The Complete Gabor-Fisher Classifier for Robust Face Recognition

Directory of Open Access Journals (Sweden)

Štruc Vitomir

2010-01-01

Full Text Available Abstract This paper develops a novel face recognition technique called Complete Gabor Fisher Classifier (CGFC. Different from existing techniques that use Gabor filters for deriving the Gabor face representation, the proposed approach does not rely solely on Gabor magnitude information but effectively uses features computed based on Gabor phase information as well. It represents one of the few successful attempts found in the literature of combining Gabor magnitude and phase information for robust face recognition. The novelty of the proposed CGFC technique comes from (1 the introduction of a Gabor phase-based face representation and (2 the combination of the recognition technique using the proposed representation with classical Gabor magnitude-based methods into a unified framework. The proposed face recognition framework is assessed in a series of face verification and identification experiments performed on the XM2VTS, Extended YaleB, FERET, and AR databases. The results of the assessment suggest that the proposed technique clearly outperforms state-of-the-art face recognition techniques from the literature and that its performance is almost unaffected by the presence of partial occlusions of the facial area, changes in facial expression, or severe illumination changes.

FINGERPRINT VERIFICATION IN PERSONAL IDENTIFICATION BY APPLYING LOCAL WALSH HADAMARD TRANSFORM AND GABOR COEFFICIENTS

Directory of Open Access Journals (Sweden)

K N Pushpalatha

2017-05-01

Full Text Available In an era of advanced computer technology world where innumerable services such as access to bank accounts, or access to secured data or entry to some national important organizations require authentication of genuine individual. Among all biometric personal identification systems, fingerprint recognition system is most accurate and economical technology. In this paper we have proposed fingerprint recognition system using Local Walsh Hadamard Transform (LWHT with Phase Magnitude Histograms (PMHs for feature extraction. Fingerprints display oriented texture-like patterns. Gabor filters have the property of capturing global and local texture information from blur or unclear images and filter bank provides the orientation features which are robust to image distortion and rotation. The LWHT algorithm is compared with other two approaches viz., Gabor Coefficients and Directional Features. The three methods are compared using FVC 2006 Finger print database images. It is found from the observation that the values of TSR, FAR and FRR have improved results compared to existing algorithm.

Texture Feature Extraction and Classification for Iris Diagnosis

Science.gov (United States)

Ma, Lin; Li, Naimin

Appling computer aided techniques in iris image processing, and combining occidental iridology with the traditional Chinese medicine is a challenging research area in digital image processing and artificial intelligence. This paper proposes an iridology model that consists the iris image pre-processing, texture feature analysis and disease classification. To the pre-processing, a 2-step iris localization approach is proposed; a 2-D Gabor filter based texture analysis and a texture fractal dimension estimation method are proposed for pathological feature extraction; and at last support vector machines are constructed to recognize 2 typical diseases such as the alimentary canal disease and the nerve system disease. Experimental results show that the proposed iridology diagnosis model is quite effective and promising for medical diagnosis and health surveillance for both hospital and public use.

Thermographic image analysis for classification of ACL rupture disease, bone cancer, and feline hyperthyroid, with Gabor filters

Science.gov (United States)

Alvandipour, Mehrdad; Umbaugh, Scott E.; Mishra, Deependra K.; Dahal, Rohini; Lama, Norsang; Marino, Dominic J.; Sackman, Joseph

2017-05-01

Thermography and pattern classification techniques are used to classify three different pathologies in veterinary images. Thermographic images of both normal and diseased animals were provided by the Long Island Veterinary Specialists (LIVS). The three pathologies are ACL rupture disease, bone cancer, and feline hyperthyroid. The diagnosis of these diseases usually involves radiology and laboratory tests while the method that we propose uses thermographic images and image analysis techniques and is intended for use as a prescreening tool. Images in each category of pathologies are first filtered by Gabor filters and then various features are extracted and used for classification into normal and abnormal classes. Gabor filters are linear filters that can be characterized by the two parameters wavelength λ and orientation θ. With two different wavelength and five different orientations, a total of ten different filters were studied. Different combinations of camera views, filters, feature vectors, normalization methods, and classification methods, produce different tests that were examined and the sensitivity, specificity and success rate for each test were produced. Using the Gabor features alone, sensitivity, specificity, and overall success rates of 85% for each of the pathologies was achieved.

Finite Discrete Gabor Analysis

DEFF Research Database (Denmark)

Søndergaard, Peter Lempel

2007-01-01

frequency bands at certain times. Gabor theory can be formulated for both functions on the real line and for discrete signals of finite length. The two theories are largely the same because many aspects come from the same underlying theory of locally compact Abelian groups. The two types of Gabor systems...... can also be related by sampling and periodization. This thesis extends on this theory by showing new results for window construction. It also provides a discussion of the problems associated to discrete Gabor bases. The sampling and periodization connection is handy because it allows Gabor systems...... on the real line to be well approximated by finite and discrete Gabor frames. This method of approximation is especially attractive because efficient numerical methods exists for doing computations with finite, discrete Gabor systems. This thesis presents new algorithms for the efficient computation of finite...

Gabor filter based fingerprint image enhancement

Science.gov (United States)

Wang, Jin-Xiang

2013-03-01

Fingerprint recognition technology has become the most reliable biometric technology due to its uniqueness and invariance, which has been most convenient and most reliable technique for personal authentication. The development of Automated Fingerprint Identification System is an urgent need for modern information security. Meanwhile, fingerprint preprocessing algorithm of fingerprint recognition technology has played an important part in Automatic Fingerprint Identification System. This article introduces the general steps in the fingerprint recognition technology, namely the image input, preprocessing, feature recognition, and fingerprint image enhancement. As the key to fingerprint identification technology, fingerprint image enhancement affects the accuracy of the system. It focuses on the characteristics of the fingerprint image, Gabor filters algorithm for fingerprint image enhancement, the theoretical basis of Gabor filters, and demonstration of the filter. The enhancement algorithm for fingerprint image is in the windows XP platform with matlab.65 as a development tool for the demonstration. The result shows that the Gabor filter is effective in fingerprint image enhancement technology.

Text Detection in Natural Scene Images by Stroke Gabor Words.

Science.gov (United States)

Yi, Chucai; Tian, Yingli

2011-01-01

In this paper, we propose a novel algorithm, based on stroke components and descriptive Gabor filters, to detect text regions in natural scene images. Text characters and strings are constructed by stroke components as basic units. Gabor filters are used to describe and analyze the stroke components in text characters or strings. We define a suitability measurement to analyze the confidence of Gabor filters in describing stroke component and the suitability of Gabor filters on an image window. From the training set, we compute a set of Gabor filters that can describe principle stroke components of text by their parameters. Then a K -means algorithm is applied to cluster the descriptive Gabor filters. The clustering centers are defined as Stroke Gabor Words (SGWs) to provide a universal description of stroke components. By suitability evaluation on positive and negative training samples respectively, each SGW generates a pair of characteristic distributions of suitability measurements. On a testing natural scene image, heuristic layout analysis is applied first to extract candidate image windows. Then we compute the principle SGWs for each image window to describe its principle stroke components. Characteristic distributions generated by principle SGWs are used to classify text or nontext windows. Experimental results on benchmark datasets demonstrate that our algorithm can handle complex backgrounds and variant text patterns (font, color, scale, etc.).

Deep learning architecture for iris recognition based on optimal Gabor filters and deep belief network

Science.gov (United States)

He, Fei; Han, Ye; Wang, Han; Ji, Jinchao; Liu, Yuanning; Ma, Zhiqiang

2017-03-01

Gabor filters are widely utilized to detect iris texture information in several state-of-the-art iris recognition systems. However, the proper Gabor kernels and the generative pattern of iris Gabor features need to be predetermined in application. The traditional empirical Gabor filters and shallow iris encoding ways are incapable of dealing with such complex variations in iris imaging including illumination, aging, deformation, and device variations. Thereby, an adaptive Gabor filter selection strategy and deep learning architecture are presented. We first employ particle swarm optimization approach and its binary version to define a set of data-driven Gabor kernels for fitting the most informative filtering bands, and then capture complex pattern from the optimal Gabor filtered coefficients by a trained deep belief network. A succession of comparative experiments validate that our optimal Gabor filters may produce more distinctive Gabor coefficients and our iris deep representations be more robust and stable than traditional iris Gabor codes. Furthermore, the depth and scales of the deep learning architecture are also discussed.

