three perceptual color spaces, CIELAB, CIELUV, and RLAB, in order to determine their contribution to natural image segmentation and to identify the space that obtains the best results over a test set of images. The nonperceptual color space RGB is also included for reference purposes. In order to quantify the quality of resulting segmentations, an empirical discrepancy evaluation methodology is discussed. The Berkeley Segmentation Dataset and Benchmark is used in test series, and two approaches are taken to perform the experiments: supervised pixelwise classification using reference colors, and unsupervised clustering using k-means. A majority filter is used as a postprocessing stage, in order to determine its contribution to the result. Furthermore, a comparison of elapsed times taken by the required transformations is included. The main finding of our study is that the CIELUV color space outperforms the other color spaces in both discriminatory performance and computational speed, for the average case.

  14. Segmentation of color images based on the gravitational clustering concept

    Lai, Andrew H.; Yung, H. C.


    A new clustering algorithm derived from the Markovian model of the gravitational clustering concept is proposed that works in the RGB measurement space for color image. To enable the model to be applicable in image segmentation, the new algorithm imposes a clustering constraint at each clustering iteration to control and determine the formation of multiple clusters. Using such constraint to limit the attraction between clusters, a termination condition can be easily defined. The new clustering algorithm is evaluated objectively and subjectively on three different images against the K-means clustering algorithm, the recursive histogram clustering algorithm for color, the Hedley-Yan algorithm, and the widely used seed-based region growing algorithm. From the evaluation, it is observed that the new algorithm exhibits the following characteristics: (1) its objective measurement figures are comparable with the best in this group of segmentation algorithms; (2) it generates smoother region boundaries; (3) the segmented boundaries align closely with the original boundaries; and (4) it forms a meaningful number of segmented regions.

  15. Interactive segmentation for geographic atrophy in retinal fundus images.

    Lee, Noah; Smith, R Theodore; Laine, Andrew F


    Fundus auto-fluorescence (FAF) imaging is a non-invasive technique for in vivo ophthalmoscopic inspection of age-related macular degeneration (AMD), the most common cause of blindness in developed countries. Geographic atrophy (GA) is an advanced form of AMD and accounts for 12-21% of severe visual loss in this disorder [3]. Automatic quantification of GA is important for determining disease progression and facilitating clinical diagnosis of AMD. The problem of automatic segmentation of pathological images still remains an unsolved problem. In this paper we leverage the watershed transform and generalized non-linear gradient operators for interactive segmentation and present an intuitive and simple approach for geographic atrophy segmentation. We compare our approach with the state of the art random walker [5] algorithm for interactive segmentation using ROC statistics. Quantitative evaluation experiments on 100 FAF images show a mean sensitivity/specificity of 98.3/97.7% for our approach and a mean sensitivity/specificity of 88.2/96.6% for the random walker algorithm.

  16. Superpixel Cut for Figure-Ground Image Segmentation

    Yang, Michael Ying; Rosenhahn, Bodo


    Figure-ground image segmentation has been a challenging problem in computer vision. Apart from the difficulties in establishing an effective framework to divide the image pixels into meaningful groups, the notions of figure and ground often need to be properly defined by providing either user inputs or object models. In this paper, we propose a novel graph-based segmentation framework, called superpixel cut. The key idea is to formulate foreground segmentation as finding a subset of superpixels that partitions a graph over superpixels. The problem is formulated as Min-Cut. Therefore, we propose a novel cost function that simultaneously minimizes the inter-class similarity while maximizing the intra-class similarity. This cost function is optimized using parametric programming. After a small learning step, our approach is fully automatic and fully bottom-up, which requires no high-level knowledge such as shape priors and scene content. It recovers coherent components of images, providing a set of multiscale hypotheses for high-level reasoning. We evaluate our proposed framework by comparing it to other generic figure-ground segmentation approaches. Our method achieves improved performance on state-of-the-art benchmark databases.

  17. Unsupervised segmentation of MRI knees using image partition forests

    Marčan, Marija; Voiculescu, Irina


    Nowadays many people are affected by arthritis, a condition of the joints with limited prevention measures, but with various options of treatment the most radical of which is surgical. In order for surgery to be successful, it can make use of careful analysis of patient-based models generated from medical images, usually by manual segmentation. In this work we show how to automate the segmentation of a crucial and complex joint -- the knee. To achieve this goal we rely on our novel way of representing a 3D voxel volume as a hierarchical structure of partitions which we have named Image Partition Forest (IPF). The IPF contains several partition layers of increasing coarseness, with partitions nested across layers in the form of adjacency graphs. On the basis of a set of properties (size, mean intensity, coordinates) of each node in the IPF we classify nodes into different features. Values indicating whether or not any particular node belongs to the femur or tibia are assigned through node filtering and node-based region growing. So far we have evaluated our method on 15 MRI knee images. Our unsupervised segmentation compared against a hand-segmented gold standard has achieved an average Dice similarity coefficient of 0.95 for femur and 0.93 for tibia, and an average symmetric surface distance of 0.98 mm for femur and 0.73 mm for tibia. The paper also discusses ways to introduce stricter morphological and spatial conditioning in the bone labelling process.

  18. The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS).

    Menze, Bjoern H; Jakab, Andras; Bauer, Stefan; Kalpathy-Cramer, Jayashree; Farahani, Keyvan; Kirby, Justin; Burren, Yuliya; Porz, Nicole; Slotboom, Johannes; Wiest, Roland; Lanczi, Levente; Gerstner, Elizabeth; Weber, Marc-André; Arbel, Tal; Avants, Brian B; Ayache, Nicholas; Buendia, Patricia; Collins, D Louis; Cordier, Nicolas; Corso, Jason J; Criminisi, Antonio; Das, Tilak; Delingette, Hervé; Demiralp, Çağatay; Durst, Christopher R; Dojat, Michel; Doyle, Senan; Festa, Joana; Forbes, Florence; Geremia, Ezequiel; Glocker, Ben; Golland, Polina; Guo, Xiaotao; Hamamci, Andac; Iftekharuddin, Khan M; Jena, Raj; John, Nigel M; Konukoglu, Ender; Lashkari, Danial; Mariz, José Antonió; Meier, Raphael; Pereira, Sérgio; Precup, Doina; Price, Stephen J; Raviv, Tammy Riklin; Reza, Syed M S; Ryan, Michael; Sarikaya, Duygu; Schwartz, Lawrence; Shin, Hoo-Chang; Shotton, Jamie; Silva, Carlos A; Sousa, Nuno; Subbanna, Nagesh K; Szekely, Gabor; Taylor, Thomas J; Thomas, Owen M; Tustison, Nicholas J; Unal, Gozde; Vasseur, Flor; Wintermark, Max; Ye, Dong Hye; Zhao, Liang; Zhao, Binsheng; Zikic, Darko; Prastawa, Marcel; Reyes, Mauricio; Van Leemput, Koen


    In this paper we report the set-up and results of the Multimodal Brain Tumor Image Segmentation Benchmark (BRATS) organized in conjunction with the MICCAI 2012 and 2013 conferences. Twenty state-of-the-art tumor segmentation algorithms were applied to a set of 65 multi-contrast MR scans of low- and high-grade glioma patients-manually annotated by up to four raters-and to 65 comparable scans generated using tumor image simulation software. Quantitative evaluations revealed considerable disagreement between the human raters in segmenting various tumor sub-regions (Dice scores in the range 74%-85%), illustrating the difficulty of this task. We found that different algorithms worked best for different sub-regions (reaching performance comparable to human inter-rater variability), but that no single algorithm ranked in the top for all sub-regions simultaneously. Fusing several good algorithms using a hierarchical majority vote yielded segmentations that consistently ranked above all individual algorithms, indicating remaining opportunities for further methodological improvements. The BRATS image data and manual annotations continue to be publicly available through an online evaluation system as an ongoing benchmarking resource.


    Zou Ning; Liu Jian; Zhou Manli; Li Qing


    This paper presents an unsupervised range image segmentation based on Kohonen neural network. At first, the derivative and partial derivative of each point are calculated and the normal in each points is gotten. With the character vectors including normal and range value, self-organization map is introduced to cluster. The normal analysis is used to eliminate over-segmentation and the last result is gotten. This method avoid selecting original seeds and uses fewer samples, moreover computes rapidly. The experiment shows the better performance.

  20. Sequence-independent segmentation of magnetic resonance images.

    Fischl, Bruce; Salat, David H; van der Kouwe, André J W; Makris, Nikos; Ségonne, Florent; Quinn, Brian T; Dale, Anders M


    We present a set of techniques for embedding the physics of the imaging process that generates a class of magnetic resonance images (MRIs) into a segmentation or registration algorithm. This results in substantial invariance to acquisition parameters, as the effect of these parameters on the contrast properties of various brain structures is explicitly modeled in the segmentation. In addition, the integration of image acquisition with tissue classification allows the derivation of sequences that are optimal for segmentation purposes. Another benefit of these procedures is the generation of probabilistic models of the intrinsic tissue parameters that cause MR contrast (e.g., T1, proton density, T2*), allowing access to these physiologically relevant parameters that may change with disease or demographic, resulting in nonmorphometric alterations in MR images that are otherwise difficult to detect. Finally, we also present a high band width multiecho FLASH pulse sequence that results in high signal-to-noise ratio with minimal image distortion due to B0 effects. This sequence has the added benefit of allowing the explicit estimation of T2* and of reducing test-retest intensity variability.

  1. An eSnake model for medical image segmentation

    L(U) Hongyu; YUAN Kehong; BAO Shanglian; ZU Donglin; DUAN Chaijie


    A novel scheme of external force for detecting the object boundary of medical image based on Snakes (active contours)is introduced in the paper. In our new method, an electrostatic field on a template plane above the original image plane is designed to form the map of the external force. Compared with the method of Gradient Vector Flow (GVF), our approach has clear physical meanings. It has stronger ability to conform to boundary concavities, is simple to implement, and reliable for shape segmenting. Additionally, our method has larger capture range for the external force and is useful for medical image preprocessing in various applications. Finally, by adding the balloon force to the electrostatic field model, our Snake is able to represent long tube-like shapes or shapes with significant protrusions or bifurcations, and it has the specialty to prevent Snake leaking from large gaps on image edge by using a two-stage segmentation technique introduced in this paper. The test of our models proves that our methods are robust, precise in medical image segmentation.

  2. Cryo-EM Structure Determination Using Segmented Helical Image Reconstruction.

    Fromm, S A; Sachse, C


    Treating helices as single-particle-like segments followed by helical image reconstruction has become the method of choice for high-resolution structure determination of well-ordered helical viruses as well as flexible filaments. In this review, we will illustrate how the combination of latest hardware developments with optimized image processing routines have led to a series of near-atomic resolution structures of helical assemblies. Originally, the treatment of helices as a sequence of segments followed by Fourier-Bessel reconstruction revealed the potential to determine near-atomic resolution structures from helical specimens. In the meantime, real-space image processing of helices in a stack of single particles was developed and enabled the structure determination of specimens that resisted classical Fourier helical reconstruction and also facilitated high-resolution structure determination. Despite the progress in real-space analysis, the combination of Fourier and real-space processing is still commonly used to better estimate the symmetry parameters as the imposition of the correct helical symmetry is essential for high-resolution structure determination. Recent hardware advancement by the introduction of direct electron detectors has significantly enhanced the image quality and together with improved image processing procedures has made segmented helical reconstruction a very productive cryo-EM structure determination method.

  3. Automatic character detection and segmentation in natural scene images

    ZHU Kai-hua; QI Fei-hu; JIANG Ren-jie; XU Li


    We present a robust connected-component (CC) based method for automatic detection and segmentation of text in real-scene images. This technique can be applied in robot vision, sign recognition, meeting processing and video indexing. First, a Non-Linear Niblack method (NLNiblack) is proposed to decompose the image into candidate CCs. Then, all these CCs are fed into a cascade of classifiers trained by Adaboost algorithm. Each classifier in the cascade responds to one feature of the CC. Proposed here are 12 novel features which are insensitive to noise, scale, text orientation and text language. The classifier cascade allows non-text CCs of the image to be rapidly discarded while more computation is spent on promising text-like CCs. The CCs passing through the cascade are considered as text components and are used to form the segmentation result. A prototype system was built,with experimental results proving the effectiveness and efficiency of the proposed method.

  4. Minimum description length synthetic aperture radar image segmentation.

    Galland, Frédéric; Bertaux, Nicolas; Réfrégier, Philippe


    We present a new minimum description length (MDL) approach based on a deformable partition--a polygonal grid--for automatic segmentation of a speckled image composed of several homogeneous regions. The image segmentation thus consists in the estimation of the polygonal grid, or, more precisely, its number of regions, its number of nodes and the location of its nodes. These estimations are performed by minimizing a unique MDL criterion which takes into account the probabilistic properties of speckle fluctuations and a measure of the stochastic complexity of the polygonal grid. This approach then leads to a global MDL criterion without an undetermined parameter since no other regularization term than the stochastic complexity of the polygonal grid is necessary and noise parameters can be estimated with maximum likelihood-like approaches. The performance of this technique is illustrated on synthetic and real synthetic aperture radar images of agricultural regions and the influence of different terms of the model is analyzed.

  5. Image segmentation for enhancing symbol recognition in prosthetic vision.

    Horne, Lachlan; Barnes, Nick; McCarthy, Chris; He, Xuming


    Current and near-term implantable prosthetic vision systems offer the potential to restore some visual function, but suffer from poor resolution and dynamic range of induced phosphenes. This can make it difficult for users of prosthetic vision systems to identify symbolic information (such as signs) except in controlled conditions. Using image segmentation techniques from computer vision, we show it is possible to improve the clarity of such symbolic information for users of prosthetic vision implants in uncontrolled conditions. We use image segmentation to automatically divide a natural image into regions, and using a fixation point controlled by the user, select a region to phosphenize. This technique improves the apparent contrast and clarity of symbolic information over traditional phosphenization approaches.

  6. Multi-scale classification based lesion segmentation for dermoscopic images.

    Abedini, Mani; Codella, Noel; Chakravorty, Rajib; Garnavi, Rahil; Gutman, David; Helba, Brian; Smith, John R


    This paper presents a robust segmentation method based on multi-scale classification to identify the lesion boundary in dermoscopic images. Our proposed method leverages a collection of classifiers which are trained at various resolutions to categorize each pixel as "lesion" or "surrounding skin". In detection phase, trained classifiers are applied on new images. The classifier outputs are fused at pixel level to build probability maps which represent lesion saliency maps. In the next step, Otsu thresholding is applied to convert the saliency maps to binary masks, which determine the border of the lesions. We compared our proposed method with existing lesion segmentation methods proposed in the literature using two dermoscopy data sets (International Skin Imaging Collaboration and Pedro Hispano Hospital) which demonstrates the superiority of our method with Dice Coefficient of 0.91 and accuracy of 94%.

  7. Underwater acoustic image segmentation based on deformable template

    SANG Enfang; LIU Zhuofu


    In order to solve the problem of deformation and blurred edge in underwater acoustic image segmentation, an approach based on the deformable template is presented. Compared with the energy minimization of the Snake model, the energy function is redefined by adding a shape restriction. This improves the noise-resistance ability so that robustness and high segmentation efficiency are acquired. The energy optimization problem is tackled using the Dijkstra Algorithm. This method has been successfully tested on the filled-in acoustic images.The results show that this algorithm is efficient, precise and very immune to image deformation and noise when compared to results obtained from the Snake model and several traditional optimization methods.

  8. Segmentation of Sinus Images for Grading of Severity of Sinusitis

    Iznita Izhar, Lila; Sagayan Asirvadam, Vijanth; Lee, San Nien

    Sinusitis is commonly diagnosed with techniques such as endoscopy, ultrasound, X-ray, Computed Tomography (CT) scan and Magnetic Resonance Imaging (MRI). Out of these techniques, imaging techniques are less invasive while being able to show blockage of sinus cavities. This project attempts to develop a computerize system by developing algorithm for the segmentation of sinus images for the detection of sinusitis. The sinus images were firstly undergo noise removal process by median filtering followed by Contrast Limited Adapted Histogram Equalisation (CLAHE) for image enhancement. Multilevel thresholding algorithm were then applied to segment the enhanced images into meaningful regions for the detection and diagnosis of severity of sinusitis. The multilevel thresholding algorithms based on Otsu method were able to extract three distinct and important features namely bone region, hollow and mucous areas from the images. Simulations were performed on images of healthy sinuses and sinuses with sinusitis. The developed algorithms are found to be able to differentiate and evaluate healthy sinuses and sinuses with sinusitis effectively.

  9. Image segmentation by EM-based adaptive pulse coupled neural networks in brain magnetic resonance imaging.

    Fu, J C; Chen, C C; Chai, J W; Wong, S T C; Li, I C


    We propose an automatic hybrid image segmentation model that integrates the statistical expectation maximization (EM) model and the spatial pulse coupled neural network (PCNN) for brain magnetic resonance imaging (MRI) segmentation. In addition, an adaptive mechanism is developed to fine tune the PCNN parameters. The EM model serves two functions: evaluation of the PCNN image segmentation and adaptive adjustment of the PCNN parameters for optimal segmentation. To evaluate the performance of the adaptive EM-PCNN, we use it to segment MR brain image into gray matter (GM), white matter (WM) and cerebrospinal fluid (CSF). The performance of the adaptive EM-PCNN is compared with that of the non-adaptive EM-PCNN, EM, and Bias Corrected Fuzzy C-Means (BCFCM) algorithms. The result is four sets of boundaries for the GM and the brain parenchyma (GM+WM), the two regions of most interest in medical research and clinical applications. Each set of boundaries is compared with the golden standard to evaluate the segmentation performance. The adaptive EM-PCNN significantly outperforms the non-adaptive EM-PCNN, EM, and BCFCM algorithms in gray mater segmentation. In brain parenchyma segmentation, the adaptive EM-PCNN significantly outperforms the BCFCM only. However, the adaptive EM-PCNN is better than the non-adaptive EM-PCNN and EM on average. We conclude that of the three approaches, the adaptive EM-PCNN yields the best results for gray matter and brain parenchyma segmentation.