New Statistics for Texture Classification Based on Gabor Filters

Directory of Open Access Journals (Sweden)

J. Pavlovicova

2007-09-01

Full Text Available The paper introduces a new method of texture segmentation efficiency evaluation. One of the well known texture segmentation methods is based on Gabor filters because of their orientation and spatial frequency character. Several statistics are used to extract more information from results obtained by Gabor filtering. Big amount of input parameters causes a wide set of results which need to be evaluated. The evaluation method is based on the normal distributions Gaussian curves intersection assessment and provides a new point of view to the segmentation method selection.

Efficient iris texture analysis method based on Gabor ordinal measures

Science.gov (United States)

Tajouri, Imen; Aydi, Walid; Ghorbel, Ahmed; Masmoudi, Nouri

2017-07-01

With the remarkably increasing interest directed to the security dimension, the iris recognition process is considered to stand as one of the most versatile technique critically useful for the biometric identification and authentication process. This is mainly due to every individual's unique iris texture. A modestly conceived efficient approach relevant to the feature extraction process is proposed. In the first place, iris zigzag "collarette" is extracted from the rest of the image by means of the circular Hough transform, as it includes the most significant regions lying in the iris texture. In the second place, the linear Hough transform is used for the eyelids' detection purpose while the median filter is applied for the eyelashes' removal. Then, a special technique combining the richness of Gabor features and the compactness of ordinal measures is implemented for the feature extraction process, so that a discriminative feature representation for every individual can be achieved. Subsequently, the modified Hamming distance is used for the matching process. Indeed, the advanced procedure turns out to be reliable, as compared to some of the state-of-the-art approaches, with a recognition rate of 99.98%, 98.12%, and 95.02% on CASIAV1.0, CASIAV3.0, and IIT Delhi V1 iris databases, respectively.

Edge Detection from High Resolution Remote Sensing Images using Two-Dimensional log Gabor Filter in Frequency Domain

International Nuclear Information System (INIS)

Wang, K; Yu, T; Meng, Q Y; Wang, G K; Li, S P; Liu, S H

2014-01-01

Edges are vital features to describe the structural information of images, especially high spatial resolution remote sensing images. Edge features can be used to define the boundaries between different ground objects in high spatial resolution remote sensing images. Thus edge detection is important in the remote sensing image processing. Even though many different edge detection algorithms have been proposed, it is difficult to extract the edge features from high spatial resolution remote sensing image including complex ground objects. This paper introduces a novel method to detect edges from the high spatial resolution remote sensing image based on frequency domain. Firstly, the high spatial resolution remote sensing images are Fourier transformed to obtain the magnitude spectrum image (frequency image) by FFT. Then, the frequency spectrum is analyzed by using the radius and angle sampling. Finally, two-dimensional log Gabor filter with optimal parameters is designed according to the result of spectrum analysis. Finally, dot product between the result of Fourier transform and the log Gabor filter is inverse Fourier transformed to obtain the detections. The experimental result shows that the proposed algorithm can detect edge features from the high resolution remote sensing image commendably

The $abc$-problem for Gabor systems

CERN Document Server

Dai, Xin-Rong

2016-01-01

A longstanding problem in Gabor theory is to identify time-frequency shifting lattices a\\mathbb{Z}\\times b\\mathbb{Z} and ideal window functions \\chi_I on intervals I of length c such that \\{e^{-2\\pi i n bt} \\chi_I(t- m a):\\ (m, n)\\in \\mathbb{Z}\\times \\mathbb{Z}\\} are Gabor frames for the space of all square-integrable functions on the real line. In this paper, the authors create a time-domain approach for Gabor frames, introduce novel techniques involving invariant sets of non-contractive and non-measure-preserving transformations on the line, and provide a complete answer to the above abc-problem for Gabor systems.

Gabor frames by sampling and periodization

DEFF Research Database (Denmark)

Søndergaard, Peter Lempel

2007-01-01

By sampling the window of Gabor frame for L-2 (R) belonging to Feichtingers algebra S-0 (R), one obtains a Gabor frame for l(2) (Z). In this article we present a survey of results by R. Orr and A.J.E.M. Janssen and extend their ideas to cover interrelations among Gabor frames for the four spaces L......-2 (R), l(2) (Z), L-2 ([O,L]) and C-L. Some new results about the general dual windows with respect to sampling and periodization are presented as well. This theory is used to show a new result of the Kaiblinger type to construct an approximation to the canonical dual window of a Gabor frame for L-2...

Density of Gabor Frames

DEFF Research Database (Denmark)

Christensen, Ole; Heil, C.; Deng, B.

1997-01-01

A Gabor system is a set of time-frequency shifts$S(g,\\Lambda) = \\{e^{2\\pi i b x} g(x-a)\\}_{(a,b) \\in \\Lambda}$of a function $g \\in L^2({\\bold R}^d)$.We prove that if a finite union of Gabor systems$\\bigcup_{k=1}^r S(g_k,\\Lambda_k)$, with arbitrary sequences $\\Lambda_k$,forms a frame for $L^2({\\bo...

On the discrete version of Gabor's signal expansion, the Gabor transform, and the Zak transform

NARCIS (Netherlands)

Bastiaans, M.J.; Veen, J.P.

1996-01-01

Gabors expansion of a discrete-time signal into a set of shifted and modulated versions of an elementary signal or synthesis window is introduced, along with the inverse operation, i.e., the Gabor transform, which uses an analysis window that is related to the synthesis window and with the help of

Gabor lens focusing of a negative ion beam

International Nuclear Information System (INIS)

Palkovic, J.A.; Mills, F.E.; Schmidt, C.; Young, D.E.

1989-05-01

Gabor or plasma lenses have previously been used to focus intense beams of positive ions at energies from 10 keV to 5 MeV. It is the large electrostatic field of the non-neutral plasma in the Gabor lens which is responsible for the focusing. Focusing an ion beam with a given sign of charge in a Gabor lens requires a non-neutral plasma with the opposite sign of charge as the beam. A Gabor lens constructed at Fermilab has been used to focus a 30 keV proton beam with good optical quality. We discuss studies of the action of a Gabor lens on a beam of negative ions. A Gabor lens has been considered for matching an H/sup /minus// beam into an RFQ in the redesign of the low energy section of the Fermilab linac. 9 refs., 3 figs., 1 tab

DETEKSI LANDMARK CITRA WAJAH DENGAN EXTRAKSI FITUR GABOR ANALISA FUZZY

Directory of Open Access Journals (Sweden)

Resmana Lim

2003-01-01

Full Text Available This paper proposes a method that automatically finds human faces as well as its landmark points in color images based on a fuzzy analysis. The proposed approach first uses color information to detect face candidate regions and then uses a fuzzy analysis of the color, shape, symmetry and interior facial features. A deformable Gabor wavelet graph matching is used to locate the facial landmark points describing the face. The latter allows for size and orientation variation since the search for landmark points allows for affine transformations as well as local deformations of the Gabor wavelet graph. The search is performed using a genetic algorithm that is essential because it effectively searches the solution space. Results based on the proposed method are included to verify the effectiveness of the proposed approach. Abstract in Bahasa Indonesia : Paper ini mengusulkan sebuah metode deteksi wajah beserta dengan titik landmarknya pada citra berwarna menggunakan analisa fuzzy. Proses awal menggunakan informasi warna kulit untuk menseleksi calon-calon obyek lantas dilanjukan dengan analisa fuzzy terhadap warna, bentuk, simetri dan fitur/landmark wajah. Proses lokalisasi landmark wajah menggunakan Gabor wavelet graph matching dengan memaksimalkan kemiripan antara landmark wajah model dengan obyek inputan. Proses maksimalisasi kemiripan ini menggunakan algoritma genetika. Hasil-hasil percobaan ditampilkan untuk memberikan gambaran keberhasilan dari metode yang diusulkan. Kata kunci: lokalisasi landmark wajah, analisa fuzzy, graph matching, algoritma genetika, Gabor wavelet.

Gabor transform and Zak transform with rational oversampling

NARCIS (Netherlands)

Bastiaans, M.J.; Ramponi, G.; Sicuranza, G.L.; Carrato, S.; Marsi, S.