  10. Image segmentation based on scaled fuzzy membership functions

    Jantzen, Jan; Ring,, P.; Christiansen, Pernille


    As a basis for an automated interpretation of magnetic resonance images, the authors propose a fuzzy segmentation method. The method uses five standard fuzzy membership functions: small, small medium, medium, large medium, and large. The method fits these membership functions to the modes...... of interest in the image histogram by means of a piecewise-linear transformation. A test example is given concerning a human head image, including a sensitivity analysis based on the fuzzy area measure. The method provides a rule-based interface to the physician...

  11. Control of multiple excited image states around segmented carbon nanotubes

    Knörzer, J., E-mail:; Fey, C., E-mail: [Zentrum für Optische Quantentechnologien, Universität Hamburg, Luruper Chaussee 149, Hamburg 22761 (Germany); Sadeghpour, H. R. [ITAMP, Harvard-Smithsonian Center for Astrophysics, 60 Garden Street, Cambridge, Massachusetts 02138 (United States); Schmelcher, P. [Zentrum für Optische Quantentechnologien, Universität Hamburg, Luruper Chaussee 149, Hamburg 22761 (Germany); The Hamburg Centre for Ultrafast Imaging, Luruper Chaussee 149, Hamburg 22761 (Germany)


    Electronic image states around segmented carbon nanotubes can be confined and shaped along the nanotube axis by engineering the image potential. We show how several such image states can be prepared simultaneously along the same nanotube. The inter-electronic distance can be controlled a priori by engineering tubes of specific geometries. High sensitivity to external electric and magnetic fields can be exploited to manipulate these states and their mutual long-range interactions. These building blocks provide access to a new kind of tailored interacting quantum systems.

  12. Colour image segmentation using unsupervised clustering technique for acute leukemia images

    Halim, N. H. Abd; Mashor, M. Y.; Nasir, A. S. Abdul; Mustafa, N.; Hassan, R.


    Colour image segmentation has becoming more popular for computer vision due to its important process in most medical analysis tasks. This paper proposes comparison between different colour components of RGB(red, green, blue) and HSI (hue, saturation, intensity) colour models that will be used in order to segment the acute leukemia images. First, partial contrast stretching is applied on leukemia images to increase the visual aspect of the blast cells. Then, an unsupervised moving k-means clustering algorithm is applied on the various colour components of RGB and HSI colour models for the purpose of segmentation of blast cells from the red blood cells and background regions in leukemia image. Different colour components of RGB and HSI colour models have been analyzed in order to identify the colour component that can give the good segmentation performance. The segmented images are then processed using median filter and region growing technique to reduce noise and smooth the images. The results show that segmentation using saturation component of HSI colour model has proven to be the best in segmenting nucleus of the blast cells in acute leukemia image as compared to the other colour components of RGB and HSI colour models.

  13. An image processing pipeline to detect and segment nuclei in muscle fiber microscopic images.

    Guo, Yanen; Xu, Xiaoyin; Wang, Yuanyuan; Wang, Yaming; Xia, Shunren; Yang, Zhong


    Muscle fiber images play an important role in the medical diagnosis and treatment of many muscular diseases. The number of nuclei in skeletal muscle fiber images is a key bio-marker of the diagnosis of muscular dystrophy. In nuclei segmentation one primary challenge is to correctly separate the clustered nuclei. In this article, we developed an image processing pipeline to automatically detect, segment, and analyze nuclei in microscopic image of muscle fibers. The pipeline consists of image pre-processing, identification of isolated nuclei, identification and segmentation of clustered nuclei, and quantitative analysis. Nuclei are initially extracted from background by using local Otsu's threshold. Based on analysis of morphological features of the isolated nuclei, including their areas, compactness, and major axis lengths, a Bayesian network is trained and applied to identify isolated nuclei from clustered nuclei and artifacts in all the images. Then a two-step refined watershed algorithm is applied to segment clustered nuclei. After segmentation, the nuclei can be quantified for statistical analysis. Comparing the segmented results with those of manual analysis and an existing technique, we find that our proposed image processing pipeline achieves good performance with high accuracy and precision. The presented image processing pipeline can therefore help biologists increase their throughput and objectivity in analyzing large numbers of nuclei in muscle fiber images.

  14. Pulmonary Vascular Tree Segmentation from Contrast-Enhanced CT Images

    Helmberger, M; Pienn, M; Balint, Z; Olschewski, A; Bischof, H


    We present a pulmonary vessel segmentation algorithm, which is fast, fully automatic and robust. It uses a coarse segmentation of the airway tree and a left and right lung labeled volume to restrict a vessel enhancement filter, based on an offset medialness function, to the lungs. We show the application of our algorithm on contrast-enhanced CT images, where we derive a clinical parameter to detect pulmonary hypertension (PH) in patients. Results on a dataset of 24 patients show that quantitative indices derived from the segmentation are applicable to distinguish patients with and without PH. Further work-in-progress results are shown on the VESSEL12 challenge dataset, which is composed of non-contrast-enhanced scans, where we range in the midfield of participating contestants.

  15. Optimal segmentation of pupillometric images for estimating pupil shape parameters.

    De Santis, A; Iacoviello, D


    The problem of determining the pupil morphological parameters from pupillometric data is considered. These characteristics are of great interest for non-invasive early diagnosis of the central nervous system response to environmental stimuli of different nature, in subjects suffering some typical diseases such as diabetes, Alzheimer disease, schizophrenia, drug and alcohol addiction. Pupil geometrical features such as diameter, area, centroid coordinates, are estimated by a procedure based on an image segmentation algorithm. It exploits the level set formulation of the variational problem related to the segmentation. A discrete set up of this problem that admits a unique optimal solution is proposed: an arbitrary initial curve is evolved towards the optimal segmentation boundary by a difference equation; therefore no numerical approximation schemes are needed, as required in the equivalent continuum formulation usually adopted in the relevant literature.

  16. Automatic segmentation of trophectoderm in microscopic images of human blastocysts.

    Singh, Amarjot; Au, Jason; Saeedi, Parvaneh; Havelock, Jon


    Accurate assessment of embryos viability is an extremely important task in the optimization of in vitro fertilization treatment outcome. One of the common ways of assessing the quality of a human embryo is grading it on its fifth day of development based on morphological quality of its three main components (Trophectoderm, Inner Cell Mass, and the level of expansion or the thickness of its Zona Pellucida). In this study, we propose a fully automatic method for segmentation and measurement of TE region of blastocysts (day-5 human embryos). Here, we eliminate the inhomogeneities of the blastocysts surface using the Retinex theory and further apply a level-set algorithm to segment the TE regions. We have tested our method on a dataset of 85 images and have been able to achieve a segmentation accuracy of 84.6% for grade A, 89.0% for grade B, and 91.7% for grade C embryos.

  17. Color Image Segmentation using Kohonen Self-Organizing Map (SOM

    I Komang Ariana


    Full Text Available Color image segmentation using Kohonen Self-Organizing Map (SOM, is proposed in this study. RGB color space is used as input in the process of clustering by SOM. Measurement of the distance between weight vector and input vector in learning and recognition stages in SOM method, uses Normalized Euclidean Distance. Then, the validity of clustering result is tested by Davies-Bouldin Index (DBI and Validity Measure (VM to determine the most optimal number of cluster. The clustering result, according to the most optimal number of cluster, then is processed with spatial operations. Spatial operations are used to eliminate noise and small regions which are formed from the clustering result. This system allows segmentation process become automatic and unsupervised. The segmentation results are close to human perception.

  18. Object-Based and Semantic Image Segmentation Using MRF

    Feng Li


    Full Text Available The problem that the Markov random field (MRF model captures the structural as well as the stochastic textures for remote sensing image segmentation is considered. As the one-point clique, namely, the external field, reflects the priori knowledge of the relative likelihood of the different region types which is often unknown, one would like to consider only two-pairwise clique in the texture. To this end, the MRF model cannot satisfactorily capture the structural component of the texture. In order to capture the structural texture, in this paper, a reference image is used as the external field. This reference image is obtained by Wold model decomposition which produces a purely random texture image and structural texture image from the original image. The structural component depicts the periodicity and directionality characteristics of the texture, while the former describes the stochastic. Furthermore, in order to achieve a good result of segmentation, such as improving smoothness of the texture edge, the proportion between the external and internal fields should be estimated by regarding it as a parameter of the MRF model. Due to periodicity of the structural texture, a useful by-product is that some long-range interaction is also taken into account. In addition, in order to reduce computation, a modified version of parameter estimation method is presented. Experimental results on remote sensing image demonstrating the performance of the algorithm are presented.

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

    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.

  20. On the Splitting Algorithm Based on Multi-target Model for Image Segmentation

    Yuezhongyi Sun


    Against to the different regions of membership functions indicated image in the traditional image segmentation variational model, resulting segmentation is not clear, de-noising effect is not obvious problems, this paper proposes multi-target model for image segmentation and the splitting algorithm. The model uses a sparse regularization method to maintain the boundaries of segmented regions, to overcome the disadvantages of segmentation fuzzy boundaries resulting from total variation regular...

  1. Joint graph cut and relative fuzzy connectedness image segmentation algorithm.

    Ciesielski, Krzysztof Chris; Miranda, Paulo A V; Falcão, Alexandre X; Udupa, Jayaram K


    We introduce an image segmentation algorithm, called GC(sum)(max), which combines, in novel manner, the strengths of two popular algorithms: Relative Fuzzy Connectedness (RFC) and (standard) Graph Cut (GC). We show, both theoretically and experimentally, that GC(sum)(max) preserves robustness of RFC with respect to the seed choice (thus, avoiding "shrinking problem" of GC), while keeping GC's stronger control over the problem of "leaking though poorly defined boundary segments." The analysis of GC(sum)(max) is greatly facilitated by our recent theoretical results that RFC can be described within the framework of Generalized GC (GGC) segmentation algorithms. In our implementation of GC(sum)(max) we use, as a subroutine, a version of RFC algorithm (based on Image Forest Transform) that runs (provably) in linear time with respect to the image size. This results in GC(sum)(max) running in a time close to linear. Experimental comparison of GC(sum)(max) to GC, an iterative version of RFC (IRFC), and power watershed (PW), based on a variety medical and non-medical images, indicates superior accuracy performance of GC(sum)(max) over these other methods, resulting in a rank ordering of GC(sum)(max)>PW∼IRFC>GC.

  2. From acoustic segmentation to language processing: evidence from optical imaging

    Hellmuth Obrig


    Full Text Available During language acquisition in infancy and when learning a foreign language, the segmentation of the auditory stream into words and phrases is a complex process. Intuitively, learners use ‘anchors’ to segment the acoustic speech stream into meaningful units like words and phrases. Regularities on a segmental (e.g., phonological or suprasegmental (e.g., prosodic level can provide such anchors. Regarding the neuronal processing of these two kinds of linguistic cues a left hemispheric dominance for segmental and a right hemispheric bias for suprasegmental information has been reported in adults. Though lateralization is common in a number of higher cognitive functions, its prominence in language may also be a key to understanding the rapid emergence of the language network in infants and the ease at which we master our language in adulthood. One question here is whether the hemispheric lateralization is driven by linguistic input per se or whether non-linguistic, especially acoustic factors, ‘guide’ the lateralization process. Methodologically, fMRI provides unsurpassed anatomical detail for such an enquiry. However, instrumental noise, experimental constraints and interference with EEG assessment limit its applicability, pointedly in infants and also when investigating the link between auditory and linguistic processing. Optical methods have the potential to fill this gap. Here we review a number of recent studies using optical imaging to investigate hemispheric differences during segmentation and basic auditory feature analysis in language development.

  3. Brain MR image segmentation improved algorithm based on probability

    Liao, Hengxu; Liu, Gang; Guo, Xiantang


    Local weight voting algorithm is a kind of current mainstream segmentation algorithm. It takes full account of the influences of the likelihood of image likelihood and the prior probabilities of labels on the segmentation results. But this method still can be improved since the essence of this method is to get the label with the maximum probability. If the probability of a label is 70%, it may be acceptable in mathematics. But in the actual segmentation, it may be wrong. So we use the matrix completion algorithm as a supplement. When the probability of the former is larger, the result of the former algorithm is adopted. When the probability of the later is larger, the result of the later algorithm is adopted. This is equivalent to adding an automatic algorithm selection switch that can theoretically ensure that the accuracy of the algorithm we propose is superior to the local weight voting algorithm. At the same time, we propose an improved matrix completion algorithm based on enumeration method. In addition, this paper also uses a multi-parameter registration model to reduce the influence that the registration made on the segmentation. The experimental results show that the accuracy of the algorithm is better than the common segmentation algorithm.


    Srikanth Prabhu


    Full Text Available The role of segmentation in image processing is to separate foreground from background. In this process, the features become clearly visible when appropriate filters are applied on the image. In this paper emphasis has been laid on segmentation of biometric retinal images to filter out the vessels explicitly for evaluating the bifurcation points and features for diabetic retinopathy. Segmentation on images is performed by calculating ridges or morphology. Ridges are those areas in the images where there is sharp contrast in features. Morphology targets the features using structuring elements. Structuring elements are of different shapes like disk, line which is used for extracting features of those shapes. When segmentation was performed on retinal images problems were encountered during image pre-processing stage. Also edge detection techniques have been deployed to find out the contours of the retinal images. After the segmentation has been performed, it has been seen that artifacts of the retinal images have been minimal when ridge based segmentation technique was deployed. In the field of Health Care Management, image segmentation has an important role to play as it determines whether a person is normal or having any disease specially diabetes. During the process of segmentation, diseased features are classified as diseased one’s or artifacts. The problem comes when artifacts are classified as diseased ones. This results in misclassification which has been discussed in the analysis Section. We have achieved fast computing with better performance, in terms of speed for non-repeating features, when compared to repeating features.

  5. Binary image segmentation based on optimized parallel K-means

    Qiu, Xiao-bing; Zhou, Yong; Lin, Li


    K-means is a classic unsupervised learning clustering algorithm. In theory, it can work well in the field of image segmentation. But compared with other segmentation algorithms, this algorithm needs much more computation, and segmentation speed is slow. This limits its application. With the emergence of general-purpose computing on the GPU and the release of CUDA, some scholars try to implement K-means algorithm in parallel on the GPU, and applied to image segmentation at the same time. They have achieved some results, but the approach they use is not completely parallel, not take full advantage of GPU's super computing power. K-means algorithm has two core steps: label and update, in current parallel realization of K-means, only labeling is parallel, update operation is still serial. In this paper, both of the two steps in K-means will be parallel to improve the degree of parallelism and accelerate this algorithm. Experimental results show that this improvement has reached a much quicker speed than the previous research.

  6. a Method of Tomato Image Segmentation Based on Mutual Information and Threshold Iteration

    Wu, Hongxia; Li, Mingxi

    Threshold Segmentation is a kind of important image segmentation method and one of the important preconditioning steps of image detection and recognition, and it has very broad application during the research scopes of the computer vision. According to the internal relation between segment image and original image, a tomato image automatic optimization segmentation method (MI-OPT) which mutual information associate with optimum threshold iteration was presented. Simulation results show that this method has a better image segmentation effect on the tomato images of mature period and little background color difference or different color.

  7. Segmentation and Content-Based Watermarking for Color Image and Image Region Indexing and Retrieval

    Nikolaos V. Boulgouris


    Full Text Available In this paper, an entirely novel approach to image indexing is presented using content-based watermarking. The proposed system uses color image segmentation and watermarking in order to facilitate content-based indexing, retrieval and manipulation of digital images and image regions. A novel segmentation algorithm is applied on reduced images and the resulting segmentation mask is embedded in the image using watermarking techniques. In each region of the image, indexing information is additionally embedded. In this way, the proposed system is endowed with content-based access and indexing capabilities which can be easily exploited via a simple watermark detection process. Several experiments have shown the potential of this approach.

  8. Image Segmentation in Liquid Argon Time Projection Chamber Detector

    Płoński, Piotr; Sulej, Robert; Zaremba, Krzysztof


    The Liquid Argon Time Projection Chamber (LAr-TPC) detectors provide excellent imaging and particle identification ability for studying neutrinos. An efficient and automatic reconstruction procedures are required to exploit potential of this imaging technology. Herein, a novel method for segmentation of images from LAr-TPC detectors is presented. The proposed approach computes a feature descriptor for each pixel in the image, which characterizes amplitude distribution in pixel and its neighbourhood. The supervised classifier is employed to distinguish between pixels representing particle's track and noise. The classifier is trained and evaluated on the hand-labeled dataset. The proposed approach can be a preprocessing step for reconstructing algorithms working directly on detector images.

  9. Removing the twin image in digital holography by segmented filtering of in-focus twin image


    We propose and investigate a new digital method for the reduction of twin-image noise from digital Fresnel holograms. For the case of in-line Fresnel holography the unwanted twin is present as a highly corruptive noise when the object image is numerically reconstructed. We propose to firstly reconstruct the unwanted twin-image when it is in-focus and in this plane we calculate a segmentation mask that borders this in focus image. The twin-image is then segmented and removed by sim...

  10. Joint Image Reconstruction and Segmentation Using the Potts Model

    Storath, Martin; Frikel, Jürgen; Unser, Michael


    We propose a new algorithmic approach to the non-smooth and non-convex Potts problem (also called piecewise-constant Mumford-Shah problem) for inverse imaging problems. We derive a suitable splitting into specific subproblems that can all be solved efficiently. Our method does not require a priori knowledge on the gray levels nor on the number of segments of the reconstruction. Further, it avoids anisotropic artifacts such as geometric staircasing. We demonstrate the suitability of our method for joint image reconstruction and segmentation from limited data in x-ray and photoacoustic tomography. For instance, our method is able to reconstruct the Shepp-Logan phantom from $7$ angular views only. We demonstrate the practical applicability in an experiment with real PET data.

  11. Structured Learning of Tree Potentials in CRF for Image Segmentation.

    Liu, Fayao; Lin, Guosheng; Qiao, Ruizhi; Shen, Chunhua


    We propose a new approach to image segmentation, which exploits the advantages of both conditional random fields (CRFs) and decision trees. In the literature, the potential functions of CRFs are mostly defined as a linear combination of some predefined parametric models, and then, methods, such as structured support vector machines, are applied to learn those linear coefficients. We instead formulate the unary and pairwise potentials as nonparametric forests--ensembles of decision trees, and learn the ensemble parameters and the trees in a unified optimization problem within the large-margin framework. In this fashion, we easily achieve nonlinear learning of potential functions on both unary and pairwise terms in CRFs. Moreover, we learn classwise decision trees for each object that appears in the image. Experimental results on several public segmentation data sets demonstrate the power of the learned nonlinear nonparametric potentials.

  12. Point based interactive image segmentation using multiquadrics splines

    Meena, Sachin; Duraisamy, Prakash; Palniappan, Kannappan; Seetharaman, Guna


    Multiquadrics (MQ) are radial basis spline function that can provide an efficient interpolation of data points located in a high dimensional space. MQ were developed by Hardy to approximate geographical surfaces and terrain modelling. In this paper we frame the task of interactive image segmentation as a semi-supervised interpolation where an interpolating function learned from the user provided seed points is used to predict the labels of unlabeled pixel and the spline function used in the semi-supervised interpolation is MQ. This semi-supervised interpolation framework has a nice closed form solution which along with the fact that MQ is a radial basis spline function lead to a very fast interactive image segmentation process. Quantitative and qualitative results on the standard datasets show that MQ outperforms other regression based methods, GEBS, Ridge Regression and Logistic Regression, and popular methods like Graph Cut,4 Random Walk and Random Forest.6

  13. Multi-atlas segmentation of biomedical images: A survey.

    Iglesias, Juan Eugenio; Sabuncu, Mert R


    Multi-atlas segmentation (MAS), first introduced and popularized by the pioneering work of Rohlfing, et al. (2004), Klein, et al. (2005), and Heckemann, et al. (2006), is becoming one of the most widely-used and successful image segmentation techniques in biomedical applications. By manipulating and utilizing the entire dataset of "atlases" (training images that have been previously labeled, e.g., manually by an expert), rather than some model-based average representation, MAS has the flexibility to better capture anatomical variation, thus offering superior segmentation accuracy. This benefit, however, typically comes at a high computational cost. Recent advancements in computer hardware and image processing software have been instrumental in addressing this challenge and facilitated the wide adoption of MAS. Today, MAS has come a long way and the approach includes a wide array of sophisticated algorithms that employ ideas from machine learning, probabilistic modeling, optimization, and computer vision, among other fields. This paper presents a survey of published MAS algorithms and studies that have applied these methods to various biomedical problems. In writing this survey, we have three distinct aims. Our primary goal is to document how MAS was originally conceived, later evolved, and now relates to alternative methods. Second, this paper is intended to be a detailed reference of past research activity in MAS, which now spans over a decade (2003-2014) and entails novel methodological developments and application-specific solutions. Finally, our goal is to also present a perspective on the future of MAS, which, we believe, will be one of the dominant approaches in biomedical image segmentation.

  14. Interactive segmentation for geographic atrophy in retinal fundus images

    Lee, Noah; SMITH, R. THEODORE; Laine, Andrew F.


    Fundus auto-fluorescence (FAF) imaging is a non-invasive technique for in vivo ophthalmoscopic inspection of age-related macular degeneration (AMD), the most common cause of blindness in developed countries. Geographic atrophy (GA) is an advanced form of AMD and accounts for 12–21% of severe visual loss in this disorder [3]. Automatic quantification of GA is important for determining disease progression and facilitating clinical diagnosis of AMD. The problem of automatic segmentation of patho...

  15. Image segmentation based on Mumford-Shah functional

    CHEN Xu-feng(陈旭锋); GUAN Zhi-cheng(管志成)


    In this paper, the authors propose a new model for active contours segmentation in a given image, based on Mumford-Shah functional (Mumford and Shah, 1989). The model is composed of a system of differential and integral equations. By the experimental results we can keep the advantages of Chan and Vese's model (Chan and Vese, 2001) and avoid the regularization for Dirac function. More importantly, in theory we prove that the system has a unique viscosity solution.

  16. SAR and Oblique Aerial Optical Image Fusion for Urban Area Image Segmentation

    Fagir, J.; Schubert, A.; Frioud, M.; Henke, D.


    The fusion of synthetic aperture radar (SAR) and optical data is a dynamic research area, but image segmentation is rarely treated. While a few studies use low-resolution nadir-view optical images, we approached the segmentation of SAR and optical images acquired from the same airborne platform - leading to an oblique view with high resolution and thus increased complexity. To overcome the geometric differences, we generated a digital surface model (DSM) from adjacent optical images and used it to project both the DSM and SAR data into the optical camera frame, followed by segmentation with each channel. The fused segmentation algorithm was found to out-perform the single-channel version.

  17. Nucleus segmentation in histology images with hierarchical multilevel thresholding

    Ahmady Phoulady, Hady; Goldgof, Dmitry B.; Hall, Lawrence O.; Mouton, Peter R.


    Automatic segmentation of histological images is an important step for increasing throughput while maintaining high accuracy, avoiding variation from subjective bias, and reducing the costs for diagnosing human illnesses such as cancer and Alzheimer's disease. In this paper, we present a novel method for unsupervised segmentation of cell nuclei in stained histology tissue. Following an initial preprocessing step involving color deconvolution and image reconstruction, the segmentation step consists of multilevel thresholding and a series of morphological operations. The only parameter required for the method is the minimum region size, which is set according to the resolution of the image. Hence, the proposed method requires no training sets or parameter learning. Because the algorithm requires no assumptions or a priori information with regard to cell morphology, the automatic approach is generalizable across a wide range of tissues. Evaluation across a dataset consisting of diverse tissues, including breast, liver, gastric mucosa and bone marrow, shows superior performance over four other recent methods on the same dataset in terms of F-measure with precision and recall of 0.929 and 0.886, respectively.

  18. Refinement of Hyperspectral Image Classification with Segment-Tree Filtering

    Lu Li


    Full Text Available This paper proposes a novel method of segment-tree filtering to improve the classification accuracy of hyperspectral image (HSI. Segment-tree filtering is a versatile method that incorporates spatial information and has been widely applied in image preprocessing. However, to use this powerful framework in hyperspectral image classification, we must reduce the original feature dimensionality to avoid the Hughes problem; otherwise, the computational costs are high and the classification accuracy by original bands in the HSI is unsatisfactory. Therefore, feature extraction is adopted to produce new salient features. In this paper, the Semi-supervised Local Fisher (SELF method of discriminant analysis is used to reduce HSI dimensionality. Then, a tree-structure filter that adaptively incorporates contextual information is constructed. Additionally, an initial classification map is generated using multi-class support vector machines (SVMs, and segment-tree filtering is conducted using this map. Finally, a simple Winner-Take-All (WTA rule is applied to determine the class of each pixel in an HSI based on the maximum probability. The experimental results demonstrate that the proposed method can improve HSI classification accuracy significantly. Furthermore, a comparison between the proposed method and the current state-of-the-art methods, such as Extended Morphological Profiles (EMPs, Guided Filtering (GF, and Markov Random Fields (MRFs, suggests that our method is both competitive and robust.

  19. Combining Constraint Types From Public Data in Aerial Image Segmentation

    Jacobsen, Thomas Stig; Jensen, Jacob Jon; Jensen, Daniel Rune


    detect the number of clusters using the elongated K-means algorithm instead of using the standard spectral clustering approach of a predefined number of clusters. The results are refined by filtering out noise with a binary morphological operator. Point data is used for semi-supervised labelling......We introduce a method for image segmentation that constraints the clustering with map and point data. The method is showcased by applying the spectral clustering algorithm on aerial images for building detection with constraints built from a height map and address point data. We automatically...

  20. A Bayesian Approach for Segmentation in Stereo Image Sequences

    Tzovaras Dimitrios


    Full Text Available Stereoscopic image sequence processing has been the focus of considerable attention in recent literature for videoconference applications. A novel Bayesian scheme is proposed in this paper, for the segmentation of a noisy stereoscopic image sequence. More specifically, occlusions and visible foreground and background regions are detected between the left and the right frame while the uncovered-background areas are identified between two successive frames of the sequence. Combined hypotheses are used for the formulation of the Bayes decision rule which employs a single intensity-difference measurement at each pixel. Experimental results illustrating the performance of the proposed technique are presented and evaluated in videoconference applications.

  1. New variable selection method using interval segmentation purity with application to blockwise kernel transform support vector machine classification of high-dimensional microarray data.

    Tang, Li-Juan; Du, Wen; Fu, Hai-Yan; Jiang, Jian-Hui; Wu, Hai-Long; Shen, Guo-Li; Yu, Ru-Qin


    One problem with discriminant analysis of microarray data is representation of each sample by a large number of genes that are possibly irrelevant, insignificant, or redundant. Methods of variable selection are, therefore, of great significance in microarray data analysis. A new method for key gene selection has been proposed on the basis of interval segmentation purity that is defined as the purity of samples belonging to a certain class in intervals segmented by a mode search algorithm. This method identifies key variables most discriminative for each class, which offers possibility of unraveling the biological implication of selected genes. A salient advantage of the new strategy over existing methods is the capability of selecting genes that, though possibly exhibit a multimodal distribution, are the most discriminative for the classes of interest, considering that the expression levels of some genes may reflect systematic difference in within-class samples derived from different pathogenic mechanisms. On the basis of the key genes selected for individual classes, a support vector machine with block-wise kernel transform is developed for the classification of different classes. The combination of the proposed gene mining approach with support vector machine is demonstrated in cancer classification using two public data sets. The results reveal that significant genes have been identified for each class, and the classification model shows satisfactory performance in training and prediction for both data sets.

  2. Fully automatic segmentation of complex organ systems: example of trachea, esophagus and heart segmentation in CT images

    Meyer, Carsten; Peters, Jochen; Weese, Jürgen


    Automatic segmentation is a prerequisite to efficiently analyze the large amount of image data produced by modern imaging modalities. Many algorithms exist to segment individual organs or organ systems. However, new clinical applications and the progress in imaging technology will require the segmentation of more and more complex organ systems composed of a number of substructures, e.g., the heart, the trachea, and the esophagus. The goal of this work is to demonstrate that such complex organ systems can be successfully segmented by integrating the individual organs into a general model-based segmentation framework, without tailoring the core adaptation engine to the individual organs. As an example, we address the fully automatic segmentation of the trachea (around its main bifurcation, including the proximal part of the two main bronchi) and the esophagus in addition to the heart with all chambers and attached major vessels. To this end, we integrate the trachea and the esophagus into a model-based cardiac segmentation framework. Specifically, in a first parametric adaptation step of the segmentation workflow, the trachea and the esophagus share global model transformations with adjacent heart structures. This allows to obtain a robust, approximate segmentation for the trachea even if it is only partly inside the field-of-view, and for the esophagus in spite of limited contrast. The segmentation is then refined in a subsequent deformable adaptation step. We obtained a mean segmentation error of about 0.6mm for the trachea and 2.3mm for the esophagus on a database of 23 volumetric cardiovascular CT images. Furthermore, we show by quantitative evaluation that our integrated framework outperforms individual esophagus segmentation, and individual trachea segmentation if the trachea is only partly inside the field-of-view.

  3. Medical Image Segmentation through Bat-Active Contour Algorithm

    Rabiu O. Isah


    Full Text Available In this research work, an improved active contour method called Bat-Active Contour Method (BAACM using bat algorithm has been developed. The bat algorithm is incorporated in order to escape local minima entrapped into by the classical active contour method, stabilize contour (snake movement and accurately, reach boundary concavity. Then, the developed Bat-Active Contour Method was applied to a dataset of medical images of the human heart, bone of knee and vertebra which were obtained from Auckland MRI Research Group (Cardiac Atlas Website, University of Auckland. Set of similarity metrics, including Jaccard index and Dice similarity measures were adopted to evaluate the performance of the developed algorithm. Jaccard index values of 0.9310, 0.9234 and 0.8947 and Dice similarity values of 0.8341, 0.8616 and 0.9138 were obtained from the human heart, vertebra and bone of knee images respectively. The results obtained show high similarity measures between BA-ACM algorithm and expert segmented images. Moreso, traditional ACM produced Jaccard index values 0.5873, 0.5601, 0.6009 and Dice similarity values of 0.5974, 0.6079, 0.6102 in the human heart, vertebra and bone of knee images respectively. The results obtained for traditional ACM show low similarity measures between it and expertly segmented images. It is evident from the results obtained that the developed algorithm performed better compared to the traditional ACM

  4. Jacquard image segmentation using Mumford-Shah model

    FENG Zhi-lin; YIN Jian-wei; CHEN Gang; DONG Jin-xiang


    Jacquard image segmentation is one of the primary steps in image analysis for jacquard pattern identification. The main aim is to recognize homogeneous regions within a jacquard image as distinct, which belongs to different patterns. Active contour models have become popular for finding the contours of a pattem with a complex shape. However, the performance of active contour models is often inadequate under noisy environment. In this paper, a robust algorithm based on the Mumford-Shah model is proposed for the segmentation of noisy jacquard images. First, the Mumford-Shah model is discretized on piecewise linear finite element spaces to yield greater stability. Then, an iterative relaxation algorithm for numerically solving the discrete version of the model is presented. In this algorithm, an adaptiye triangular mesh is refined to generate Delaunay type triangular mesh defined on structured triangulations, and then a quasi-Newton numerical method is applied to find the absolute minimum of the discrete model. Experimental results on noisy jacquard images demonstrated the efficacy of the proposed algorithm.

  5. Method, Software and Aparatus for Segmenting a Series of 2D or 3D Images

    Noble, Nicholas M.I.; Spreeuwers, Lieuwe Jan; Breeuwer, Marcel


    he invention relates to an apparatus having means for segmenting a series of 2D or 3D images obtained by monitoring a patient's organ or other body part, wherein a first segmentation is carried out on a first image of the series of images and wherein the first segmentation is used for the subsequent

  6. Method, Software and Aparatus for Segmenting a Series of 2D or 3D Images

    Noble, Nicholas Michael Ian; Spreeuwers, Lieuwe Jan; Breeuwer, Marcel


    he invention relates to an apparatus having means for segmenting a series of 2D or 3D images obtained by monitoring a patient's organ or other body part, wherein a first segmentation is carried out on a first image of the series of images and wherein the first segmentation is used for the subsequent

  7. Fast Graph Partitioning Active Contours for Image Segmentation Using Histograms

    Nath SumitK


    Full Text Available Abstract We present a method to improve the accuracy and speed, as well as significantly reduce the memory requirements, for the recently proposed Graph Partitioning Active Contours (GPACs algorithm for image segmentation in the work of Sumengen and Manjunath (2006. Instead of computing an approximate but still expensive dissimilarity matrix of quadratic size, , for a 2D image of size and regular image tiles of size , we use fixed length histograms and an intensity-based symmetric-centrosymmetric extensor matrix to jointly compute terms associated with the complete dissimilarity matrix. This computationally efficient reformulation of GPAC using a very small memory footprint offers two distinct advantages over the original implementation. It speeds up convergence of the evolving active contour and seamlessly extends performance of GPAC to multidimensional images.

  8. Magnetic Resonance Image Segmentation and its Volumetric Measurement

    Rahul R. Ambalkar


    Full Text Available Image processing techniques make it possible to extract meaningful information from medical images. Magnetic resonance (MR imaging has been widely applied in biological research and diagnostics because of its excellent soft tissue contrast, non-invasive character, high spatial resolution and easy slice selection at any orientation. The MRI-based brain volumetric is concerned with the analysis of volumes and shapes of the structural components of the human brain. It also provides a criterion, by which we recognize the presence of degenerative diseases and characterize their rates of progression to make the diagnosis and treatments as a easy task. In this paper we have proposed an automated method for volumetric measurement of Magnetic Resonance Imaging and used Self Organized Map (SOM clustering method for their segmentations. We have used the MRI data set of 61 slices of 256×256 pixels in DICOM standard format

  9. Filler segmentation of SEM paper images based on mathematical morphology.

    Ait Kbir, M; Benslimane, Rachid; Princi, Elisabetta; Vicini, Silvia; Pedemonte, Enrico


    Recent developments in microscopy and image processing have made digital measurements on high-resolution images of fibrous materials possible. This helps to gain a better understanding of the structure and other properties of the material at micro level. In this paper SEM image segmentation based on mathematical morphology is proposed. In fact, paper models images (Whatman, Murillo, Watercolor, Newsprint paper) selected in the context of the Euro Mediterranean PaperTech Project have different distributions of fibers and fillers, caused by the presence of SiAl and CaCO3 particles. It is a microscopy challenge to make filler particles in the sheet distinguishable from the other components of the paper surface. This objectif is reached here by using switable strutural elements and mathematical morphology operators.

  10. Medical image segmentation based on SLIC superpixels model

    Chen, Xiang-ting; Zhang, Fan; Zhang, Ruo-ya


    Medical imaging has been widely used in clinical practice. It is an important basis for medical experts to diagnose the disease. However, medical images have many unstable factors such as complex imaging mechanism, the target displacement will cause constructed defect and the partial volume effect will lead to error and equipment wear, which increases the complexity of subsequent image processing greatly. The segmentation algorithm which based on SLIC (Simple Linear Iterative Clustering, SLIC) superpixels is used to eliminate the influence of constructed defect and noise by means of the feature similarity in the preprocessing stage. At the same time, excellent clustering effect can reduce the complexity of the algorithm extremely, which provides an effective basis for the rapid diagnosis of experts.