1996-01-01

Gabor's expansion of a signal into a set of shifted and modulated versions of an elementary signal is introduced, along with the inverse operation, i.e. the Gabor transform, which uses a window function that is related to the elementary signal and with the help of which Gabor's expansion

Automatic target classification of man-made objects in synthetic aperture radar images using Gabor wavelet and neural network

Science.gov (United States)

Vasuki, Perumal; Roomi, S. Mohamed Mansoor

2013-01-01

Processing of synthetic aperture radar (SAR) images has led to the development of automatic target classification approaches. These approaches help to classify individual and mass military ground vehicles. This work aims to develop an automatic target classification technique to classify military targets like truck/tank/armored car/cannon/bulldozer. The proposed method consists of three stages via preprocessing, feature extraction, and neural network (NN). The first stage removes speckle noise in a SAR image by the identified frost filter and enhances the image by histogram equalization. The second stage uses a Gabor wavelet to extract the image features. The third stage classifies the target by an NN classifier using image features. The proposed work performs better than its counterparts, like K-nearest neighbor (KNN). The proposed work performs better on databases like moving and stationary target acquisition and recognition against the earlier methods by KNN.

Extraction of latent images from printed media

Science.gov (United States)

Sergeyev, Vladislav; Fedoseev, Victor

2015-12-01

In this paper we propose an automatic technology for extraction of latent images from printed media such as documents, banknotes, financial securities, etc. This technology includes image processing by adaptively constructed Gabor filter bank for obtaining feature images, as well as subsequent stages of feature selection, grouping and multicomponent segmentation. The main advantage of the proposed technique is versatility: it allows to extract latent images made by different texture variations. Experimental results showing performance of the method over another known system for latent image extraction are given.

Gabor Weber Local Descriptor for Bovine Iris Recognition

OpenAIRE

Sun, Shengnan; Zhao, Lindu; Yang, Shicai

2013-01-01

Iris recognition is a robust biometric technology. This paper proposes a novel local descriptor for bovine iris recognition, named Gabor Weber local descriptor (GWLD). We first compute the Gabor magnitude maps for the input bovine iris image, and then calculate the differential excitation and orientation for each pixel over each Gabor magnitude map. After that, we use these differential excitations and orientations to construct the GWLD histogram representation. Finally, histogram intersectio...

On transforms between Gabor frames and wavelet frames

DEFF Research Database (Denmark)

Christensen, Ole; Goh, Say Song

2013-01-01

We describe a procedure that enables us to construct dual pairs of wavelet frames from certain dual pairs of Gabor frames. Applying the construction to Gabor frames generated by appropriate exponential Bsplines gives wavelet frames generated by functions whose Fourier transforms are compactly...... supported splines with geometrically distributed knot sequences. There is also a reverse transform, which yields pairs of dual Gabor frames when applied to certain wavelet frames....

On R-Duals and the Duality Principle in Gabor Analysis

DEFF Research Database (Denmark)

Stoeva, Diana T.; Christensen, Ole

2015-01-01

The concept of R-duals of a frame was introduced by Casazza, Kutyniok and Lammers in 2004, with the motivation to obtain a general version of the duality principle in Gabor analysis. For tight Gabor frames and Gabor Riesz bases the three authors were actually able to show that the duality principle...... these classes coincide with the R-duals by Casazza et al., which is desirable in the sense that the motivating case of tight Gabor frames already is well covered by these R-duals. On the other hand, all the introduced types of R-duals generalize the duality principle for larger classes of Gabor frames than just...

SISTEM VERIFIKASI SIDIK JARI DENGAN METODE PENCOCOKAN BERBASIS BANK GABOR FILTER

Directory of Open Access Journals (Sweden)

A.A. K. Oka Sudana

2009-05-01

Full Text Available Many cases of fraud are exposed where someone, claiming to be someone else attempts to accesssomething. This situation challenges us to create a system that is both reliable and trustworthy to verify someone’sidentity. A biometric system represent an automatic recognition system based on the physiological characteristicsand/or behaviors of the human being. One of these biometric system is fingerprint recognition. Fingerprint verification system is a system to verify a human fingerprint according to the identity which has been claimed. Thusfingerprint image input is compared with the reference fingerprint image which has been kept in a database,according to the given identity. On this research, the Gabor Filter Bank-based Fingerprint Matching Method is used to extract the image features.On application, one of sample image will be matched with one of the database reference image. First, before matching, the sample image features need to be calculate using the aforementioned method. The resulting matchingprocess will find a reference image which has the shortest Euclidean distance with the sample image. This matchingprocess will only succeed if the sample image and the reference image are from the same person. Images used inthis research are fingerprint images with dimension 191 x 191 pixels. This research is looking for the successful rateand the burst time on the verification process. Result of the system testing show that Gabor Filter Bank Method canprovide high enough success level i.e. 95%. The items influence success level are subject to quality of fingerprint image and accuracy to find a reference point/core point, Similarity between query image and reference image is determined by projection distance both of images, and also threshold value is used to decide whether this image isvalid or not.

Duality results for co-compact Gabor systems

DEFF Research Database (Denmark)

Jakobsen, Mads Sielemann; Lemvig, Jakob

2015-01-01

In this paper we give an account of recent developments in the duality theory of Gabor frames. We prove the Wexler-Raz biorthogonality relations and the duality principle for co-compact Gabor systems on second countable, locally compact abelian groups G. Our presentation does not rely on the exis...

Discrete Gabor transform and discrete Zak transform

NARCIS (Netherlands)

Bastiaans, M.J.; Namazi, N.M.; Matthews, K.

1996-01-01

Gabor's expansion of a discrete-time signal into a set of shifted and modulated versions of an elementary signal or synthesis window is introduced, along with the inverse operation, i.e. the Gabor transform, which uses an analysis window that is related to the synthesis window and with the help of

On the discrete Gabor transform and the discrete Zak transform

NARCIS (Netherlands)

Bastiaans, M.J.; Geilen, M.C.W.

1996-01-01

Gabor's expansion of a discrete-time signal into a set of shifted and modulated versions of an elementary signal (or synthesis window) and the inverse operation -- the Gabor transform -- with which Gabor's expansion coefficients can be determined, are introduced. It is shown how, in the case of a

Gabor Analysis for Imaging

DEFF Research Database (Denmark)

Christensen, Ole; Feichtinger, Hans G.; Paukner, Stephan

2015-01-01

, it characterizes a function by its transform over phase space, which is the time–frequency plane (TF-plane) in a musical context or the location–wave-number domain in the context of image processing. Since the transition from the signal domain to the phase space domain introduces an enormous amount of data...... of the generalities relevant for an understanding of Gabor analysis of functions on Rd. We pay special attention to the case d = 2, which is the most important case for image processing and image analysis applications. The chapter is organized as follows. Section 2 presents central tools from functional analysis......, the application of Gabor expansions to image representation is considered in Sect. 6....

On Dual Gabor Frame Pairs Generated by Polynomials

DEFF Research Database (Denmark)

Christensen, Ole; Rae Young, Kim

2010-01-01

We provide explicit constructions of particularly convenient dual pairs of Gabor frames. We prove that arbitrary polynomials restricted to sufficiently large intervals will generate Gabor frames, at least for small modulation parameters. Unfortunately, no similar function can generate a dual Gabo...

AN APPLE GRADING SYSTEM ACCORDING TO EUROPEAN FRUIT QUALITY STANDARDS USING GABOR FILTER AND ARTIFICIAL NEURAL NETWORKS

Directory of Open Access Journals (Sweden)

KEYVAN ASEFPOUR VAKILIAN

2016-04-01

Full Text Available With the advent of applications of machine learning methods in food engineering in recent decades, several intelligent methods have been introduced in fruit grading technology. In this study, an apple grading system is presented using image’s textural features extraction and artificial intelligence. The objective of this study was to simplify the use of Gabor filter in classification of two varieties of apple fruits (Golden Delicious and Red Delicious in four categories according to the European fruit quality standards. Using this filter, neural network classifier was trained for four category grading of the fruits. Two textural parameters were extracted from each obtained image: mean and variance of energy values of obtained image representing image’s luminous intensity and contrast, respectively. Experimental results indicated that the training of extracted features of about 350 fruits enabled the network to classify the test samples with appropriate accuracy. Compared to the state-of-the-art, the proposed grading categories (‘Extra’, ‘Type 1’, ‘Type 2’ and ‘Rejected’ classes achieved acceptable recognition rates of about 89 % and 92 % overall accuracy for Golden Delicious and Red Delicious varieties, respectively. These experimental results show the appropriate application of proposed method in fast grading of apple fruits. Furthermore, proposed feature extraction and network training methods can be used efficiently in online applications.