  11. A new iterative triclass thresholding technique in image segmentation.

    Cai, Hongmin; Yang, Zhong; Cao, Xinhua; Xia, Weiming; Xu, Xiaoyin


    We present a new method in image segmentation that is based on Otsu's method but iteratively searches for subregions of the image for segmentation, instead of treating the full image as a whole region for processing. The iterative method starts with Otsu's threshold and computes the mean values of the two classes as separated by the threshold. Based on the Otsu's threshold and the two mean values, the method separates the image into three classes instead of two as the standard Otsu's method does. The first two classes are determined as the foreground and background and they will not be processed further. The third class is denoted as a to-be-determined (TBD) region that is processed at next iteration. At the succeeding iteration, Otsu's method is applied on the TBD region to calculate a new threshold and two class means and the TBD region is again separated into three classes, namely, foreground, background, and a new TBD region, which by definition is smaller than the previous TBD regions. Then, the new TBD region is processed in the similar manner. The process stops when the Otsu's thresholds calculated between two iterations is less than a preset threshold. Then, all the intermediate foreground and background regions are, respectively, combined to create the final segmentation result. Tests on synthetic and real images showed that the new iterative method can achieve better performance than the standard Otsu's method in many challenging cases, such as identifying weak objects and revealing fine structures of complex objects while the added computational cost is minimal.

  12. Automatic segmentation of brain images: selection of region extraction methods

    Gong, Leiguang; Kulikowski, Casimir A.; Mezrich, Reuben S.


    In automatically analyzing brain structures from a MR image, the choice of low level region extraction methods depends on the characteristics of both the target object and the surrounding anatomical structures in the image. The authors have experimented with local thresholding, global thresholding, and other techniques, using various types of MR images for extracting the major brian landmarks and different types of lesions. This paper describes specifically a local- binary thresholding method and a new global-multiple thresholding technique developed for MR image segmentation and analysis. The initial testing results on their segmentation performance are presented, followed by a comparative analysis of the two methods and their ability to extract different types of normal and abnormal brain structures -- the brain matter itself, tumors, regions of edema surrounding lesions, multiple sclerosis lesions, and the ventricles of the brain. The analysis and experimental results show that the global multiple thresholding techniques are more than adequate for extracting regions that correspond to the major brian structures, while local binary thresholding is helpful for more accurate delineation of small lesions such as those produced by MS, and for the precise refinement of lesion boundaries. The detection of other landmarks, such as the interhemispheric fissure, may require other techniques, such as line-fitting. These experiments have led to the formulation of a set of generic computer-based rules for selecting the appropriate segmentation packages for particular types of problems, based on which further development of an innovative knowledge- based, goal directed biomedical image analysis framework is being made. The system will carry out the selection automatically for a given specific analysis task.

  13. Hybrid of Fuzzy Logic and Random Walker Method for Medical Image Segmentation

    Jasdeep Kaur; Manish Mahajan


    ...’ treatment are based on information extracted from radiological images. Several algorithms and techniques have developed for image segmentation and have their own advantages and disadvantages...

  14. Segmentation of the thoracic aorta in noncontrast cardiac CT images.

    Avila-Montes, Olga C; Kurkure, Uday; Nakazato, Ryo; Berman, Daniel S; Dey, Damini; Kakadiaris, Ioannis A


    Studies have shown that aortic calcification is associated with cardiovascular disease. In this study, a method for localization, centerline extraction, and segmentation of the thoracic aorta in noncontrast cardiac-computed tomography (CT) images, toward the detection of aortic calcification, is presented. The localization of the right coronary artery ostium slice is formulated as a regression problem whose input variables are obtained from simple intensity features computed from a pyramid representation of the slice. The localization, centerline extraction, and segmentation of the aorta are formulated as optimal path detection problems. Dynamic programming is applied in the Hough space for localizing key center points in the aorta which guide the centerline tracing using a fast marching-based minimal path extraction framework. The input volume is then resampled into a stack of 2-D cross-sectional planes orthogonal to the obtained centerline. Dynamic programming is again applied for the segmentation of the aorta in each slice of the resampled volume. The obtained segmentation is finally mapped back to its original volume space. The performance of the proposed method was assessed on cardiac noncontrast CT scans and promising results were obtained.

  15. Adaptive distance metric learning for diffusion tensor image segmentation.

    Kong, Youyong; Wang, Defeng; Shi, Lin; Hui, Steve C N; Chu, Winnie C W


    High quality segmentation of diffusion tensor images (DTI) is of key interest in biomedical research and clinical application. In previous studies, most efforts have been made to construct predefined metrics for different DTI segmentation tasks. These methods require adequate prior knowledge and tuning parameters. To overcome these disadvantages, we proposed to automatically learn an adaptive distance metric by a graph based semi-supervised learning model for DTI segmentation. An original discriminative distance vector was first formulated by combining both geometry and orientation distances derived from diffusion tensors. The kernel metric over the original distance and labels of all voxels were then simultaneously optimized in a graph based semi-supervised learning approach. Finally, the optimization task was efficiently solved with an iterative gradient descent method to achieve the optimal solution. With our approach, an adaptive distance metric could be available for each specific segmentation task. Experiments on synthetic and real brain DTI datasets were performed to demonstrate the effectiveness and robustness of the proposed distance metric learning approach. The performance of our approach was compared with three classical metrics in the graph based semi-supervised learning framework.

  16. Adaptive distance metric learning for diffusion tensor image segmentation.

    Youyong Kong

    Full Text Available High quality segmentation of diffusion tensor images (DTI is of key interest in biomedical research and clinical application. In previous studies, most efforts have been made to construct predefined metrics for different DTI segmentation tasks. These methods require adequate prior knowledge and tuning parameters. To overcome these disadvantages, we proposed to automatically learn an adaptive distance metric by a graph based semi-supervised learning model for DTI segmentation. An original discriminative distance vector was first formulated by combining both geometry and orientation distances derived from diffusion tensors. The kernel metric over the original distance and labels of all voxels were then simultaneously optimized in a graph based semi-supervised learning approach. Finally, the optimization task was efficiently solved with an iterative gradient descent method to achieve the optimal solution. With our approach, an adaptive distance metric could be available for each specific segmentation task. Experiments on synthetic and real brain DTI datasets were performed to demonstrate the effectiveness and robustness of the proposed distance metric learning approach. The performance of our approach was compared with three classical metrics in the graph based semi-supervised learning framework.

  17. Alternative Fuzzy Cluster Segmentation of Remote Sensing Images Based on Adaptive Genetic Algorithm

    WANG Jing; TANG Jilong; LIU Jibin; REN Chunying; LIU Xiangnan; FENG Jiang


    Remote sensing image segmentation is the basis of image understanding and analysis. However, the precision and the speed of segmentation can not meet the need of image analysis, due to strong uncertainty and rich texture details of remote sensing images. We proposed a new segmentation method based on Adaptive Genetic Algorithm (AGA) and Alternative Fuzzy C-Means (AFCM). Segmentation thresholds were identified by AGA. Then the image was segmented by AFCM. The results indicate that the precision and the speed of segmentation have been greatly increased, and the accuracy of threshold selection is much higher compared with traditional Otsu and Fuzzy C-Means (FCM) segmentation methods. The segmentation results also show that multi-thresholds segmentation has been achieved by combining AGA with AFCM.

  18. A quantum mechanics-based framework for image processing and its application to image segmentation

    Youssry, Akram; El-Rafei, Ahmed; Elramly, Salwa


    Quantum mechanics provides the physical laws governing microscopic systems. A novel and generic framework based on quantum mechanics for image processing is proposed in this paper. The basic idea is to map each image element to a quantum system. This enables the utilization of the quantum mechanics powerful theory in solving image processing problems. The initial states of the image elements are evolved to the final states, controlled by an external force derived from the image features. The final states can be designed to correspond to the class of the element providing solutions to image segmentation, object recognition, and image classification problems. In this work, the formulation of the framework for a single-object segmentation problem is developed. The proposed algorithm based on this framework consists of four major steps. The first step is designing and estimating the operator that controls the evolution process from image features. The states associated with the pixels of the image are initialized in the second step. In the third step, the system is evolved. Finally, a measurement is performed to determine the output. The presented algorithm is tested on noiseless and noisy synthetic images as well as natural images. The average of the obtained results is 98.5 % for sensitivity and 99.7 % for specificity. A comparison with other segmentation algorithms is performed showing the superior performance of the proposed method. The application of the introduced quantum-based framework to image segmentation demonstrates high efficiency in handling different types of images. Moreover, it can be extended to multi-object segmentation and utilized in other applications in the fields of signal and image processing.

  19. Automatic Scheme for Fused Medical Image Segmentation with Nonsubsampled Contourlet Transform

    Ch.Hima Bindu; Dr. K. Satya Prasad


    Medical image segmentation has become an essential technique in clinical and research- oriented applications. Because manual segmentation methods are tedious, and semi-automatic segmentation lacks the flexibility, fully-automatic methods have become the preferred type of medical image segmentation. This work proposes a robust fully automatic segmentation scheme based on the modified contouring technique. The entire scheme consists of three stages. In the first stage, the Nonsubsampled Contour...

  20. A comparative performance study characterizing breast tissue microarrays using standard RGB and multispectral imaging

    Qi, Xin; Cukierski, William; Foran, David J.


    The lack of clear consensus over the utility of multispectral imaging (MSI) for bright-field imaging prompted our team to investigate the benefit of using MSI on breast tissue microarrays (TMA). We have conducted performance studies to compare MSI with standard bright-field imaging in hematoxylin stained breast tissue. The methodology has three components. The first extracts a region of interest using adaptive thresholding and morphological processing. The second performs texture feature extraction from a local binary pattern within each spectral channel and compared to features of co-occurrence matrix and texture feature coding in third component. The third component performs feature selection and classification. For each spectrum, exhaustive feature selection was used to search for the combination of features that yields the best classification accuracy. AdaBoost with a linear perceptron least-square classifier was applied. The spectra carrying the greatest discriminatory power were automatically chosen and a majority vote was used to make the final classification. 92 breast TMA discs were included in the study. Sensitivity of 0.96 and specificity of 0.89 were achieved on the multispectral data, compared with sensitivity of 0.83 and specificity of 0.85 on RGB data. MSI consistently achieved better classification results than those obtained using standard RGB images. While the benefits of MSI for unmixing multi-stained specimens are well documented, this study demonstrated statistically significant improvements in the automated analysis of single stained bright-field images.

  1. Multicolor surface plasmon resonance imaging of ink jet-printed protein microarrays.

    Singh, Bipin K; Hillier, Andrew C


    We report a technique that utilizes surface plasmon resonance dispersion as a mechanism to provide multicolor contrast for imaging thin molecular films. Illumination of gold surfaces with p-polarized white light in the Kretschmann configuration produces distinct reflected colors due to excitation of surface plasmons and the resulting absorption of specific wavelengths from the source light. In addition, these colors transform in response to the formation of thin molecular films. This process represents a simple detection method for distinguishing between films of varying thickness in sensor applications. As an example, we interrogated a protein microarray formed by a commercial drop-on-demand chemical ink jet printer. Submonolayer films of a test protein (bovine serum albumin) were readily detected by this method. Analysis of the dispersion relations and absorbance sensitivities illustrate the performance and characteristics of this system. Higher detection sensitivity was achieved at angles where red wavelengths coupled to surface plasmons. However, improved contrast and spatial resolution occurred when the angle of incidence was such that shorter wavelengths coupled to the surface plasmons. Simplified optics combined with the robust microarray printing platform are used to demonstrate the applicability of this technique as a rapid and versatile, high-throughput tool for label-free detection of adsorbed films and macromolecules.

  2. Replica inference approach to unsupervised multiscale image segmentation.

    Hu, Dandan; Ronhovde, Peter; Nussinov, Zohar


    We apply a replica-inference-based Potts model method to unsupervised image segmentation on multiple scales. This approach was inspired by the statistical mechanics problem of "community detection" and its phase diagram. Specifically, the problem is cast as identifying tightly bound clusters ("communities" or "solutes") against a background or "solvent." Within our multiresolution approach, we compute information-theory-based correlations among multiple solutions ("replicas") of the same graph over a range of resolutions. Significant multiresolution structures are identified by replica correlations manifest by information theory overlaps. We further employ such information theory measures (such as normalized mutual information and variation of information), thermodynamic quantities such as the system entropy and energy, and dynamic measures monitoring the convergence time to viable solutions as metrics for transitions between various solvable and unsolvable phases. Within the solvable phase, transitions between contending solutions (such as those corresponding to segmentations on different scales) may also appear. With the aid of these correlations as well as thermodynamic measures, the phase diagram of the corresponding Potts model is analyzed at both zero and finite temperatures. Optimal parameters corresponding to a sensible unsupervised segmentations appear within the "easy phase" of the Potts model. Our algorithm is fast and shown to be at least as accurate as the best algorithms to date and to be especially suited to the detection of camouflaged images.

  3. Fuzzy Markov random fields versus chains for multispectral image segmentation.

    Salzenstein, Fabien; Collet, Christophe


    This paper deals with a comparison of recent statistical models based on fuzzy Markov random fields and chains for multispectral image segmentation. The fuzzy scheme takes into account discrete and continuous classes which model the imprecision of the hidden data. In this framework, we assume the dependence between bands and we express the general model for the covariance matrix. A fuzzy Markov chain model is developed in an unsupervised way. This method is compared with the fuzzy Markovian field model previously proposed by one of the authors. The segmentation task is processed with Bayesian tools, such as the well-known MPM (Mode of Posterior Marginals) criterion. Our goal is to compare the robustness and rapidity for both methods (fuzzy Markov fields versus fuzzy Markov chains). Indeed, such fuzzy-based procedures seem to be a good answer, e.g., for astronomical observations when the patterns present diffuse structures. Moreover, these approaches allow us to process missing data in one or several spectral bands which correspond to specific situations in astronomy. To validate both models, we perform and compare the segmentation on synthetic images and raw multispectral astronomical data.

  4. Segmentation of the ovine lung in 3D CT Images

    Shi, Lijun; Hoffman, Eric A.; Reinhardt, Joseph M.


    Pulmonary CT images can provide detailed information about the regional structure and function of the respiratory system. Prior to any of these analyses, however, the lungs must be identified in the CT data sets. A popular animal model for understanding lung physiology and pathophysiology is the sheep. In this paper we describe a lung segmentation algorithm for CT images of sheep. The algorithm has two main steps. The first step is lung extraction, which identifies the lung region using a technique based on optimal thresholding and connected components analysis. The second step is lung separation, which separates the left lung from the right lung by identifying the central fissure using an anatomy-based method incorporating dynamic programming and a line filter algorithm. The lung segmentation algorithm has been validated by comparing our automatic method to manual analysis for five pulmonary CT datasets. The RMS error between the computer-defined and manually-traced boundary is 0.96 mm. The segmentation requires approximately 10 minutes for a 512x512x400 dataset on a PC workstation (2.40 GHZ CPU, 2.0 GB RAM), while it takes human observer approximately two hours to accomplish the same task.

  5. Segmentation of interstitial lung disease patterns in HRCT images

    Dash, Jatindra K.; Madhavi, Vaddepalli; Mukhopadhyay, Sudipta; Khandelwal, Niranjan; Kumar, Prafulla


    Automated segmentation of pathological bearing region is the first step towards the development of lung CAD. Most of the work reported in the literature related to automated analysis of lung tissue aims towards classification of fixed sized block into one of the classes. This block level classification of lung tissues in the image never results in accurate or smooth boundaries between different regions. In this work, effort is taken to investigate the performance of three automated image segmentation algorithms those results in smooth boundaries among lung tissue patterns commonly encountered in HRCT images of the thorax. A public database that consists of HRCT images taken from patients affected with Interstitial Lung Diseases (ILDs) is used for the evaluation. The algorithms considered are Markov Random Field (MRF), Gaussian Mixture Model (GMM) and Mean Shift (MS). 2-fold cross validation approach is followed for the selection of the best parameter value for individual algorithm as well as to evaluate the performance of all the algorithms. Mean shift algorithm is observed as the best performer in terms of Jaccard Index, Modified Hausdorff Distance, accuracy, Dice Similarity Coefficient and execution speed.

  6. Practical contour segmentation algorithm for small animal digital radiography image

    Zheng, Fang; Hui, Gong


    In this paper a practical, automated contour segmentation technique for digital radiography image is described. Digital radiography is an imaging mode based on the penetrability of x-ray. Unlike reflection imaging mode such as visible light camera, the pixel brightness represents the summation of the attenuations on the photon thoroughfare. It is not chromophotograph but gray scale picture. Contour extraction is of great importance in medical applications, especially in non-destructive inspection. Manual segmentation techniques include pixel selection, geometrical boundary selection and tracing. But it relies heavily on the experience of the operators, and is time-consuming. Some researchers try to find contours from the intensity jumping characters around them. However these characters also exist in the juncture of bone and soft tissue. The practical way is back to the primordial threshold algorithm. This research emphasizes on how to find the optimal threshold. A high resolution digital radiography system is used to provide the oriental gray scale image. A mouse is applied as the sample of this paper to show the feasibility of the algorithm.

  7. Proximity graphs based multi-scale image segmentation

    Skurikhin, Alexei N [Los Alamos National Laboratory


    We present a novel multi-scale image segmentation approach based on irregular triangular and polygonal tessellations produced by proximity graphs. Our approach consists of two separate stages: polygonal seeds generation followed by an iterative bottom-up polygon agglomeration into larger chunks. We employ constrained Delaunay triangulation combined with the principles known from the visual perception to extract an initial ,irregular polygonal tessellation of the image. These initial polygons are built upon a triangular mesh composed of irregular sized triangles and their shapes are ad'apted to the image content. We then represent the image as a graph with vertices corresponding to the polygons and edges reflecting polygon relations. The segmentation problem is then formulated as Minimum Spanning Tree extraction. We build a successive fine-to-coarse hierarchy of irregular polygonal grids by an iterative graph contraction constructing Minimum Spanning Tree. The contraction uses local information and merges the polygons bottom-up based on local region-and edge-based characteristics.

  8. Semantic Segmentation of Aerial Images with AN Ensemble of Cnns

    Marmanis, D.; Wegner, J. D.; Galliani, S.; Schindler, K.; Datcu, M.; Stilla, U.


    This paper describes a deep learning approach to semantic segmentation of very high resolution (aerial) images. Deep neural architectures hold the promise of end-to-end learning from raw images, making heuristic feature design obsolete. Over the last decade this idea has seen a revival, and in recent years deep convolutional neural networks (CNNs) have emerged as the method of choice for a range of image interpretation tasks like visual recognition and object detection. Still, standard CNNs do not lend themselves to per-pixel semantic segmentation, mainly because one of their fundamental principles is to gradually aggregate information over larger and larger image regions, making it hard to disentangle contributions from different pixels. Very recently two extensions of the CNN framework have made it possible to trace the semantic information back to a precise pixel position: deconvolutional network layers undo the spatial downsampling, and Fully Convolution Networks (FCNs) modify the fully connected classification layers of the network in such a way that the location of individual activations remains explicit. We design a FCN which takes as input intensity and range data and, with the help of aggressive deconvolution and recycling of early network layers, converts them into a pixelwise classification at full resolution. We discuss design choices and intricacies of such a network, and demonstrate that an ensemble of several networks achieves excellent results on challenging data such as the ISPRS semantic labeling benchmark, using only the raw data as input.

  9. An Unsupervised Dynamic Image Segmentation using Fuzzy Hopfield Neural Network based Genetic Algorithm

    Halder, Amiya


    This paper proposes a Genetic Algorithm based segmentation method that can automatically segment gray-scale images. The proposed method mainly consists of spatial unsupervised grayscale image segmentation that divides an image into regions. The aim of this algorithm is to produce precise segmentation of images using intensity information along with neighborhood relationships. In this paper, Fuzzy Hopfield Neural Network (FHNN) clustering helps in generating the population of Genetic algorithm which there by automatically segments the image. This technique is a powerful method for image segmentation and works for both single and multiple-feature data with spatial information. Validity index has been utilized for introducing a robust technique for finding the optimum number of components in an image. Experimental results shown that the algorithm generates good quality segmented image.

  10. Efficient color representation for image segmentation under nonwhite illumination

    Park, Jae Byung


    Color image segmentation algorithms often consider object color to be a constant property of an object. If the light source dominantly exhibits a particular color, however, it becomes necessary to consider the color variation induced by the colored illuminant. This paper presents a new approach to segmenting color images that are photographed under non-white illumination conditions. It also addresses how to estimate the color of illuminant in terms of the standard RGB color values rather than the spectrum of the illuminant. With respect to the illumination axis that goes through the origin and the centroid of illuminant color clusters (prior given by the estimation process), the RGB color space is transformed into our new color coordinate system. Our new color scheme shares the intuitiveness of the HSI (HSL or HSV) space that comes from the conical (double-conical or cylindrical) structure of hue and saturation aligned with the intensity variation at its center. It has been developed by locating the ordinary RGB cube in such a way that the illumination axis aligns with the vertical axis (Z-axis) of a larger Cartesian (XYZ) space. The work in this paper uses the dichromatic reflection model [1] to interpret the physics about light and optical effects in color images. The linearity proposed in the dichromatic reflection model is essential and is well preserved in the RGB color space. By proposing a straightforward color model transduction, we suggest dimensionality reduction and provide an efficient way to analyze color images of dielectric objects under non-white illumination conditions. The feasibility of the proposed color representation has been demonstrated by our experiment that is twofold: 1) Segmentation result from a multi-modal histogram-based thresholding technique and 2) Color constancy result from discounting illumination effect further by color balancing.

  11. Asymmetric similarity-weighted ensembles for image segmentation

    Cheplygina, V.; Van Opbroek, A.; Ikram, M. A.


    the images, thus representative data might not be available. Transfer learning techniques can be used to account for these differences, thus taking advantage of all the available data acquired with different protocols. We investigate the use of classifier ensembles, where each classifier is weighted...... according to the similarity between the data it is trained on, and the data it needs to segment. We examine 3 asymmetric similarity measures that can be used in scenarios where no labeled data from a newly introduced scanner or scanning protocol is available. We show that the asymmetry is informative...... and the direction of measurement needs to be chosen carefully. We also show that a point set similarity measure is robust across different studies, and outperforms state-of-the-art results on a multi-center brain tissue segmentation task....

  12. Automatic airline baggage counting using 3D image segmentation

    Yin, Deyu; Gao, Qingji; Luo, Qijun


    The baggage number needs to be checked automatically during baggage self-check-in. A fast airline baggage counting method is proposed in this paper using image segmentation based on height map which is projected by scanned baggage 3D point cloud. There is height drop in actual edge of baggage so that it can be detected by the edge detection operator. And then closed edge chains are formed from edge lines that is linked by morphological processing. Finally, the number of connected regions segmented by closed chains is taken as the baggage number. Multi-bag experiment that is performed on the condition of different placement modes proves the validity of the method.

  13. Simultaneous light-directed synthesis of mirror-image microarrays in a photochemical reaction cell with flare suppression.

    Sack, Matej; Kretschy, Nicole; Rohm, Barbara; Somoza, Veronika; Somoza, Mark M


    The use of photolabile protecting groups is a versatile and well-established means of synthesizing high complexity microarrays of biopolymers, such as nucleic acids and peptides, for high-throughput analysis. The synthesis takes place in a photochemical reaction cell which positions the microarray substrate at the focus of the optical system delivering the light and which can be connected to a fluidics system which delivers appropriate reagents to the surface in synchrony with the light exposure. Here we describe a novel photochemical reaction cell which allows for the simultaneous synthesis of microarrays on two substrates. The reaction cell positions both substrates within the limited depth-of-focus of the optical system while maintaining the necessary reagent flow conditions. The resulting microarrays are mirror images of each other but otherwise essentially identical. The new reaction cell doubles the throughput of microarray synthesis without increasing the consumption of reagents. In addition, a secondary flow chamber behind the reaction cell can be filled with an absorbent and index-matching fluid to eliminate reflections from light exiting the reaction cell assembly, greatly reducing unintended light exposure that reduces the sequence fidelity of the microarray probes.

  14. An Enhanced Level Set Segmentation for Multichannel Images Using Fuzzy Clustering and Lattice Boltzmann Method

    Savita Agrawal


    Full Text Available In the last decades, image segmentation has proved its applicability in various areas like satellite image processing, medical image processing and many more. In the present scenario the researchers tries to develop hybrid image segmentation techniques to generates efficient segmentation. Due to the development of the parallel programming, the lattice Boltzmann method (LBM has attracted much attention as a fast alternative approach for solving partial differential equations. In this project work, first designed an energy functional based on the fuzzy c-means objective function which incorporates the bias field that accounts for the intensity in homogeneity of the real-world image. Using the gradient descent method, corresponding level set equations are obtained from which we deduce a fuzzy external force for the LBM solver based on the model by Zhao. The method is speedy, robust for denoise, and does not dependent on the position of the initial contour, effective in the presence of intensity in homogeneity, highly parallelizable and can detect objects with or without edges. For the implementation of segmentation techniques defined for gray images, most of the time researchers determines single channel segments of the images and superimposes the single channel segment information on color images. This idea leads to provide color image segmentation using single channel segments of multi channel images. Though this method is widely adopted but doesn’t provide complete true segmentation of multichannel ie color images because a color image contains three different channels for Red, green and blue components. Hence segmenting a color image, by having only single channel segments information, will definitely loose important segment regions of color images. To overcome this problem this paper work starts with the development of Enhanced Level Set Segmentation for single channel Images Using Fuzzy Clustering and Lattice Boltzmann Method. For the

  15. An Enhanced Level Set Segmentation for Multichannel Images Using Fuzzy Clustering and Lattice Boltzmann Method

    Savita Agrawal


    Full Text Available In the last decades, image segmentation has proved its applicability in various areas like satellite image processing, medical image processing and many more. In the present scenario the researchers tries to develop hybrid image segmentation techniques to generates efficient segmentation. Due to the development of the parallel programming, the lattice Boltzmann met hod (LBM has attracted much attention as a fast alternative approach for solving partial differential equations. In this project work, first designed an energy functional based on the fuzzy c-means objective function which incorporates the bias field that accounts for the intensity in homogeneity of the real-world image. Using the gradient descent method, corresponding level set equations are obtained from which we deduce a fuzzy external force for the LBM solver based on the model by Zhao. The method is speedy, robust for denoise, and does not dependent on the position of the initial contour, effective in the presence of intensity in homogeneity, highly parallelizable and can detect objects with or without edges. For the implementation of segmentation techniques defined for gr ay images, most of the time researchers determines single channel segments of the images and superimposes the single channel segment information on color images. This idea leads to provide color image segmentation using single channel segments of multi chann el images. Though this method is widely adopted but doesn’t provide complete true segmentation of multichannel ie color images because a color image contains three different channels for Red, green and blue components. Hence segmenting a color image, b y having only single channel segments information, will definitely loose important segment regions of color images. To overcome this problem this paper work starts with the development of Enhanced Level Set Segmentation for single channel Images Using Fuzzy Clustering and Lattice Boltzmann Method. For the

  16. Infrared image segmentation based on region of interest extraction with Gaussian mixture modeling

    Yeom, Seokwon


    Infrared (IR) imaging has the capability to detect thermal characteristics of objects under low-light conditions. This paper addresses IR image segmentation with Gaussian mixture modeling. An IR image is segmented with Expectation Maximization (EM) method assuming the image histogram follows the Gaussian mixture distribution. Multi-level segmentation is applied to extract the region of interest (ROI). Each level of the multi-level segmentation is composed of the k-means clustering, the EM algorithm, and a decision process. The foreground objects are individually segmented from the ROI windows. In the experiments, various methods are applied to the IR image capturing several humans at night.

  17. Color image segmentation using watershed and Nyström method based spectral clustering

    Bai, Xiaodong; Cao, Zhiguo; Yu, Zhenghong; Zhu, Hu


    Color image segmentation draws a lot of attention recently. In order to improve efficiency of spectral clustering in color image segmentation, a novel two-stage color image segmentation method is proposed. In the first stage, we use vector gradient approach to detect color image gradient information, and watershed transformation to get the pre-segmentation result. In the second stage, Nyström extension based spectral clustering is used to get the final result. To verify the proposed algorithm, it is applied to color images from the Berkeley Segmentation Dataset. Experiments show our method can bring promising results and reduce the runtime significantly.

  18. Adaptive Image Restoration and Segmentation Method Using Different Neighborhood Sizes

    Chengcheng Li


    Full Text Available The image restoration methods based on the Bayesian's framework and Markov random fields (MRF have been widely used in the image-processing field. The basic idea of all these methods is to use calculus of variation and mathematical statistics to average or estimate a pixel value by the values of its neighbors. After applying this averaging process to the whole image a number of times, the noisy pixels, which are abnormal values, are filtered out. Based on the Tea-trade model, which states that the closer the neighbor, more contribution it makes, almost all of these methods use only the nearest four neighbors for calculation. In our previous research [1, 2], we extended the research on CLRS (image restoration and segmentation by using competitive learning algorithm to enlarge the neighborhood size. The results showed that the longer neighborhood range could improve or worsen the restoration results. We also found that the autocorrelation coefficient was an important factor to determine the proper neighborhood size. We then further realized that the computational complexity increased dramatically along with the enlargement of the neighborhood size. This paper is to further the previous research and to discuss the tradeoff between the computational complexity and the restoration improvement by using longer neighborhood range. We used a couple of methods to construct the synthetic images with the exact correlation coefficients we want and to determine the corresponding neighborhood size. We constructed an image with a range of correlation coefficients by blending some synthetic images. Then an adaptive method to find the correlation coefficients of this image was constructed. We restored the image by applying different neighborhood CLRS algorithm to different parts of the image according to its correlation coefficient. Finally, we applied this adaptive method to some real-world images to get improved restoration results than by using single

  19. A Markov Random Field Model for Image Segmentation of Rice Planthopper in Rice Fields

    Hongwei Yue; Ken Cai; Hanhui Lin; Hong Man; Zhaofeng Zeng


    It is meaningful to develop the automation segmentation of rice planthopper pests based on imaging technology in precision agriculture. However, rice planthopper images affected by light and complicated backgrounds in open rice fields make the segmentation difficult. This study proposed a segmentation approach of rice planthopper images based on the Markov random field to conduct effective segmentation. First, fractional order differential was introduced into the extraction proces...

  20. Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool

    Taha, Abdel Aziz; Hanbury, Allan


    Background Medical Image segmentation is an important image processing step. Comparing images to evaluate the quality of segmentation is an essential part of measuring progress in this research area. Some of the challenges in evaluating medical segmentation are: metric selection, the use in the literature of multiple definitions for certain metrics, inefficiency of the metric calculation implementations leading to difficulties with large volumes, and lack of support for fuzzy segmentation by ...

  1. Hybrid of Fuzzy Logic and Random Walker Method for Medical Image Segmentation

    Jasdeep Kaur; Manish Mahajan


    The procedure of partitioning an image into various segments to reform an image into somewhat that is more significant and easier to analyze, defined as image segmentation. In real world applications, noisy images exits and there could be some measurement errors too. These factors affect the quality of segmentation, which is of major concern in medical fields where decisions about patients’ treatment are based on information extracted from radiological images. Several algorithms and technique...

  2. Quantitative Assessment of Image Segmentation Quality by Random Walk Relaxation Times

    Andres, Björn; Köthe, Ullrich; Bonea, Andreea; Nadler, Boaz; Hamprecht, Fred A.

    The purpose of image segmentation is to partition the pixel grid of an image into connected components termed segments such that (i) each segment is homogenous and (ii) for any pair of adjacent segments, their union is not homogenous. (If it were homogenous the segments should be merged). We propose a rigorous definition of segment homogeneity which is scale-free and adaptive to the geometry of segments. We motivate this definition using random walk theory and show how segment homogeneity facilitates the quantification of violations of the conditions (i) and (ii) which are referred to as under-segmentation and over-segmentation, respectively. We describe the theoretical foundations of our approach and present a proof of concept on a few natural images.

  3. Effect of image compression and scaling on automated scoring of immunohistochemical stainings and segmentation of tumor epithelium

    Konsti Juho


    Full Text Available Abstract Background Digital whole-slide scanning of tissue specimens produces large images demanding increasing storing capacity. To reduce the need of extensive data storage systems image files can be compressed and scaled down. The aim of this article is to study the effect of different levels of image compression and scaling on automated image analysis of immunohistochemical (IHC stainings and automated tumor segmentation. Methods Two tissue microarray (TMA slides containing 800 samples of breast cancer tissue immunostained against Ki-67 protein and two TMA slides containing 144 samples of colorectal cancer immunostained against EGFR were digitized with a whole-slide scanner. The TMA images were JPEG2000 wavelet compressed with four compression ratios: lossless, and 1:12, 1:25 and 1:50 lossy compression. Each of the compressed breast cancer images was furthermore scaled down either to 1:1, 1:2, 1:4, 1:8, 1:16, 1:32, 1:64 or 1:128. Breast cancer images were analyzed using an algorithm that quantitates the extent of staining in Ki-67 immunostained images, and EGFR immunostained colorectal cancer images were analyzed with an automated tumor segmentation algorithm. The automated tools were validated by comparing the results from losslessly compressed and non-scaled images with results from conventional visual assessments. Percentage agreement and kappa statistics were calculated between results from compressed and scaled images and results from lossless and non-scaled images. Results Both of the studied image analysis methods showed good agreement between visual and automated results. In the automated IHC quantification, an agreement of over 98% and a kappa value of over 0.96 was observed between losslessly compressed and non-scaled images and combined compression ratios up to 1:50 and scaling down to 1:8. In automated tumor segmentation, an agreement of over 97% and a kappa value of over 0.93 was observed between losslessly compressed images and

  4. Statistical Methods for Analyzing Tissue Microarray Images - Algorithmic Scoring and Co-training

    Yan, Donghui; Knudsen, Beatrice S; Linden, Michael; Randolph, Timothy W


    Recent advances in tissue microarray technology have allowed immunohistochemistry to become a powerful medium-to-high throughput analysis tool, particularly for the validation of diagnostic and prognostic biomarkers. However, as study size grows, the manual evaluation of these assays becomes a prohibitive limitation; it vastly reduces throughput and greatly increases variability and expense. We propose an algorithm - Tissue Array Co-Occurrence Matrix Analysis (TACOMA) - for quantifying cellular phenotypes based on textural regularity summarized by local inter-pixel relationships. The algorithm can be easily trained for any staining pattern, is absent of sensitive tuning parameters and has the ability to report salient pixels in an image that contribute to its score. Pathologists' input via informative training patches is an important aspect of the algorithm that allows the training for any specific marker or cell type. With co-training, TACOMA can be trained with a radically small training sample (e.g., with ...

  5. Segmentation of complex objects' sonar images using parameter-fixed MRF model

    YAO Bin; LI Hai-sen; ZHOU Tian; SUN SHENG-he


    The effective method of the recognition of underwater complex objects in sonar image is to segment sonar image into target, shadow and sea-bottom reverberation regions and then extract the edge of the object. Because of the time-varying and space-varying characters of underwater acoustics environment, the sonar images have poor quality and serious speckle noise, so traditional image segmentation is unable to achieve precise segmentation. In the paper, the image segmentation process based on MRF (Markov random field) model is studied, and a practical method of estimating model parameters is proposed. Through analyzing the impact of chosen model parameters, a sonar imagery segmentation algorithm based on fixed parameters' MRF model is proposed. Both of the segmentation effect and the low computing load are gained. By applying the algorithm to the synthesized texture image and actual side-scan sonar image, the algorithm can be achieved with precise segmentation result.

  6. Development of image-processing software for automatic segmentation of brain tumors in MR images

    C Vijayakumar


    Full Text Available Most of the commercially available software for brain tumor segmentation have limited functionality and frequently lack the careful validation that is required for clinical studies. We have developed an image-analysis software package called ′Prometheus,′ which performs neural system-based segmentation operations on MR images using pre-trained information. The software also has the capability to improve its segmentation performance by using the training module of the neural system. The aim of this article is to present the design and modules of this software. The segmentation module of Prometheus can be used primarily for image analysis in MR images. Prometheus was validated against manual segmentation by a radiologist and its mean sensitivity and specificity was found to be 85.71±4.89% and 93.2±2.87%, respectively. Similarly, the mean segmentation accuracy and mean correspondence ratio was found to be 92.35±3.37% and 0.78±0.046, respectively.