Gabor frames on locally compact abelian groups and related topics

DEFF Research Database (Denmark)

Jakobsen, Mads Sielemann

This thesis consists of four papers. The first one introduces generalized translation invariant systems and considers their frame properties, the second and third paper give new results on the theory of Gabor frames, and the fourth is a review paper with proofs and new results on the Feichtinger......- and shearlet-type and for (generalized) shift-invariant systems and their continuous formulations. This thesis advances the theory of both separable and non-separable, discrete, semicontinuous and continuous Gabor systems. In particular, the well established structure theory for separable lattice Gabor frames...... and Gabor Riesz bases. The theory of GTI systems and Gabor frames in this thesis is developed and presented in the setting of locally compact abelian groups, however, even in the euclidean setting the results given here improve the existing theory. Finally, the thesis contains a review paper with proofs...

Gabor Weber Local Descriptor for Bovine Iris Recognition

Directory of Open Access Journals (Sweden)

Shengnan Sun

2013-01-01

Full Text Available Iris recognition is a robust biometric technology. This paper proposes a novel local descriptor for bovine iris recognition, named Gabor Weber local descriptor (GWLD. We first compute the Gabor magnitude maps for the input bovine iris image, and then calculate the differential excitation and orientation for each pixel over each Gabor magnitude map. After that, we use these differential excitations and orientations to construct the GWLD histogram representation. Finally, histogram intersection is adopted to measure the similarity between different GWLD histograms. The experimental results on the SEU bovine iris database verify the representation power of our proposed local descriptor.

Symmetric, discrete fractional splines and Gabor systems

DEFF Research Database (Denmark)

Søndergaard, Peter Lempel

2006-01-01

In this paper we consider fractional splines as windows for Gabor frames. We introduce two new types of symmetric, fractional splines in addition to one found by Unser and Blu. For the finite, discrete case we present two families of splines: One is created by sampling and periodizing the continu......In this paper we consider fractional splines as windows for Gabor frames. We introduce two new types of symmetric, fractional splines in addition to one found by Unser and Blu. For the finite, discrete case we present two families of splines: One is created by sampling and periodizing...... the continuous splines, and one is a truly finite, discrete construction. We discuss the properties of these splines and their usefulness as windows for Gabor frames and Wilson bases....

Transient space-time surface waves characterization using Gabor analysis

Energy Technology Data Exchange (ETDEWEB)

Martinez, L; Wilkie-Chancellier, N; Caplain, E [Universite de Cergy Pontoise, ENS Cachan, UMR CNRS 8029, Laboratoire Systemes et Applications des Techniques de l' Information et de l' Energie (SATIE), 5 mail Gay-Lussac, F 9500 Cergy-Pontoise (France); Glorieux, C; Sarens, B, E-mail: nicolas.wilkie-chancellier@u-cergy.f [Katholieke Universiteit Leuven, Laboratorium voor Akoestiek en Thermische Fysica (LATF), Celestijnenlaan 200D, B-3001 Leuven (Belgium)

2009-11-01

Laser ultrasonics allow the observation of transient surface waves along their propagation media and their interaction with encountered objects like cracks, holes, borders. In order to characterize and localize these transient aspects in the Space-Time-Wave number-Frequency domains, the 1D, 2D and 3D Gabor transforms are presented. The Gabor transform enables the identification of several properties of the local wavefronts such as their shape, wavelength, frequency, attenuation, group velocity and the full conversion sequence along propagation. The ability of local properties identification by Gabor transform is illustrated by two experimental studies: Lamb waves generated by an annular source on a circular quartz and Lamb wave interaction with a fluid droplet. In both cases, results obtained with Gabor transform enable ones to identify the observed local waves.

Gabor's signal expansion and the Zak transform with non-critical sampling

NARCIS (Netherlands)

Bastiaans, M.J.; Geilen, M.C.W.; Boashash, B.; HHrle, N.; Zoubir, A.M.

1996-01-01

Gabor's expansion of a signal into a set of shifted and modulated versions of a synthesis window is introduced, along with the inverse operation, i.e. the Gabor transform, which uses an analysis window with the help of which Gabor's expansion coefficients can be determined. The Zak transform is

Face Recognition using Gabor Filters

Directory of Open Access Journals (Sweden)

Sajjad MOHSIN

2011-01-01

Full Text Available An Elastic Bunch Graph Map (EBGM algorithm is being proposed in this research paper that successfully implements face recognition using Gabor filters. The proposed system applies 40 different Gabor filters on an image. As aresult of which 40 images with different angles and orientation are received. Next, maximum intensity points in each filtered image are calculated and mark them as Fiducial points. The system reduces these points in accordance to distance between them. The next step is calculating the distances between the reduced points using distance formula. At last, the distances are compared with database. If match occurs, it means that the image is recognized.

Self-Invertible 2D Log-Gabor Wavelets

Czech Academy of Sciences Publication Activity Database

Fischer, S.; Šroubek, Filip; Perrinet, L.; Redondo, R.; Cristóbal, G.

2007-01-01

Roč. 75, č. 2 (2007), s. 231-246 ISSN 0920-5691 R&D Projects: GA ČR GA202/05/0242 Grant - others:GA MŠk(CZ) 2004CZ0009 Institutional research plan: CEZ:AV0Z10750506 Keywords : wavelet transforms * log-Gabor filters * oriented high-pass filters * image denoising Subject RIV: JD - Computer Applications, Robotics Impact factor: 3.381, year: 2007 http://staff.utia.cas.cz/sroubekf/papers/gabor_07.pdf

Gabor Frames in ℓ2(Z) and Linear Dependence

DEFF Research Database (Denmark)

Christensen, Ole; Hasannasab, Marzieh

2017-01-01

We prove that an overcomplete Gabor frame in (Formula presented.) generated by a finitely supported sequence is always linearly dependent. This is a particular case of a general result about linear dependence versus independence for Gabor systems in (Formula presented.) with modulation parameter ...

a Signal-Tuned Gabor Transform with Application to Eeg Analysis

Science.gov (United States)

Torreão, José R. A.; Victer, Silvia M. C.; Fernandes, João L.

2013-04-01

We introduce a time-frequency transform based on Gabor functions whose parameters are given by the Fourier transform of the analyzed signal. At any given frequency, the width and the phase of the Gabor function are obtained, respectively, from the magnitude and the phase of the signal's corresponding Fourier component, yielding an analyzing kernel which is a representation of the signal's content at that particular frequency. The resulting Gabor transform tunes itself to the input signal, allowing the accurate detection of time and frequency events, even in situations where the traditional Gabor and S-transform approaches tend to fail. This is the case, for instance, when considering the time-frequency representation of electroencephalogram traces (EEG) of epileptic subjects, as illustrated by the experimental study presented here.

Stochastic Gabor reflectivity and acoustic impedance inversion

Science.gov (United States)

Hariri Naghadeh, Diako; Morley, Christopher Keith; Ferguson, Angus John

2018-02-01

To delineate subsurface lithology to estimate petrophysical properties of a reservoir, it is possible to use acoustic impedance (AI) which is the result of seismic inversion. To change amplitude to AI, removal of wavelet effects from the seismic signal in order to get a reflection series, and subsequently transforming those reflections to AI, is vital. To carry out seismic inversion correctly it is important to not assume that the seismic signal is stationary. However, all stationary deconvolution methods are designed following that assumption. To increase temporal resolution and interpretation ability, amplitude compensation and phase correction are inevitable. Those are pitfalls of stationary reflectivity inversion. Although stationary reflectivity inversion methods are trying to estimate reflectivity series, because of incorrect assumptions their estimations will not be correct, but may be useful. Trying to convert those reflection series to AI, also merging with the low frequency initial model, can help us. The aim of this study was to apply non-stationary deconvolution to eliminate time variant wavelet effects from the signal and to convert the estimated reflection series to the absolute AI by getting bias from well logs. To carry out this aim, stochastic Gabor inversion in the time domain was used. The Gabor transform derived the signal’s time-frequency analysis and estimated wavelet properties from different windows. Dealing with different time windows gave an ability to create a time-variant kernel matrix, which was used to remove matrix effects from seismic data. The result was a reflection series that does not follow the stationary assumption. The subsequent step was to convert those reflections to AI using well information. Synthetic and real data sets were used to show the ability of the introduced method. The results highlight that the time cost to get seismic inversion is negligible related to general Gabor inversion in the frequency domain. Also

An Efficient Algorithm for the Discrete Gabor Transform using full length Windows

DEFF Research Database (Denmark)

Søndergaard, Peter Lempel

2007-01-01

This paper extends the efficient factorization of the Gabor frame operator developed by Strohmer in [1] to the Gabor analysis/synthesis operator. This provides a fast method for computing the discrete Gabor transform (DGT) and several algorithms associated with it. The algorithm is used...