  7. An Interactive Java Statistical Image Segmentation System: GemIdent.

    Holmes, Susan; Kapelner, Adam; Lee, Peter P


    Supervised learning can be used to segment/identify regions of interest in images using both color and morphological information. A novel object identification algorithm was developed in Java to locate immune and cancer cells in images of immunohistochemically-stained lymph node tissue from a recent study published by Kohrt et al. (2005). The algorithms are also showing promise in other domains. The success of the method depends heavily on the use of color, the relative homogeneity of object appearance and on interactivity. As is often the case in segmentation, an algorithm specifically tailored to the application works better than using broader methods that work passably well on any problem. Our main innovation is the interactive feature extraction from color images. We also enable the user to improve the classification with an interactive visualization system. This is then coupled with the statistical learning algorithms and intensive feedback from the user over many classification-correction iterations, resulting in a highly accurate and user-friendly solution. The system ultimately provides the locations of every cell recognized in the entire tissue in a text file tailored to be easily imported into R (Ihaka and Gentleman 1996; R Development Core Team 2009) for further statistical analyses. This data is invaluable in the study of spatial and multidimensional relationships between cell populations and tumor structure. This system is available at together with three demonstration videos and a manual.

  8. Segmentation of dynamic PET images with kinetic spectral clustering

    Mouysset, S.; Zbib, H.; Stute, S.; Girault, J. M.; Charara, J.; Noailles, J.; Chalon, S.; Buvat, I.; Tauber, C.


    Segmentation is often required for the analysis of dynamic positron emission tomography (PET) images. However, noise and low spatial resolution make it a difficult task and several supervised and unsupervised methods have been proposed in the literature to perform the segmentation based on semi-automatic clustering of the time activity curves of voxels. In this paper we propose a new method based on spectral clustering that does not require any prior information on the shape of clusters in the space in which they are identified. In our approach, the p-dimensional data, where p is the number of time frames, is first mapped into a high dimensional space and then clustering is performed in a low-dimensional space of the Laplacian matrix. An estimation of the bounds for the scale parameter involved in the spectral clustering is derived. The method is assessed using dynamic brain PET images simulated with GATE and results on real images are presented. We demonstrate the usefulness of the method and its superior performance over three other clustering methods from the literature. The proposed approach appears as a promising pre-processing tool before parametric map calculation or ROI-based quantification tasks.

  9. Ant Colony Clustering Algorithm and Improved Markov Random Fusion Algorithm in Image Segmentation of Brain Images

    Guohua Zou


    Full Text Available New medical imaging technology, such as Computed Tomography and Magnetic Resonance Imaging (MRI, has been widely used in all aspects of medical diagnosis. The purpose of these imaging techniques is to obtain various qualitative and quantitative data of the patient comprehensively and accurately, and provide correct digital information for diagnosis, treatment planning and evaluation after surgery. MR has a good imaging diagnostic advantage for brain diseases. However, as the requirements of the brain image definition and quantitative analysis are always increasing, it is necessary to have better segmentation of MR brain images. The FCM (Fuzzy C-means algorithm is widely applied in image segmentation, but it has some shortcomings, such as long computation time and poor anti-noise capability. In this paper, firstly, the Ant Colony algorithm is used to determine the cluster centers and the number of FCM algorithm so as to improve its running speed. Then an improved Markov random field model is used to improve the algorithm, so that its antinoise ability can be improved. Experimental results show that the algorithm put forward in this paper has obvious advantages in image segmentation speed and segmentation effect.

  10. Segmentation of left atrial intracardiac ultrasound images for image guided cardiac ablation therapy

    Rettmann, M. E.; Stephens, T.; Holmes, D. R.; Linte, C.; Packer, D. L.; Robb, R. A.


    Intracardiac echocardiography (ICE), a technique in which structures of the heart are imaged using a catheter navigated inside the cardiac chambers, is an important imaging technique for guidance in cardiac ablation therapy. Automatic segmentation of these images is valuable for guidance and targeting of treatment sites. In this paper, we describe an approach to segment ICE images by generating an empirical model of blood pool and tissue intensities. Normal, Weibull, Gamma, and Generalized Extreme Value (GEV) distributions are fit to histograms of tissue and blood pool pixels from a series of ICE scans. A total of 40 images from 4 separate studies were evaluated. The model was trained and tested using two approaches. In the first approach, the model was trained on all images from 3 studies and subsequently tested on the 40 images from the 4th study. This procedure was repeated 4 times using a leave-one-out strategy. This is termed the between-subjects approach. In the second approach, the model was trained on 10 randomly selected images from a single study and tested on the remaining 30 images in that study. This is termed the within-subjects approach. For both approaches, the model was used to automatically segment ICE images into blood and tissue regions. Each pixel is classified using the Generalized Liklihood Ratio Test across neighborhood sizes ranging from 1 to 49. Automatic segmentation results were compared against manual segmentations for all images. In the between-subjects approach, the GEV distribution using a neighborhood size of 17 was found to be the most accurate with a misclassification rate of approximately 17%. In the within-subjects approach, the GEV distribution using a neighborhood size of 19 was found to be the most accurate with a misclassification rate of approximately 15%. As expected, the majority of misclassified pixels were located near the boundaries between tissue and blood pool regions for both methods.

  11. A Nonparametric Approach to Segmentation of Ladar Images


    Cribb, LtCol Doug Wickert, LtCol Amie Stryker, LtCol Jeff McGuirk , Lt Col Brad Christiansen , and Maj Craig Larsen. We all wanted to keep the good thing...28 3.6. Correlation coefficients and p-values for matched filter output. . . . . . . . . . . . . . 29 4.1. Sample “first-phase” principal...ladar data. The range segmentation is initialized using regions of uniform color in the registered RGB image. This detail, however, is not well-suited

  12. New variational image decomposition model for simultaneously denoising and segmenting optical coherence tomography images.

    Duan, Jinming; Tench, Christopher; Gottlob, Irene; Proudlock, Frank; Bai, Li


    Optical coherence tomography (OCT) imaging plays an important role in clinical diagnosis and monitoring of diseases of the human retina. Automated analysis of optical coherence tomography images is a challenging task as the images are inherently noisy. In this paper, a novel variational image decomposition model is proposed to decompose an OCT image into three components: the first component is the original image but with the noise completely removed; the second contains the set of edges representing the retinal layer boundaries present in the image; and the third is an image of noise, or in image decomposition terms, the texture, or oscillatory patterns of the original image. In addition, a fast Fourier transform based split Bregman algorithm is developed to improve computational efficiency of solving the proposed model. Extensive experiments are conducted on both synthesised and real OCT images to demonstrate that the proposed model outperforms the state-of-the-art speckle noise reduction methods and leads to accurate retinal layer segmentation.

  13. Automated Brain Tumor Segmentation on MR Images Based on Neutrosophic Set Approach

    Mohan J; Krishnaveni V; Yanhui Huo


    Brain tumor segmentation for MR images is a difficult and challenging task due to variation in type, size, location and shape of tumors. This paper presents an efficient and fully automatic brain tumor segmentation technique. This proposed technique includes non local preprocessing, fuzzy intensification to enhance the quality of the MR images, k - means clustering method for brain tumor segmentation.

  14. The reconstructed residual error: a novel segmentation evaluation measure for reconstructed images in tomography

    Roelandts, T.; Batenburg, K.J.; Dekker, A.J. den; Sijbers, J.


    In this paper, we present the reconstructed residual error, which evaluates the quality of a given segmentation of a reconstructed image in tomography. This novel evaluation method, which is independent of the methods that were used to reconstruct and segment the image, is applicable to segmentation

  15. Choroidal vasculature characteristics based choroid segmentation for enhanced depth imaging optical coherence tomography images

    Chen, Qiang; Niu, Sijie [School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094 (China); Yuan, Songtao; Fan, Wen, E-mail:; Liu, Qinghuai [Department of Ophthalmology, The First Affiliated Hospital with Nanjing Medical University, Nanjing 210029 (China)


    Purpose: In clinical research, it is important to measure choroidal thickness when eyes are affected by various diseases. The main purpose is to automatically segment choroid for enhanced depth imaging optical coherence tomography (EDI-OCT) images with five B-scans averaging. Methods: The authors present an automated choroid segmentation method based on choroidal vasculature characteristics for EDI-OCT images with five B-scans averaging. By considering the large vascular of the Haller’s layer neighbor with the choroid-sclera junction (CSJ), the authors measured the intensity ascending distance and a maximum intensity image in the axial direction from a smoothed and normalized EDI-OCT image. Then, based on generated choroidal vessel image, the authors constructed the CSJ cost and constrain the CSJ search neighborhood. Finally, graph search with smooth constraints was utilized to obtain the CSJ boundary. Results: Experimental results with 49 images from 10 eyes in 8 normal persons and 270 images from 57 eyes in 44 patients with several stages of diabetic retinopathy and age-related macular degeneration demonstrate that the proposed method can accurately segment the choroid of EDI-OCT images with five B-scans averaging. The mean choroid thickness difference and overlap ratio between the authors’ proposed method and manual segmentation drawn by experts were −11.43 μm and 86.29%, respectively. Conclusions: Good performance was achieved for normal and pathologic eyes, which proves that the authors’ method is effective for the automated choroid segmentation of the EDI-OCT images with five B-scans averaging.

  16. Choroidal vasculature characteristics based choroid segmentation for enhanced depth imaging optical coherence tomography images.

    Chen, Qiang; Niu, Sijie; Yuan, Songtao; Fan, Wen; Liu, Qinghuai


    In clinical research, it is important to measure choroidal thickness when eyes are affected by various diseases. The main purpose is to automatically segment choroid for enhanced depth imaging optical coherence tomography (EDI-OCT) images with five B-scans averaging. The authors present an automated choroid segmentation method based on choroidal vasculature characteristics for EDI-OCT images with five B-scans averaging. By considering the large vascular of the Haller's layer neighbor with the choroid-sclera junction (CSJ), the authors measured the intensity ascending distance and a maximum intensity image in the axial direction from a smoothed and normalized EDI-OCT image. Then, based on generated choroidal vessel image, the authors constructed the CSJ cost and constrain the CSJ search neighborhood. Finally, graph search with smooth constraints was utilized to obtain the CSJ boundary. Experimental results with 49 images from 10 eyes in 8 normal persons and 270 images from 57 eyes in 44 patients with several stages of diabetic retinopathy and age-related macular degeneration demonstrate that the proposed method can accurately segment the choroid of EDI-OCT images with five B-scans averaging. The mean choroid thickness difference and overlap ratio between the authors' proposed method and manual segmentation drawn by experts were -11.43 μm and 86.29%, respectively. Good performance was achieved for normal and pathologic eyes, which proves that the authors' method is effective for the automated choroid segmentation of the EDI-OCT images with five B-scans averaging.

  17. A combinatorial Bayesian and Dirichlet model for prostate MR image segmentation using probabilistic image features

    Li, Ang; Li, Changyang; Wang, Xiuying; Eberl, Stefan; Feng, Dagan; Fulham, Michael


    Blurred boundaries and heterogeneous intensities make accurate prostate MR image segmentation problematic. To improve prostate MR image segmentation we suggest an approach that includes: (a) an image patch division method to partition the prostate into homogeneous segments for feature extraction; (b) an image feature formulation and classification method, using the relevance vector machine, to provide probabilistic prior knowledge for graph energy construction; (c) a graph energy formulation scheme with Bayesian priors and Dirichlet graph energy and (d) a non-iterative graph energy minimization scheme, based on matrix differentiation, to perform the probabilistic pixel membership optimization. The segmentation output was obtained by assigning pixels with foreground and background labels based on derived membership probabilities. We evaluated our approach on the PROMISE-12 dataset with 50 prostate MR image volumes. Our approach achieved a mean dice similarity coefficient (DSC) of 0.90  ±  0.02, which surpassed the five best prior-based methods in the PROMISE-12 segmentation challenge.

  18. A curated collection of tissue microarray images and clinical outcome data of prostate cancer patients

    Zhong, Qing; Guo, Tiannan; Rechsteiner, Markus; Rüschoff, Jan H.; Rupp, Niels; Fankhauser, Christian; Saba, Karim; Mortezavi, Ashkan; Poyet, Cédric; Hermanns, Thomas; Zhu, Yi; Moch, Holger; Aebersold, Ruedi; Wild, Peter J.


    Microscopy image data of human cancers provide detailed phenotypes of spatially and morphologically intact tissues at single-cell resolution, thus complementing large-scale molecular analyses, e.g., next generation sequencing or proteomic profiling. Here we describe a high-resolution tissue microarray (TMA) image dataset from a cohort of 71 prostate tissue samples, which was hybridized with bright-field dual colour chromogenic and silver in situ hybridization probes for the tumour suppressor gene PTEN. These tissue samples were digitized and supplemented with expert annotations, clinical information, statistical models of PTEN genetic status, and computer source codes. For validation, we constructed an additional TMA dataset for 424 prostate tissues, hybridized with FISH probes for PTEN, and performed survival analysis on a subset of 339 radical prostatectomy specimens with overall, disease-specific and recurrence-free survival (maximum 167 months). For application, we further produced 6,036 image patches derived from two whole slides. Our curated collection of prostate cancer data sets provides reuse potential for both biomedical and computational studies. PMID:28291248

  19. A curated collection of tissue microarray images and clinical outcome data of prostate cancer patients.

    Zhong, Qing; Guo, Tiannan; Rechsteiner, Markus; Rüschoff, Jan H; Rupp, Niels; Fankhauser, Christian; Saba, Karim; Mortezavi, Ashkan; Poyet, Cédric; Hermanns, Thomas; Zhu, Yi; Moch, Holger; Aebersold, Ruedi; Wild, Peter J


    Microscopy image data of human cancers provide detailed phenotypes of spatially and morphologically intact tissues at single-cell resolution, thus complementing large-scale molecular analyses, e.g., next generation sequencing or proteomic profiling. Here we describe a high-resolution tissue microarray (TMA) image dataset from a cohort of 71 prostate tissue samples, which was hybridized with bright-field dual colour chromogenic and silver in situ hybridization probes for the tumour suppressor gene PTEN. These tissue samples were digitized and supplemented with expert annotations, clinical information, statistical models of PTEN genetic status, and computer source codes. For validation, we constructed an additional TMA dataset for 424 prostate tissues, hybridized with FISH probes for PTEN, and performed survival analysis on a subset of 339 radical prostatectomy specimens with overall, disease-specific and recurrence-free survival (maximum 167 months). For application, we further produced 6,036 image patches derived from two whole slides. Our curated collection of prostate cancer data sets provides reuse potential for both biomedical and computational studies.

  20. Robust automatic segmentation of corneal layer boundaries in SDOCT images using graph theory and dynamic programming.

    Larocca, Francesco; Chiu, Stephanie J; McNabb, Ryan P; Kuo, Anthony N; Izatt, Joseph A; Farsiu, Sina


    Segmentation of anatomical structures in corneal images is crucial for the diagnosis and study of anterior segment diseases. However, manual segmentation is a time-consuming and subjective process. This paper presents an automatic approach for segmenting corneal layer boundaries in Spectral Domain Optical Coherence Tomography images using graph theory and dynamic programming. Our approach is robust to the low-SNR and different artifact types that can appear in clinical corneal images. We show that our method segments three corneal layer boundaries in normal adult eyes more accurately compared to an expert grader than a second grader-even in the presence of significant imaging outliers.

  1. Fast interactive segmentation algorithm of image sequences based on relative fuzzy connectedness

    Tian Chunna; Gao Xinbo


    A fast interactive segmentation algorithm of image-sequences based on relative fuzzy connectedness is presented. In comparison with the original algorithm, the proposed one, with the same accuracy, accelerates the segmentation speed by three times for single image. Meanwhile, this fast segmentation algorithm is extended from single object to multiple objects and from single-image to image-sequences. Thus the segmentation of multiple objects from complex background and batch segmentation of image-sequences can be achieved. In addition, a post-processing scheme is incorporated in this algorithm, which extracts smooth edge with one-pixel-width for each segmented object. The experimental results illustrate that the proposed algorithm can obtain the object regions of interest from medical image or image-sequences as well as man-made images quickly and reliably with only a little interaction.

  2. [Automatic houses detection with color aerial images based on image segmentation].

    He, Pei-Pei; Wan, You-Chuan; Jiang, Peng-Rui; Gao, Xian-Jun; Qin, Jia-Xin


    In order to achieve housing automatic detection from high-resolution aerial imagery, the present paper utilized the color information and spectral characteristics of the roofing material, with the image segmentation theory, to study the housing automatic detection method. Firstly, This method proposed in this paper converts the RGB color space to HIS color space, uses the characteristics of each component of the HIS color space and the spectral characteristics of the roofing material for image segmentation to isolate red tiled roofs and gray cement roof areas, and gets the initial segmentation housing areas by using the marked watershed algorithm. Then, region growing is conducted in the hue component with the seed segment sample by calculating the average hue in the marked region. Finally through the elimination of small spots and rectangular fitting process to obtain a clear outline of the housing area. Compared with the traditional pixel-based region segmentation algorithm, the improved method proposed in this paper based on segment growing is in a one-dimensional color space to reduce the computation without human intervention, and can cater to the geometry information of the neighborhood pixels so that the speed and accuracy of the algorithm has been significantly improved. A case study was conducted to apply the method proposed in this paper to high resolution aerial images, and the experimental results demonstrate that this method has a high precision and rational robustness.