On the windowed Fourier transform as an interpolation of the Gabor transform

NARCIS (Netherlands)

Bastiaans, M.J.; Prochßzka, A.; Uhlør, J.; Sovka, P.

1997-01-01

The windowed Fourier transform and its sampled version - the Gabor transform - are introduced. With the help of Gabor's signal expansion, an interpolation function is derived with which the windowed Fourier transform can be constructed from the Gabor transform. Using the Zak transform, it is shown

Co-compact Gabor Systems on Locally Compact Abelian Groups

DEFF Research Database (Denmark)

Jakobsen, Mads Sielemann; Lemvig, Jakob

2016-01-01

In this work we extend classical structure and duality results in Gabor analysis on the euclidean space to the setting of second countable locally compact abelian (LCA) groups. We formulate the concept of rationally oversampling of Gabor systems in an LCA group and prove corresponding characteriz...

Face-iris multimodal biometric scheme based on feature level fusion

Science.gov (United States)

Huo, Guang; Liu, Yuanning; Zhu, Xiaodong; Dong, Hongxing; He, Fei

2015-11-01

Unlike score level fusion, feature level fusion demands all the features extracted from unimodal traits with high distinguishability, as well as homogeneity and compatibility, which is difficult to achieve. Therefore, most multimodal biometric research focuses on score level fusion, whereas few investigate feature level fusion. We propose a face-iris recognition method based on feature level fusion. We build a special two-dimensional-Gabor filter bank to extract local texture features from face and iris images, and then transform them by histogram statistics into an energy-orientation variance histogram feature with lower dimensions and higher distinguishability. Finally, through a fusion-recognition strategy based on principal components analysis and support vector machine (FRSPS), feature level fusion and one-to-n identification are accomplished. The experimental results demonstrate that this method can not only effectively extract face and iris features but also provide higher recognition accuracy. Compared with some state-of-the-art fusion methods, the proposed method has a significant performance advantage.

Feature Vector Construction Method for IRIS Recognition

Science.gov (United States)

Odinokikh, G.; Fartukov, A.; Korobkin, M.; Yoo, J.

2017-05-01

One of the basic stages of iris recognition pipeline is iris feature vector construction procedure. The procedure represents the extraction of iris texture information relevant to its subsequent comparison. Thorough investigation of feature vectors obtained from iris showed that not all the vector elements are equally relevant. There are two characteristics which determine the vector element utility: fragility and discriminability. Conventional iris feature extraction methods consider the concept of fragility as the feature vector instability without respect to the nature of such instability appearance. This work separates sources of the instability into natural and encodinginduced which helps deeply investigate each source of instability independently. According to the separation concept, a novel approach of iris feature vector construction is proposed. The approach consists of two steps: iris feature extraction using Gabor filtering with optimal parameters and quantization with separated preliminary optimized fragility thresholds. The proposed method has been tested on two different datasets of iris images captured under changing environmental conditions. The testing results show that the proposed method surpasses all the methods considered as a prior art by recognition accuracy on both datasets.

THE IDENTIFICATION OF EAR PRINTS USING COMPLEX GABOR FILTERS

Directory of Open Access Journals (Sweden)

Alexander A S Gunawan

2012-05-01

Full Text Available Biometrics is a method used to recognize humans based on one or a few characteristicsphysical or behavioral traits that are unique such as DNA, face, fingerprints, gait, iris, palm, retina,signature and sound. Although the facts that ear prints are found in 15% of crime scenes, ear printsresearch has been very limited since the success of fingerprints modality. The advantage of the useof ear prints, as forensic evidence, are it relatively unchanged due to increased age and have fewervariations than faces with expression variation and orientation. In this research, complex Gaborfilters is used to extract the ear prints feature based on texture segmentation. Principal componentanalysis (PCA is then used for dimensionality-reduction where variation in the dataset ispreserved. The classification is done in a lower dimension space defined by principal componentsbased on Euclidean distance. In experiments, it is used left and right ear prints of ten respondentsand in average, the successful recognition rate is 78%. Based on the experiment results, it isconcluded that ear prints is suitable as forensic evidence mainly when combined with otherbiometric modalities.Keywords: Biometrics; Ear prints; Complex Gabor filters; Principal component analysis;Euclidean distance

Gabor lenses

International Nuclear Information System (INIS)

Mobley, R.M.; Gamml, G.; Maschke, A.W.

1979-01-01

Stable operation of Gabor lenses has been reported by at least three experimental groups. At Brookhaven, several lens designs have been tried since February, 1978 with very good results. The lens concept is simple, operation is less complicated than anticipated, and the focussing strengths attainable make them very attractive alternatives to magnetic focussing for heavy ion beams at low energies. Results obtained with five different configurations are presented. The lenses work well, concern is now with fine details of their beam-optical performance

Gabor Wave Packet Method to Solve Plasma Wave Equations

International Nuclear Information System (INIS)

Pletzer, A.; Phillips, C.K.; Smithe, D.N.

2003-01-01

A numerical method for solving plasma wave equations arising in the context of mode conversion between the fast magnetosonic and the slow (e.g ion Bernstein) wave is presented. The numerical algorithm relies on the expansion of the solution in Gaussian wave packets known as Gabor functions, which have good resolution properties in both real and Fourier space. The wave packets are ideally suited to capture both the large and small wavelength features that characterize mode conversion problems. The accuracy of the scheme is compared with a standard finite element approach

Parametric classification of handvein patterns based on texture features

Science.gov (United States)

Al Mahafzah, Harbi; Imran, Mohammad; Supreetha Gowda H., D.

2018-04-01

In this paper, we have developed Biometric recognition system adopting hand based modality Handvein,which has the unique pattern for each individual and it is impossible to counterfeit and fabricate as it is an internal feature. We have opted in choosing feature extraction algorithms such as LBP-visual descriptor, LPQ-blur insensitive texture operator, Log-Gabor-Texture descriptor. We have chosen well known classifiers such as KNN and SVM for classification. We have experimented and tabulated results of single algorithm recognition rate for Handvein under different distance measures and kernel options. The feature level fusion is carried out which increased the performance level.

Gabor fusion master slave optical coherence tomography

DEFF Research Database (Denmark)

Cernat, Ramona; Bradu, Adrian; Israelsen, Niels Møller

2017-01-01

This paper describes the application of the Gabor filtering protocol to a Master/Slave (MS) swept source optical coherence tomography (SS)-OCT system at 1300 nm. The MS-OCT system delivers information from selected depths, a property that allows operation similar to that of a time domain OCT system......, where dynamic focusing is possible. The Gabor filtering processing following collection of multiple data from different focus positions is different from that utilized by a conventional swept source OCT system using a Fast Fourier transform (FFT) to produce an A-scan. Instead of selecting the bright...

Rectangular-to-quincunx Gabor lattice conversion via fractional Fourier transformation

NARCIS (Netherlands)

Bastiaans, M.J.; Leest, van A.J.

1998-01-01

Transformations of Gabor lattices are associated with operations on the window functions that arise in Gabor theory. In particular it is shown that transformation from a rectangular to a quincunx lattice can be associated with fractional Fourier transformation. Since a Gaussian function, which plays

Properties of an improved Gabor wavelet transform and its applications to seismic signal processing and interpretation

Science.gov (United States)

Ji, Zhan-Huai; Yan, Sheng-Gang

2017-12-01

This paper presents an analytical study of the complete transform of improved Gabor wavelets (IGWs), and discusses its application to the processing and interpretation of seismic signals. The complete Gabor wavelet transform has the following properties. First, unlike the conventional transform, the improved Gabor wavelet transform (IGWT) maps time domain signals to the time-frequency domain instead of the time-scale domain. Second, the IGW's dominant frequency is fixed, so the transform can perform signal frequency division, where the dominant frequency components of the extracted sub-band signal carry essentially the same information as the corresponding components of the original signal, and the subband signal bandwidth can be regulated effectively by the transform's resolution factor. Third, a time-frequency filter consisting of an IGWT and its inverse transform can accurately locate target areas in the time-frequency field and perform filtering in a given time-frequency range. The complete IGW transform's properties are investigated using simulation experiments and test cases, showing positive results for seismic signal processing and interpretation, such as enhancing seismic signal resolution, permitting signal frequency division, and allowing small faults to be identified.

On the non-orthogonal sampling scheme for Gabor's signal expansion

NARCIS (Netherlands)

Bastiaans, M.J.; Leest, van A.J.; Veen, J.P.

2000-01-01

Gabor's signal expansion and the Gabor transform are formulated on a non-orthogonal time-frequency lattice instead of on the traditional rectangular lattice [1,2]. The reason for doing so is that a non-orthogonal sampling geometry might be better adapted to the form of the window functions (in the

Approximately dual frames in Hilbert spaces and applications to Gabor frames

DEFF Research Database (Denmark)

Christensen, Ole; Laugesen, Richard S.

2011-01-01

constructed via perturbation theory. An alternative bound is derived for the rich class of Gabor frames, by using the Walnut representation of the frame operator to estimate the deviation from equality in the duality conditions. To illustrate these results, we construct explicit approximate duals of Gabor...

Feature Level Two -Dimensional Arrays Based Fusion in the Personal Authentication system using Physiological Biometric traits

Directory of Open Access Journals (Sweden)

Jerusalin Carol .J

Full Text Available ABSTRACT The fingerprint, knuckle print and the retina are used to authenticate a person accurately because of the permanence in the features. These three biometric traits are fused for better security. The fingerprint and knuckle print images are pre-processed by morphological techniques and the features are extracted from the normalized image using gabor filter. The retinal image is converted to gray image and pre-processing is done using top hat and bottom hat filtering. Blood vessels are segmented and the features are extracted by locating the optic disk as the centre point. The extracted features from the fingerprint, knuckle print and the retina are fused together as one template and stored in the data base for authentication purpose, thus reducing the space and time complexity.

Finger-vein and fingerprint recognition based on a feature-level fusion method

Science.gov (United States)

Yang, Jinfeng; Hong, Bofeng

2013-07-01

Multimodal biometrics based on the finger identification is a hot topic in recent years. In this paper, a novel fingerprint-vein based biometric method is proposed to improve the reliability and accuracy of the finger recognition system. First, the second order steerable filters are used here to enhance and extract the minutiae features of the fingerprint (FP) and finger-vein (FV). Second, the texture features of fingerprint and finger-vein are extracted by a bank of Gabor filter. Third, a new triangle-region fusion method is proposed to integrate all the fingerprint and finger-vein features in feature-level. Thus, the fusion features contain both the finger texture-information and the minutiae triangular geometry structure. Finally, experimental results performed on the self-constructed finger-vein and fingerprint databases are shown that the proposed method is reliable and precise in personal identification.

From the rectangular to the quincunx Gabor lattice via fractional Fourier transformation

NARCIS (Netherlands)

Bastiaans, M.J.; Leest, van A.J.

1998-01-01

Transformations of Gabor lattices have been associated with operations on the window functions that arise in Gabor theory. In particular it has been shown that transformation from a rectangular to a quincunx lattice can be associated with fractional Fourier transformation. Since a Gaussian function,

Gabor's signal expansion on a quincunx lattice and the modified Zak transform

NARCIS (Netherlands)

Leest, van A.J.; Bastiaans, M.J.

1999-01-01

Gabor's expansion of a signal on a quincunx lattice with oversampling by a rational factor is presented for continuous-time signals. It is shown how a modified Zak transform instead of the ordinary Zak transform can be helpful in determining Gabor's signal expansion coefficients and how it can be

Identifying city PV roof resource based on Gabor filter

Science.gov (United States)

Ruhang, Xu; Zhilin, Liu; Yong, Huang; Xiaoyu, Zhang

2017-06-01

To identify a city’s PV roof resources, the area and ownership distribution of residential buildings in an urban district should be assessed. To achieve this assessment, remote sensing data analysing is a promising approach. Urban building roof area estimation is a major topic for remote sensing image information extraction. There are normally three ways to solve this problem. The first way is pixel-based analysis, which is based on mathematical morphology or statistical methods; the second way is object-based analysis, which is able to combine semantic information and expert knowledge; the third way is signal-processing view method. This paper presented a Gabor filter based method. This result shows that the method is fast and with proper accuracy.

A short introduction to frames, Gabor systems, and wavelet systems

DEFF Research Database (Denmark)

Christensen, Ole

2014-01-01

In this article we present a short survey of frame theory in Hilbert spaces. We discuss Gabor frames and wavelet frames, and a recent transform that allows to move results from one setting into the other and vice versa.......In this article we present a short survey of frame theory in Hilbert spaces. We discuss Gabor frames and wavelet frames, and a recent transform that allows to move results from one setting into the other and vice versa....

Facial Expression Recognition from Video Sequences Based on Spatial-Temporal Motion Local Binary Pattern and Gabor Multiorientation Fusion Histogram

Directory of Open Access Journals (Sweden)

Lei Zhao

2017-01-01

Full Text Available This paper proposes novel framework for facial expressions analysis using dynamic and static information in video sequences. First, based on incremental formulation, discriminative deformable face alignment method is adapted to locate facial points to correct in-plane head rotation and break up facial region from background. Then, spatial-temporal motion local binary pattern (LBP feature is extracted and integrated with Gabor multiorientation fusion histogram to give descriptors, which reflect static and dynamic texture information of facial expressions. Finally, a one-versus-one strategy based multiclass support vector machine (SVM classifier is applied to classify facial expressions. Experiments on Cohn-Kanade (CK + facial expression dataset illustrate that integrated framework outperforms methods using single descriptors. Compared with other state-of-the-art methods on CK+, MMI, and Oulu-CASIA VIS datasets, our proposed framework performs better.

Fast parallel approach for 2-D DHT-based real-valued discrete Gabor transform.

Science.gov (United States)

Tao, Liang; Kwan, Hon Keung

2009-12-01

Two-dimensional fast Gabor transform algorithms are useful for real-time applications due to the high computational complexity of the traditional 2-D complex-valued discrete Gabor transform (CDGT). This paper presents two block time-recursive algorithms for 2-D DHT-based real-valued discrete Gabor transform (RDGT) and its inverse transform and develops a fast parallel approach for the implementation of the two algorithms. The computational complexity of the proposed parallel approach is analyzed and compared with that of the existing 2-D CDGT algorithms. The results indicate that the proposed parallel approach is attractive for real time image processing.

Characterization and perturbation of Gabor frame sequences with rational parameters

DEFF Research Database (Denmark)

Bownik, M.; Christensen, Ole

2007-01-01

Let A c L-2(R) be at most countable, and E N. We characterize various frame-properties for Gabor systems of the form G(l. p/q . A) = {e(2 pi imx) g (x-np/q) : m, n epsilon Z, g epsilon A} in terms of the corresponding frame properties for the row vectors in the Zibulski-Zeevi matrix. This extends...... work by [Ron and Shen, Weyl-Heisenherg systenis and Riesz bases in L-2(R-d). Duke Math. J. 89 (1997) 237-282]. who considered the case where A is finite. As a consequence of the results, we obtain results concerning stability of Gabor frames under perturbation of the generators. We also introduce...... the concept of rigid frame sequences, which have the property that all Sufficiently small perturbations with a lower frame bound above some threshold value, automatically generate the same closed linear span. Finally, we characterize rigid Gabor frame sequences in terms of their Zibulski-Zeevi matrix....

Experimental studies of stable confined electron clouds using Gabor lenses

CERN Document Server

Meusel, O.; Glaeser, B.; Schulte, K.