  3. Automated 3D ultrasound image segmentation to aid breast cancer image interpretation.

    Gu, Peng; Lee, Won-Mean; Roubidoux, Marilyn A; Yuan, Jie; Wang, Xueding; Carson, Paul L


    Segmentation of an ultrasound image into functional tissues is of great importance to clinical diagnosis of breast cancer. However, many studies are found to segment only the mass of interest and not all major tissues. Differences and inconsistencies in ultrasound interpretation call for an automated segmentation method to make results operator-independent. Furthermore, manual segmentation of entire three-dimensional (3D) ultrasound volumes is time-consuming, resource-intensive, and clinically impractical. Here, we propose an automated algorithm to segment 3D ultrasound volumes into three major tissue types: cyst/mass, fatty tissue, and fibro-glandular tissue. To test its efficacy and consistency, the proposed automated method was employed on a database of 21 cases of whole breast ultrasound. Experimental results show that our proposed method not only distinguishes fat and non-fat tissues correctly, but performs well in classifying cyst/mass. Comparison of density assessment between the automated method and manual segmentation demonstrates good consistency with an accuracy of 85.7%. Quantitative comparison of corresponding tissue volumes, which uses overlap ratio, gives an average similarity of 74.54%, consistent with values seen in MRI brain segmentations. Thus, our proposed method exhibits great potential as an automated approach to segment 3D whole breast ultrasound volumes into functionally distinct tissues that may help to correct ultrasound speed of sound aberrations and assist in density based prognosis of breast cancer.

  4. Methods for segmenting curved needles in ultrasound images.

    Okazawa, Stephen H; Ebrahimi, Richelle; Chuang, Jason; Rohling, Robert N; Salcudean, Septimiu E


    Ultrasound-guided percutaneous needle insertions are widely used techniques in current clinical practice. Some of these procedures have a high degree of difficulty because of poor observability of the needle in the ultrasound image. There have been recent efforts to improve guidance by computer assisted needle detection. These software techniques are often limited by not representing needle curvature. We present two methods to detect the needle in 2D ultrasound that specifically address needle curvature. Firstly, we demonstrate a real-time needle segmentation algorithm based on the Hough transform which detects the needle and represents its curved shape. Secondly, we demonstrate how a new coordinate transformation can transform detection of a curved needle to a linear fit. These methods are demonstrated on ultrasound and photographic images.

  5. Image segmentation and edge enhancement with stabilized inverse diffusion equations.

    Pollak, I; Willsky, A S; Krim, H


    We introduce a family of first-order multidimensional ordinary differential equations (ODEs) with discontinuous right-hand sides and demonstrate their applicability in image processing. An equation belonging to this family is an inverse diffusion everywhere except at local extrema, where some stabilization is introduced. For this reason, we call these equations "stabilized inverse diffusion equations" (SIDEs). Existence and uniqueness of solutions, as well as stability, are proven for SIDEs. A SIDE in one spatial dimension may be interpreted as a limiting case of a semi-discretized Perona-Malik equation. In an experiment, SIDE's are shown to suppress noise while sharpening edges present in the input signal. Their application to image segmentation is also demonstrated.

  6. Mixture Segmentation of Multispectral MR Brain Images for Multiple Sclerosis

    Lihong Li


    Full Text Available We present a fully automatic mixture model-based tissue classification of multispectral (T1- and T2-weighted magnetic resonance (MR brain images. Unlike the conventional hard classification with a unique label for each voxel, our method models a mixture to estimate the partial volumes (PV of multiple tissue types within a voxel. A new Markov random field (MRF model is proposed to reflect the spatial information of tissue mixtures. A mixture classification algorithm is performed by the maximum a posterior (MAP criterion, where the expectation maximization (EM algorithm is utilized to estimate model parameters. The algorithm interleaves segmentation with parameter estimation and improves classification in an iterative manner. The presented method is evaluated by clinical MR image datasets for quantification of brain volumes and multiple sclerosis (MS.

  7. Image Segmentation using bi directional of neural network

    HimadriNath Moulick


    Full Text Available Now a days image processing methods are widely used in medical science, to improve critical disease detection and fast treatment for recovery. Mainly this mechanism detects the disease as soon as possible and also find out the exact point of disorder and calculate the growth of this disease,especially in Squamous cell carcinoma in lower lip. Actinic keratosis which is 1/4 inch in diameter, isa pink or flesh coloured rough spot is one of the most important cause of squamous cell carcinoma,which is mainly grown in sun-exposed area. It is usually grow slowly and affects epidermis layer todermis layer. Our proposed method focuses on five different modules. These methods are including inImage Acquisition module and respective Pre-processing ,Segmentation , Filtering Phase and Edge Detection modules.

  8. Pixel-based skin segmentation in psoriasis images.

    George, Y; Aldeen, M; Garnavi, R


    In this paper, we present a detailed comparison study of skin segmentation methods for psoriasis images. Different techniques are modified and then applied to a set of psoriasis images acquired from the Royal Melbourne Hospital, Melbourne, Australia, with aim of finding the best technique suited for application to psoriasis images. We investigate the effect of different colour transformations on skin detection performance. In this respect, explicit skin thresholding is evaluated with three different decision boundaries (CbCr, HS and rgHSV). Histogram-based Bayesian classifier is applied to extract skin probability maps (SPMs) for different colour channels. This is then followed by using different approaches to find a binary skin map (SM) image from the SPMs. The approaches used include binary decision tree (DT) and Otsu's thresholding. Finally, a set of morphological operations are implemented to refine the resulted SM image. The paper provides detailed analysis and comparison of the performance of the Bayesian classifier in five different colour spaces (YCbCr, HSV, RGB, XYZ and CIELab). The results show that histogram-based Bayesian classifier is more effective than explicit thresholding, when applied to psoriasis images. It is also found that decision boundary CbCr outperforms HS and rgHSV. Another finding is that the SPMs of Cb, Cr, H and B-CIELab colour bands yield the best SMs for psoriasis images. In this study, we used a set of 100 psoriasis images for training and testing the presented methods. True Positive (TP) and True Negative (TN) are used as statistical evaluation measures.

  9. Estimation of coal particle size distribution by image segmentation

    Zhang Zelin; Yang Jianguo; Ding Lihua; Zhao Yuemin


    Several industrial coal processes are largely determined by the distribution of particle sizes in their feed.Currently these parameters are measured by manual sampling,which is time consuming and cannot provide real time feedback for automatic control purposes.In this paper,an approach using image segmentation on images of overlapped coal particles is described.The estimation of the particle size distribution by number is also described.The particle overlap problem was solved using image enhancement algorithms that converted those image parts representing material in lower layers to black.Exponential high-pass filter (EHPF) algorithms were used to remove the texture from particles on the surface.Finally,the edges of the surface particles were identified by morphological edge detection.These algorithms are described in detail as is the method of extracting the coal particle size.Tests indicate that using more coal images gives a higher accuracy estimate.The positive absolute error of 50 random tests was consistently less than 2.5% and the errors were reduced as the size of the fraction increased.

  10. Artificial immune kernel clustering network for unsupervised image segmentation

    Wenlong Huang; Licheng Jiao


    An immune kernel clustering network (IKCN) is proposed based on the combination of the artificial immune network and the support vector domain description (SVDD) for the unsupervised image segmentation. In the network, a new antibody neighborhood and an adaptive learning coefficient, which is inspired by the long-term memory in cerebral cortices are presented. Starting from IKCN algorithm, we divide the image feature sets into subsets by the antibodies, and then map each subset into a high dimensional feature space by a mercer kernel, where each antibody neighborhood is represented as a support vector hypersphere. The clustering results of the local support vector hyperspheres are combined to yield a global clustering solution by the minimal spanning tree (MST), where a predefined number of clustering is not needed. We compare the proposed methods with two common clustering algorithms for the artificial synthetic data set and several image data sets, including the synthetic texture images and the SAR images, and encouraging experimental results are obtained.

  11. A novel SAR fusion image segmentation method based on triplet Markov field

    Wang, Jiajing; Jiao, Shuhong; Sun, Zhenyu


    Markov random field (MRF) has been widely used in SAR image segmentation because of the advantage of directly modeling the posterior distribution and suppresses the speckle on the influence of the segmentation result. However, when the real SAR images are nonstationary images, the unsupervised segmentation results by MRF can be poor. The recent proposed triplet Markov field (TMF) model is well appropriate for nonstationary SAR image processing due to the introduction of an auxiliary field which reflects the nonstationarity. In addition, on account of the texture features of SAR image, a fusion image segmentation method is proposed by fusing the gray level image and texture feature image. The effectiveness of the proposed method in this paper is demonstrated by a synthesis SAR image and the real SAR images segmentation experiments, and it is better than the state-of-art methods.

  12. Feature selection applied to ultrasound carotid images segmentation.

    Rosati, Samanta; Molinari, Filippo; Balestra, Gabriella


    The automated tracing of the carotid layers on ultrasound images is complicated by noise, different morphology and pathology of the carotid artery. In this study we benchmarked four methods for feature selection on a set of variables extracted from ultrasound carotid images. The main goal was to select those parameters containing the highest amount of information useful to classify the pixels in the carotid regions they belong to. Six different classes of pixels were identified: lumen, lumen-intima interface, intima-media complex, media-adventitia interface, adventitia and adventitia far boundary. The performances of QuickReduct Algorithm (QRA), Entropy-Based Algorithm (EBR), Improved QuickReduct Algorithm (IQRA) and Genetic Algorithm (GA) were compared using Artificial Neural Networks (ANNs). All methods returned subsets with a high dependency degree, even if the average classification accuracy was about 50%. Among all classes, the best results were obtained for the lumen. Overall, the four methods for feature selection assessed in this study return comparable results. Despite the need for accuracy improvement, this study could be useful to build a pre-classifier stage for the optimization of segmentation performance in ultrasound automated carotid segmentation.

  13. Using Kernel Principal Components for Color Image Segmentation

    Wesolkowski, Slawo


    Distinguishing objects on the basis of color is fundamental to humans. In this paper, a clustering approach is used to segment color images. Clustering is usually done using a single point or vector as a cluster prototype. The data can be clustered in the input or feature space where the feature space is some nonlinear transformation of the input space. The idea of kernel principal component analysis (KPCA) was introduced to align data along principal components in the kernel or feature space. KPCA is a nonlinear transformation of the input data that finds the eigenvectors along which this data has maximum information content (or variation). The principal components resulting from KPCA are nonlinear in the input space and represent principal curves. This is a necessary step as colors in RGB are not linearly correlated especially considering illumination effects such as shading or highlights. The performance of the k-means (Euclidean distance-based) and Mixture of Principal Components (vector angle-based) algorithms are analyzed in the context of the input space and the feature space obtained using KPCA. Results are presented on a color image segmentation task. The results are discussed and further extensions are suggested.

  14. Selective Search and Intensity Context Based Retina Vessel Image Segmentation.

    Tang, Zhaohui; Zhang, Jin; Gui, Weihua


    In the framework of computer-aided diagnosis of eye disease, a new contextual image feature named influence degree of average intensity is proposed for retinal vessel image segmentation. This new feature evaluates the influence degree of current detected pixel decreasing the average intensity of the local row where that pixel located. Firstly, Hessian matrix is introduced to detect candidate regions, for the reason of accelerating segmentation. Then, the influence degree of average intensity of each pixel is extracted. Next, contextual feature vector for each pixel is constructed by concatenating the 8 feature neighbors. Finally, a classifier is built to classify each pixel into vessel or non-vessel based on its contextual feature. The effectiveness of the proposed method is demonstrated through receiver operating characteristic analysis on the benchmarked databases of DRIVE and STARE. Experiment results show that our method is comparable with the state-of-the-art methods. For example, the average accuracy, sensitivity, specificity achieved on the database DRIVE and STARE are 0.9611, 0.8174, 0.9747 and 0.9547, 0.7768, 0.9751, respectively.

  15. Automatic segmentation of pulmonary nodules on CT images by use of NCI lung image database consortium

    Tachibana, Rie; Kido, Shoji


    Accurate segmentation of small pulmonary nodules (SPNs) on thoracic CT images is an important technique for volumetric doubling time estimation and feature characterization for the diagnosis of SPNs. Most of the nodule segmentation algorithms that have been previously presented were designed to handle solid pulmonary nodules. However, SPNs with ground-glass opacity (GGO) also affects a diagnosis. Therefore, we have developed an automated volumetric segmentation algorithm of SPNs with GGO on thoracic CT images. This paper presents our segmentation algorithm with multiple fixed-thresholds, template-matching method, a distance-transformation method, and a watershed method. For quantitative evaluation of the performance of our algorithm, we used the first dataset provided by NCI Lung Image Database Consortium (LIDC). In the evaluation, we employed the coincident rate which was calculated with both the computerized segmented region of a SPN and the matching probability map (pmap) images provided by LIDC. As the result of 23 cases, the mean of the total coincident rate was 0.507 +/- 0.219. From these results, we concluded that our algorithm is useful for extracting SPNs with GGO and solid pattern as well as wide variety of SPNs in size.

  16. Image segmentation of pyramid style identifier based on Support Vector Machine for colorectal endoscopic images.

    Okamoto, Takumi; Koide, Tetsushi; Sugi, Koki; Shimizu, Tatsuya; Anh-Tuan Hoang; Tamaki, Toru; Raytchev, Bisser; Kaneda, Kazufumi; Kominami, Yoko; Yoshida, Shigeto; Mieno, Hiroshi; Tanaka, Shinji


    With the increase of colorectal cancer patients in recent years, the needs of quantitative evaluation of colorectal cancer are increased, and the computer-aided diagnosis (CAD) system which supports doctor's diagnosis is essential. In this paper, a hardware design of type identification module in CAD system for colorectal endoscopic images with narrow band imaging (NBI) magnification is proposed for real-time processing of full high definition image (1920 × 1080 pixel). A pyramid style image segmentation with SVMs for multi-size scan windows, which can be implemented on an FPGA with small circuit area and achieve high accuracy, is proposed for actual complex colorectal endoscopic images.

  17. Active Contour Model Coupling with Higher Order Diffusion for Medical Image Segmentation

    Guodong Wang


    Full Text Available Active contour models are very popular in image segmentation. Different features such as mean gray and variance are selected for different purpose. But for image with intensity inhomogeneities, there are no features for segmentation using the active contour model. The images with intensity inhomogeneities often occurred in real world especially in medical images. To deal with the difficulties raised in image segmentation with intensity inhomogeneities, a new active contour model with higher-order diffusion method is proposed. With the addition of gradient and Laplace information, the active contour model can converge to the edge of the image even with the intensity inhomogeneities. Because of the introduction of Laplace information, the difference scheme becomes more difficult. To enhance the efficiency of the segmentation, the fast Split Bregman algorithm is designed for the segmentation implementation. The performance of our method is demonstrated through numerical experiments of some medical image segmentations with intensity inhomogeneities.

  18. Evaluation of k-Means and fuzzy C-means segmentation on MR images of brain

    S.Madhukumar; N. Santhiyakumari


    This paper does the qualitative comparison of Fuzzy C-means (FCM) and k-Means segmentation, with histogram guided initialization, on tumor edema complex MR images. The accuracy of any segmentation scheme depends on its ability to distinguish different tissue classes, separately. Hence, there is a serious pre-requisite to evaluate this ability before employing the segmentation scheme on medical images. This paper evaluates the ability of FCM and k-Means to segment Gray Matter (GM), White Matte...

  19. New two-dimensional fuzzy C-means clustering algorithm for image segmentation


    To solve the problem of poor anti-noise performance of the traditional fuzzy C-means (FCM) algorithm in image segmentation,a novel two-dimensional FCM clustering algorithm for image segmentation was proposed.In this method,the image segmentation was converted into an optimization problem.The fitness function containing neighbor information was set up based on the gray information and the neighbor relations between the pixcls described by the improved two-dimensional histogram.By making use of the global searching ability of the predator-prey particle swarm optimization,the optimal cluster center could be obtained by iterative optimization,and the image segmentation could be accomplished.The simulation results show that the segmentation accuracy ratio of the proposed method is above 99%.The proposed algorithm has strong anti-noise capability,high clustering accuracy and good segment effect,indicating that it is an effective algorithm for image segmentation.

  20. Expanding the Diversity of Imaging-Based RNAi Screen Applications Using Cell Spot Microarrays.

    Rantala, Juha K; Kwon, Sunjong; Korkola, James; Gray, Joe W


    Over the past decade, great strides have been made in identifying gene aberrations and deregulated pathways that are associated with specific disease states. These association studies guide experimental studies aimed at identifying the aberrant genes and networks that cause the disease states. This requires functional manipulation of these genes and networks in laboratory models of normal and diseased cells. One approach is to assess molecular and biological responses to high-throughput RNA interference (RNAi)-induced gene knockdown. These responses can be revealed by immunofluorescent staining for a molecular or cellular process of interest and quantified using fluorescence image analysis. These applications are typically performed in multiwell format, but are limited by high reagent costs and long plate processing times. These limitations can be mitigated by analyzing cells grown in cell spot microarray (CSMA) format. CSMAs are produced by growing cells on small (~200 mm diameter) spots with each spot carrying an siRNA with transfection reagent. The spacing between spots is only a few hundred micrometers, thus thousands of cell spots can be arranged on a single cell culture surface. These high-density cell cultures can be immunofluorescently stained with minimal reagent consumption and analyzed quickly using automated fluorescence microscopy platforms. This review covers basic aspects of imaging-based CSMA technology, describes a wide range of immunofluorescence assays that have already been implemented successfully for CSMA screening and suggests future directions for advanced RNAi screening experiments.

  1. Segmentation of colon tissue sample images using multiple graphics accelerators.

    Szénási, Sándor


    Nowadays, processing medical images is increasingly done through using digital imagery and custom software solutions. The distributed algorithm presented in this paper is used to detect special tissue parts, the nuclei on haematoxylin and eosin stained colon tissue sample images. The main aim of this work is the development of a new data-parallel region growing algorithm that can be implemented even in an environment using multiple video accelerators. This new method has three levels of parallelism: (a) the parallel region growing itself, (b) starting more region growing in the device, and (c) using more than one accelerator. We use the split-and-merge technique based on our already existing data-parallel cell nuclei segmentation algorithm extended with a fast, backtracking-based, non-overlapping cell filter method. This extension does not cause significant degradation of the accuracy; the results are practically the same as those of the original sequential region growing method. However, as expected, using more devices usually means that less time is needed to process the tissue image; in the case of the configuration of one central processing unit and two graphics cards, the average speed-up is about 4-6×. The implemented algorithm has the additional advantage of efficiently processing very large images with high memory requirements. Copyright © 2014 Elsevier Ltd. All rights reserved.