2013-04-22

Based on the idea of D. Gabor [1] space charge lenses are under investigation to be a powerful focussing device for intense ion beams. A stable confined electron column is used to provide strong radially symmetric electrostatic focussing, e.g. for positively charged ion beams. The advantages of Gabor lenses are a mass independent focussing strength, space charge compensation of the ion beam and reduced magnetic or electric fields compared to conventional focussing devices. Collective phenomena of the electron cloud result in aberrations and emittance growth of the ion beam. The knowledge of the behaviour of the electron cloud prevents a decrease of the beam brilliance. Numerical models developed to describe the electron confinement and dynamics within a Gabor lens help to understand the interaction of the ion beam with the electron column and show the causes of non-neutral plasma instabilities. The diagnosis of the electron cloud properties helps to evaluate the numerical models and to investigate the influen...

On some Hermite series identities and their applications to Gabor analysis

DEFF Research Database (Denmark)

Lemvig, Jakob

2016-01-01

We prove some infinite series identities for the Hermite functions. From these identities we disprove the Gabor frame set conjecture for Hermite functions of order (Formula presented.) and (Formula presented.) for (Formula presented.). The results hold not only for Hermite functions, but for two ...... large classes of eigenfunctions of the Fourier transform associated with the eigenvalues (Formula presented.) and i, and the results indicate that the Gabor frame set of all such functions must have a rather complicated structure....

Secondary iris recognition method based on local energy-orientation feature

Science.gov (United States)

Huo, Guang; Liu, Yuanning; Zhu, Xiaodong; Dong, Hongxing

2015-01-01

This paper proposes a secondary iris recognition based on local features. The application of the energy-orientation feature (EOF) by two-dimensional Gabor filter to the extraction of the iris goes before the first recognition by the threshold of similarity, which sets the whole iris database into two categories-a correctly recognized class and a class to be recognized. Therefore, the former are accepted and the latter are transformed by histogram to achieve an energy-orientation histogram feature (EOHF), which is followed by a second recognition with the chi-square distance. The experiment has proved that the proposed method, because of its higher correct recognition rate, could be designated as the most efficient and effective among its companion studies in iris recognition algorithms.

A novel computer-aided diagnosis system for breast MRI based on feature selection and ensemble learning.

Science.gov (United States)

Lu, Wei; Li, Zhe; Chu, Jinghui

2017-04-01

Breast cancer is a common cancer among women. With the development of modern medical science and information technology, medical imaging techniques have an increasingly important role in the early detection and diagnosis of breast cancer. In this paper, we propose an automated computer-aided diagnosis (CADx) framework for magnetic resonance imaging (MRI). The scheme consists of an ensemble of several machine learning-based techniques, including ensemble under-sampling (EUS) for imbalanced data processing, the Relief algorithm for feature selection, the subspace method for providing data diversity, and Adaboost for improving the performance of base classifiers. We extracted morphological, various texture, and Gabor features. To clarify the feature subsets' physical meaning, subspaces are built by combining morphological features with each kind of texture or Gabor feature. We tested our proposal using a manually segmented Region of Interest (ROI) data set, which contains 438 images of malignant tumors and 1898 images of normal tissues or benign tumors. Our proposal achieves an area under the ROC curve (AUC) value of 0.9617, which outperforms most other state-of-the-art breast MRI CADx systems. Compared with other methods, our proposal significantly reduces the false-positive classification rate. Copyright © 2017 Elsevier Ltd. All rights reserved.

Local gradient Gabor pattern (LGGP) with applications in face recognition, cross-spectral matching, and soft biometrics

Science.gov (United States)

Chen, Cunjian; Ross, Arun

2013-05-01

Researchers in face recognition have been using Gabor filters for image representation due to their robustness to complex variations in expression and illumination. Numerous methods have been proposed to model the output of filter responses by employing either local or global descriptors. In this work, we propose a novel but simple approach for encoding Gradient information on Gabor-transformed images to represent the face, which can be used for identity, gender and ethnicity assessment. Extensive experiments on the standard face benchmark FERET (Visible versus Visible), as well as the heterogeneous face dataset HFB (Near-infrared versus Visible), suggest that the matching performance due to the proposed descriptor is comparable against state-of-the-art descriptor-based approaches in face recognition applications. Furthermore, the same feature set is used in the framework of a Collaborative Representation Classification (CRC) scheme for deducing soft biometric traits such as gender and ethnicity from face images in the AR, Morph and CAS-PEAL databases.

Iris recognition based on key image feature extraction.

Science.gov (United States)

Ren, X; Tian, Q; Zhang, J; Wu, S; Zeng, Y

2008-01-01

In iris recognition, feature extraction can be influenced by factors such as illumination and contrast, and thus the features extracted may be unreliable, which can cause a high rate of false results in iris pattern recognition. In order to obtain stable features, an algorithm was proposed in this paper to extract key features of a pattern from multiple images. The proposed algorithm built an iris feature template by extracting key features and performed iris identity enrolment. Simulation results showed that the selected key features have high recognition accuracy on the CASIA Iris Set, where both contrast and illumination variance exist.

IDENTIFIKASI IRIS MATA MENGGUNAKAN TAPIS GABOR WAVELET DAN JARINGAN SYARAF TIRUAN LEARNING VECTOR QUANTIZATION (LVQ

Directory of Open Access Journals (Sweden)

Budi Setiyono

2012-02-01

Full Text Available Biometric represents the human identification method development using natural characteristic of humanbeing as its bases. Every iris has the detail and unique texture, even differ between right and left eye.Theeye iris identification process in this research are data acquisition, early processing, feature exctractionand classification. Algorithm used for classification of texture slice the eye is Gabor wavelet filtering, andclassification process of slice the eye texture will be used by a Artificial Neural Network LVQ. Recognitionthe value of feature vektor in each iris obtained from to the number of right recognition value or thepercentage of right one. The best recognition percentage is 87,5 %.

B-Spline Approximations of the Gaussian, their Gabor Frame Properties, and Approximately Dual Frames

DEFF Research Database (Denmark)

Christensen, Ole; Kim, Hong Oh; Kim, Rae Young

2017-01-01

We prove that Gabor systems generated by certain scaled B-splines can be considered as perturbations of the Gabor systems generated by the Gaussian, with a deviation within an arbitrary small tolerance whenever the order N of the B-spline is sufficiently large. As a consequence we show that for a...

Audio feature extraction using probability distribution function

Science.gov (United States)

Suhaib, A.; Wan, Khairunizam; Aziz, Azri A.; Hazry, D.; Razlan, Zuradzman M.; Shahriman A., B.

2015-05-01

Voice recognition has been one of the popular applications in robotic field. It is also known to be recently used for biometric and multimedia information retrieval system. This technology is attained from successive research on audio feature extraction analysis. Probability Distribution Function (PDF) is a statistical method which is usually used as one of the processes in complex feature extraction methods such as GMM and PCA. In this paper, a new method for audio feature extraction is proposed which is by using only PDF as a feature extraction method itself for speech analysis purpose. Certain pre-processing techniques are performed in prior to the proposed feature extraction method. Subsequently, the PDF result values for each frame of sampled voice signals obtained from certain numbers of individuals are plotted. From the experimental results obtained, it can be seen visually from the plotted data that each individuals' voice has comparable PDF values and shapes.

Kernel Learning of Histogram of Local Gabor Phase Patterns for Face Recognition

Directory of Open Access Journals (Sweden)

Bineng Zhong

2008-06-01

Full Text Available This paper proposes a new face recognition method, named kernel learning of histogram of local Gabor phase pattern (K-HLGPP, which is based on Daugman’s method for iris recognition and the local XOR pattern (LXP operator. Unlike traditional Gabor usage exploiting the magnitude part in face recognition, we encode the Gabor phase information for face classification by the quadrant bit coding (QBC method. Two schemes are proposed for face recognition. One is based on the nearest-neighbor classifier with chi-square as the similarity measurement, and the other makes kernel discriminant analysis for HLGPP (K-HLGPP using histogram intersection and Gaussian-weighted chi-square kernels. The comparative experiments show that K-HLGPP achieves a higher recognition rate than other well-known face recognition systems on the large-scale standard FERET, FERET200, and CAS-PEAL-R1 databases.