  2. Region-based retrieval of remote sensing image patches with adaptive image segmentation

    Li, Shijin; Zhu, Jiali; Zhu, Yuelong; Feng, Jun


    Over the past four decades, the satellite imaging sensors have acquired huge quantities of Earth- observation data. Content-based image retrieval allows for fast and effective queries of remote sensing images. Here, we take the following two issues into consideration. Firstly, different features and their combination should be chosen for different land covers. Secondly, for the block dividing strategy and the complexities of the remote sensing images, it can not effectively retrieve some small target areas scattered in multiple nontarget blocks. Aiming at the above two issues, a new region-based retrieval method with adaptive image segmentation is proposed. In order to improve the accuracy of remote sensing image segmentation, feature selection and weighing is performed by two-stage clustering, and image segmentation is accomplished based on the chosen features and mean shift procedure. Meanwhile, for the homogeneous characteristics of remote sensing land covers, a new regional representation and matching scheme are adopted to perform image retrieval. Experimental results on retrieving various land covers show that the method can avoid the impact of traditional blocking strategies, and can achieve an average percentage of 19% higher precision with the same level of recall rate, than the relevance feedback method for small target areas.

  3. Automated segmentation of regions of interest in whole slide skin histopathological images.

    Xu, Hongming; Lu, Cheng; Mandal, Mrinal


    In the diagnosis of skin melanoma by analyzing histopathological images, the epidermis and epidermis-dermis junctional areas are regions of interest as they provide the most important histologic diagnosis features. This paper presents an automated technique for segmenting epidermis and dermis regions from whole slide skin histopathological images. The proposed technique first performs epidermis segmentation using a thresholding and thickness measurement based method. The dermis area is then segmented based on a predefined depth of segmentation from the epidermis outer boundary. Experimental results on 66 different skin images show that the proposed technique can robustly segment regions of interest as desired.

  4. Gravel Image Segmentation in Noisy Background Based on Partial Entropy Method


    Because of wide variation in gray levels and particle dimensions and the presence of many small gravel objects in the background, as well as corrupting the image by noise, it is difficult o segment gravel objects. In this paper, we develop a partial entropy method and succeed to realize gravel objects segmentation. We give entropy principles and fur calculation methods. Moreover, we use minimum entropy error automaticly to select a threshold to segment image. We introduce the filter method using mathematical morphology. The segment experiments are performed by using different window dimensions for a group of gravel image and demonstrates that this method has high segmentation rate and low noise sensitivity.

  5. Wavelet-based improved Chan-Vese model for image segmentation

    Zhao, Xiaoli; Zhou, Pucheng; Xue, Mogen


    In this paper, a kind of image segmentation approach which based on improved Chan-Vese (CV) model and wavelet transform was proposed. Firstly, one-level wavelet decomposition was adopted to get the low frequency approximation image. And then, the improved CV model, which contains the global term, local term and the regularization term, was utilized to segment the low frequency approximation image, so as to obtain the coarse image segmentation result. Finally, the coarse segmentation result was interpolated into the fine scale as an initial contour, and the improved CV model was utilized again to get the fine scale segmentation result. Experimental results show that our method can segment low contrast images and/or inhomogeneous intensity images more effectively than traditional level set methods.

  6. Automatic Spatially-Adaptive Balancing of Energy Terms for Image Segmentation

    Rao, Josna; Abugharbieh, Rafeef


    Image segmentation techniques are predominately based on parameter-laden optimization. The objective function typically involves weights for balancing competing image fidelity and segmentation regularization cost terms. Setting these weights suitably has been a painstaking, empirical process. Even if such ideal weights are found for a novel image, most current approaches fix the weight across the whole image domain, ignoring the spatially-varying properties of object shape and image appearance. We propose a novel technique that autonomously balances these terms in a spatially-adaptive manner through the incorporation of image reliability in a graph-based segmentation framework. We validate on synthetic data achieving a reduction in mean error of 47% (p-value << 0.05) when compared to the best fixed parameter segmentation. We also present results on medical images (including segmentations of the corpus callosum and brain tissue in MRI data) and on natural images.

  7. Hierarchical segmentation-assisted multimodal registration for MR brain images.

    Lu, Huanxiang; Beisteiner, Roland; Nolte, Lutz-Peter; Reyes, Mauricio


    Information theory-based metric such as mutual information (MI) is widely used as similarity measurement for multimodal registration. Nevertheless, this metric may lead to matching ambiguity for non-rigid registration. Moreover, maximization of MI alone does not necessarily produce an optimal solution. In this paper, we propose a segmentation-assisted similarity metric based on point-wise mutual information (PMI). This similarity metric, termed SPMI, enhances the registration accuracy by considering tissue classification probabilities as prior information, which is generated from an expectation maximization (EM) algorithm. Diffeomorphic demons is then adopted as the registration model and is optimized in a hierarchical framework (H-SPMI) based on different levels of anatomical structure as prior knowledge. The proposed method is evaluated using Brainweb synthetic data and clinical fMRI images. Both qualitative and quantitative assessment were performed as well as a sensitivity analysis to the segmentation error. Compared to the pure intensity-based approaches which only maximize mutual information, we show that the proposed algorithm provides significantly better accuracy on both synthetic and clinical data.

  8. X-ray image segmentation for vertebral mobility analysis

    Benjelloun, Mohammed; Mahmoudi, Said [Computer Science Department, Faculty of Engineering of Mons, Mons (Belgium)


    The goal of this work is to extract the parameters determining vertebral motion and its variation during flexion-extension movements using a computer vision tool for estimating and analyzing vertebral mobility. To compute vertebral body motion parameters we propose a comparative study between two segmentation methods proposed and applied to lateral X-ray images of the cervical spine. The two vertebra contour detection methods include (1) a discrete dynamic contour model (DDCM) and (2) a template matching process associated with a polar signature system. These two methods not only enable vertebra segmentation but also extract parameters that can be used to evaluate vertebral mobility. Lateral cervical spine views including 100 views in flexion, extension and neutral orientations were available for evaluation. Vertebral body motion was evaluated by human observers and using automatic methods. The results provided by the automated approaches were consistent with manual measures obtained by 15 human observers. The automated techniques provide acceptable results for the assessment of vertebral body mobility in flexion and extension on lateral views of the cervical spine. (orig.)

  9. An Island and Coastal Image Segmentation Method Based on Quadtree and GAC Model

    Guo, Haitao; Sun, Lei; SHEN Jiashuang; Chen, Xiaowei; Zhang, Hongwei


    Island and coastal image segmentation is of great importance for the subsequent coastline extraction, terrain inversion for intertidal zone, analysis of the situation for shore evolution, and so on. Firstly, the advantages and disadvantages of quadtree, geodesic active contour (GAC) model and Canny edge detector used in the island and coastal image segmentation are analyzed. Secondly, an island and coastal image segmentation method is proposed by integrating quadtree, GAC model and Canny edge...

  10. Time of Flight Image Segmentation through Co-Regularized Spectral Clustering

    Lorenti, Luciano; Giacomantone, Javier


    Time of Flight (TOF) cameras generate two simultaneous images, one for intensity and one for range. This allows tackling segmentation problems where the information pertaining to intensity or range alone is not enough to extract objects of interest from a 3D scene. In this paper, we present a spectral segmentation method that combines information from both images. By modifying the affinity matrix of each of the images based on the other, the segmentation of objects in the scene is improved. T...

  11. Two-level evaluation on sensor interoperability of features in fingerprint image segmentation.

    Yang, Gongping; Li, Ying; Yin, Yilong; Li, Ya-Shuo


    Features used in fingerprint segmentation significantly affect the segmentation performance. Various features exhibit different discriminating abilities on fingerprint images derived from different sensors. One feature which has better discriminating ability on images derived from a certain sensor may not adapt to segment images derived from other sensors. This degrades the segmentation performance. This paper empirically analyzes the sensor interoperability problem of segmentation feature, which refers to the feature's ability to adapt to the raw fingerprints captured by different sensors. To address this issue, this paper presents a two-level feature evaluation method, including the first level feature evaluation based on segmentation error rate and the second level feature evaluation based on decision tree. The proposed method is performed on a number of fingerprint databases which are obtained from various sensors. Experimental results show that the proposed method can effectively evaluate the sensor interoperability of features, and the features with good evaluation results acquire better segmentation accuracies of images originating from different sensors.

  12. Automatic segmentation for brain MR images via a convex optimized segmentation and bias field correction coupled model.

    Chen, Yunjie; Zhao, Bo; Zhang, Jianwei; Zheng, Yuhui


    Accurate segmentation of magnetic resonance (MR) images remains challenging mainly due to the intensity inhomogeneity, which is also commonly known as bias field. Recently active contour models with geometric information constraint have been applied, however, most of them deal with the bias field by using a necessary pre-processing step before segmentation of MR data. This paper presents a novel automatic variational method, which can segment brain MR images meanwhile correcting the bias field when segmenting images with high intensity inhomogeneities. We first define a function for clustering the image pixels in a smaller neighborhood. The cluster centers in this objective function have a multiplicative factor that estimates the bias within the neighborhood. In order to reduce the effect of the noise, the local intensity variations are described by the Gaussian distributions with different means and variances. Then, the objective functions are integrated over the entire domain. In order to obtain the global optimal and make the results independent of the initialization of the algorithm, we reconstructed the energy function to be convex and calculated it by using the Split Bregman theory. A salient advantage of our method is that its result is independent of initialization, which allows robust and fully automated application. Our method is able to estimate the bias of quite general profiles, even in 7T MR images. Moreover, our model can also distinguish regions with similar intensity distribution with different variances. The proposed method has been rigorously validated with images acquired on variety of imaging modalities with promising results.

  13. Simulated annealing spectral clustering algorithm for image segmentation

    Yifang Yang; and Yuping Wang


    The similarity measure is crucial to the performance of spectral clustering. The Gaussian kernel function based on the Euclidean distance is usual y adopted as the similarity mea-sure. However, the Euclidean distance measure cannot ful y reveal the complex distribution data, and the result of spectral clustering is very sensitive to the scaling parameter. To solve these problems, a new manifold distance measure and a novel simulated anneal-ing spectral clustering (SASC) algorithm based on the manifold distance measure are proposed. The simulated annealing based on genetic algorithm (SAGA), characterized by its rapid conver-gence to the global optimum, is used to cluster the sample points in the spectral mapping space. The proposed algorithm can not only reflect local and global consistency better, but also reduce the sensitivity of spectral clustering to the kernel parameter, which improves the algorithm’s clustering performance. To efficiently ap-ply the algorithm to image segmentation, the Nystr¨om method is used to reduce the computation complexity. Experimental re-sults show that compared with traditional clustering algorithms and those popular spectral clustering algorithms, the proposed algorithm can achieve better clustering performances on several synthetic datasets, texture images and real images.

  14. RBCs and Parasites Segmentation from Thin Smear Blood Cell Images

    Vishal V. Panchbhai


    Full Text Available Manually examine the blood smear for the detection of malaria parasite consumes lot of time for trend pathologists. As the computational power increases, the role of automatic visual inspection becomes more important. An automated system is therefore needed to complete as much work as possible for the identification of malaria parasites. The given scheme based on used of RGB color space, G layer processing, and segmentation of Red Blood Cells (RBC as well as cell parasites by auto-thresholding with offset value and use of morphological processing. The work compare with the manual results obtained from the pathology lab, based on total RBC count and cells parasite count. The designed system successfully detects malaria parasites and RBC cells in thin smear image.

  15. Fat segmentation on chest CT images via fuzzy models

    Tong, Yubing; Udupa, Jayaram K.; Wu, Caiyun; Pednekar, Gargi; Subramanian, Janani Rajan; Lederer, David J.; Christie, Jason; Torigian, Drew A.


    Quantification of fat throughout the body is vital for the study of many diseases. In the thorax, it is important for lung transplant candidates since obesity and being underweight are contraindications to lung transplantation given their associations with increased mortality. Common approaches for thoracic fat segmentation are all interactive in nature, requiring significant manual effort to draw the interfaces between fat and muscle with low efficiency and questionable repeatability. The goal of this paper is to explore a practical way for the segmentation of subcutaneous adipose tissue (SAT) and visceral adipose tissue (VAT) components of chest fat based on a recently developed body-wide automatic anatomy recognition (AAR) methodology. The AAR approach involves 3 main steps: building a fuzzy anatomy model of the body region involving all its major representative objects, recognizing objects in any given test image, and delineating the objects. We made several modifications to these steps to develop an effective solution to delineate SAT/VAT components of fat. Two new objects representing interfaces of SAT and VAT regions with other tissues, SatIn and VatIn are defined, rather than using directly the SAT and VAT components as objects for constructing the models. A hierarchical arrangement of these new and other reference objects is built to facilitate their recognition in the hierarchical order. Subsequently, accurate delineations of the SAT/VAT components are derived from these objects. Unenhanced CT images from 40 lung transplant candidates were utilized in experimentally evaluating this new strategy. Mean object location error achieved was about 2 voxels and delineation error in terms of false positive and false negative volume fractions were, respectively, 0.07 and 0.1 for SAT and 0.04 and 0.2 for VAT.

  16. Automatic gallbladder and gallstone regions segmentation in ultrasound image.

    Lian, Jing; Ma, Yide; Ma, Yurun; Shi, Bin; Liu, Jizhao; Yang, Zhen; Guo, Yanan


    As gallbladder diseases including gallstone and cholecystitis are mainly diagnosed by using ultra-sonographic examinations, we propose a novel method to segment the gallbladder and gallstones in ultrasound images. The method is divided into five steps. Firstly, a modified Otsu algorithm is combined with the anisotropic diffusion to reduce speckle noise and enhance image contrast. The Otsu algorithm separates distinctly the weak edge regions from the central region of the gallbladder. Secondly, a global morphology filtering algorithm is adopted for acquiring the fine gallbladder region. Thirdly, a parameter-adaptive pulse-coupled neural network (PA-PCNN) is employed to obtain the high-intensity regions including gallstones. Fourthly, a modified region-growing algorithm is used to eliminate physicians' labeled regions and avoid over-segmentation of gallstones. It also has good self-adaptability within the growth cycle in light of the specified growing and terminating conditions. Fifthly, the smoothing contours of the detected gallbladder and gallstones are obtained by the locally weighted regression smoothing (LOESS). We test the proposed method on the clinical data from Gansu Provincial Hospital of China and obtain encouraging results. For the gallbladder and gallstones, average similarity percent of contours (EVA) containing metrics dice's similarity , overlap fraction and overlap value is 86.01 and 79.81%, respectively; position error is 1.7675 and 0.5414 mm, respectively; runtime is 4.2211 and 0.6603 s, respectively. Our method then achieves competitive performance compared with the state-of-the-art methods. The proposed method is potential to assist physicians for diagnosing the gallbladder disease rapidly and effectively.

  17. Using Quadtree Algorithm for Improving Fuzzy C-means Method in Image Segmentation

    Zahra Ghorbanzad; Farshid Babapour


    Image segmentation is an essential processing step for much image application and there are a large number of segmentation techniques. A new algorithm for image segmentation called Quad tree fuzzy c-means (QFCM) is presented I this work. The key idea in our approach is a Quad tree function combined with fuzzy c-means algorithm. In this article we also discuss the advantages and disadvantages of other image segmenting methods like: k-means, c-means, and blocked fuzzy c-means. Different experim...

  18. The remote sensing image segmentation mean shift algorithm parallel processing based on MapReduce

    Chen, Xi; Zhou, Liqing


    With the development of satellite remote sensing technology and the remote sensing image data, traditional remote sensing image segmentation technology cannot meet the massive remote sensing image processing and storage requirements. This article put cloud computing and parallel computing technology in remote sensing image segmentation process, and build a cheap and efficient computer cluster system that uses parallel processing to achieve MeanShift algorithm of remote sensing image segmentation based on the MapReduce model, not only to ensure the quality of remote sensing image segmentation, improved split speed, and better meet the real-time requirements. The remote sensing image segmentation MeanShift algorithm parallel processing algorithm based on MapReduce shows certain significance and a realization of value.

  19. An Island and Coastal Image Segmentation Method Based on Quadtree and GAC Model

    GUO Haitao


    Full Text Available Island and coastal image segmentation is of great importance for the subsequent coastline extraction, terrain inversion for intertidal zone, analysis of the situation for shore evolution, and so on. Firstly, the advantages and disadvantages of quadtree, geodesic active contour (GAC model and Canny edge detector used in the island and coastal image segmentation are analyzed. Secondly, an island and coastal image segmentation method is proposed by integrating quadtree, GAC model and Canny edge detector. The advantages of these three kinds of method are taken in the method proposed in this paper. The method introduces the results of Canny edge detector into edge indicator function of geodesic active contour model based on quadtree segmentation, evolutes the level set equation, and realizes island and coastal image segmentation.The experimental results show that the method proposed in this paper is of high speed, precision, reliability and automation for island and coastal image segmentation, even in the weak edges and serious concave edges.

  20. Multiple-Channel Lo cal Binary Fitting Mo del for Medical Image Segmentation

    GUO Qi; WANG Long; SHEN Shuting


    This study proposes an innovative M-L (Multiple-channel local binary fitting) model for medical image segmentation. Designed to improve upon existing image segmentation models, the M-L model introduces a regional limit function to the multi-band active con-tour model to enable multilayer image segmentation. The Gaussian kernel function is used to improve the previous model’s robustness, necessitating the use of a new initial-ization curve which enhances the accuracy of segmentation results. Compared to existing image segmentation meth-ods, the proposed M-L model improves numerical stability and efficiency through the introduction of a new penalty term and an increased step length. This simulation exper-iment verifies the advantages of the new M-L model for improved medical image segmentation, including increased efficiency and usability of the model.