Effective Approach to Calculate Analysis Window in Infinite Discrete Gabor Transform

Directory of Open Access Journals (Sweden)

Rui Li

2018-01-01

Full Text Available The long-periodic/infinite discrete Gabor transform (DGT is more effective than the periodic/finite one in many applications. In this paper, a fast and effective approach is presented to efficiently compute the Gabor analysis window for arbitrary given synthesis window in DGT of long-periodic/infinite sequences, in which the new orthogonality constraint between analysis window and synthesis window in DGT for long-periodic/infinite sequences is derived and proved to be equivalent to the completeness condition of the long-periodic/infinite DGT. By using the property of delta function, the original orthogonality can be expressed as a certain number of linear equation sets in both the critical sampling case and the oversampling case, which can be fast and efficiently calculated by fast discrete Fourier transform (FFT. The computational complexity of the proposed approach is analyzed and compared with that of the existing canonical algorithms. The numerical results indicate that the proposed approach is efficient and fast for computing Gabor analysis window in both the critical sampling case and the oversampling case in comparison to existing algorithms.

A Phase Vocoder Based on Nonstationary Gabor Frames

DEFF Research Database (Denmark)

Ottosen, Emil Solsbæk; Dörfler, Monika

2017-01-01

We propose a new algorithm for time stretching music signals based on the theory of nonstationary Gabor frames (NSGFs). The algorithm extends the techniques of the classical phase vocoder (PV) by incorporating adaptive timefrequency (TF) representations and adaptive phase locking. The adaptive TF...

Iris recognition using possibilistic fuzzy matching on local features.

Science.gov (United States)

Tsai, Chung-Chih; Lin, Heng-Yi; Taur, Jinshiuh; Tao, Chin-Wang

2012-02-01

In this paper, we propose a novel possibilistic fuzzy matching strategy with invariant properties, which can provide a robust and effective matching scheme for two sets of iris feature points. In addition, the nonlinear normalization model is adopted to provide more accurate position before matching. Moreover, an effective iris segmentation method is proposed to refine the detected inner and outer boundaries to smooth curves. For feature extraction, the Gabor filters are adopted to detect the local feature points from the segmented iris image in the Cartesian coordinate system and to generate a rotation-invariant descriptor for each detected point. After that, the proposed matching algorithm is used to compute a similarity score for two sets of feature points from a pair of iris images. The experimental results show that the performance of our system is better than those of the systems based on the local features and is comparable to those of the typical systems.

Text feature extraction based on deep learning: a review.

Science.gov (United States)

Liang, Hong; Sun, Xiao; Sun, Yunlei; Gao, Yuan

2017-01-01

Selection of text feature item is a basic and important matter for text mining and information retrieval. Traditional methods of feature extraction require handcrafted features. To hand-design, an effective feature is a lengthy process, but aiming at new applications, deep learning enables to acquire new effective feature representation from training data. As a new feature extraction method, deep learning has made achievements in text mining. The major difference between deep learning and conventional methods is that deep learning automatically learns features from big data, instead of adopting handcrafted features, which mainly depends on priori knowledge of designers and is highly impossible to take the advantage of big data. Deep learning can automatically learn feature representation from big data, including millions of parameters. This thesis outlines the common methods used in text feature extraction first, and then expands frequently used deep learning methods in text feature extraction and its applications, and forecasts the application of deep learning in feature extraction.

Identification of everyday objects on the basis of Gaborized outline versions.

Science.gov (United States)

Sassi, Michaël; Vancleef, Kathleen; Machilsen, Bart; Panis, Sven; Wagemans, Johan

2010-01-01

Using outlines derived from a widely used set of line drawings, we created stimuli geared towards the investigation of contour integration and texture segmentation using shapes of everyday objects. Each stimulus consisted of Gabor elements positioned and oriented curvilinearly along the outline of an object, embedded within a larger Gabor array of homogeneous density. We created six versions of the resulting Gaborized outline stimuli by varying the orientations of elements inside and outside the outline. Data from two experiments, in which participants attempted to identify the objects in the stimuli, provide norms for identifiability and name agreement, and show differences in identifiability between stimulus versions. While there was substantial variability between the individual objects in our stimulus set, further analyses suggest a number of stimulus properties which are generally predictive of identification performance. The stimuli and the accompanying normative data, both available on our website (http://www.gestaltrevision.be/sources/gaboroutlines), provide a useful tool to further investigate contour integration and texture segmentation in both normal and clinical populations, especially when top-down influences on these processes, such as the role of prior knowledge of familiar objects, are of main interest.

An Improved Iris Recognition Algorithm Based on Hybrid Feature and ELM

Science.gov (United States)

Wang, Juan

2018-03-01

The iris image is easily polluted by noise and uneven light. This paper proposed an improved extreme learning machine (ELM) based iris recognition algorithm with hybrid feature. 2D-Gabor filters and GLCM is employed to generate a multi-granularity hybrid feature vector. 2D-Gabor filter and GLCM feature work for capturing low-intermediate frequency and high frequency texture information, respectively. Finally, we utilize extreme learning machine for iris recognition. Experimental results reveal our proposed ELM based multi-granularity iris recognition algorithm (ELM-MGIR) has higher accuracy of 99.86%, and lower EER of 0.12% under the premise of real-time performance. The proposed ELM-MGIR algorithm outperforms other mainstream iris recognition algorithms.

AUTOMATED DETECTION OF MITOTIC FIGURES IN BREAST CANCER HISTOPATHOLOGY IMAGES USING GABOR FEATURES AND DEEP NEURAL NETWORKS

Directory of Open Access Journals (Sweden)

Maqlin Paramanandam

2016-11-01

Full Text Available The count of mitotic figures in Breast cancer histopathology slides is the most significant independent prognostic factor enabling determination of the proliferative activity of the tumor. In spite of the strict protocols followed, the mitotic counting activity suffers from subjectivity and considerable amount of observer variability despite being a laborious task. Interest in automated detection of mitotic figures has been rekindled with the advent of Whole Slide Scanners. Subsequently mitotic detection grand challenge contests have been held in recent years and several research methodologies developed by their participants. This paper proposes an efficient mitotic detection methodology for Hematoxylin and Eosin stained Breast cancer Histopathology Images using Gabor features and a Deep Belief Network- Deep Neural Network architecture (DBN-DNN. The proposed method has been evaluated on breast histopathology images from the publicly available dataset from MITOS contest held at the ICPR 2012 conference. It contains 226 mitoses annotated on 35 HPFs by several pathologists and 15 testing HPFs, yielding an F-measure of 0.74. In addition the said methodology was also tested on 3 slides from the MITOSIS- ATYPIA grand challenge held at the ICPR 2014 conference, an extension of MITOS containing 749 mitoses annotated on 1200 HPFs, by pathologists worldwide. This study has employed 3 slides (294 HPFs from the MITOS-ATYPIA training dataset in its evaluation and the results showed F-measures 0.65, 0.72and 0.74 for each slide. The proposed method is fast and computationally simple yet its accuracy and specificity is comparable to the best winning methods of the aforementioned grand challenges

Classification of Textures Using Filter Based Local Feature Extraction

Directory of Open Access Journals (Sweden)

Bocekci Veysel Gokhan

2016-01-01

Full Text Available In this work local features are used in feature extraction process in image processing for textures. The local binary pattern feature extraction method from textures are introduced. Filtering is also used during the feature extraction process for getting discriminative features. To show the effectiveness of the algorithm before the extraction process, three different noise are added to both train and test images. Wiener filter and median filter are used to remove the noise from images. We evaluate the performance of the method with Naïve Bayesian classifier. We conduct the comparative analysis on benchmark dataset with different filtering and size. Our experiments demonstrate that feature extraction process combine with filtering give promising results on noisy images.

Feature Extraction Using Fractal Codes

NARCIS (Netherlands)

B.A.M. Schouten (Ben); P.M. de Zeeuw (Paul)

1999-01-01

htmlabstractFast and successful searching for an object in a multimedia database is a highly desirable functionality. Several approaches to content based retrieval for multimedia databases can be found in the literature [9,10,12,14,17]. The approach we consider is feature extraction. A feature can

Characters Feature Extraction Based on Neat Oracle Bone Rubbings

OpenAIRE

Lei Guo

2013-01-01

In order to recognize characters on the neat oracle bone rubbings, a new mesh point feature extraction algorithm was put forward in this paper by researching and improving of the existing coarse mesh feature extraction algorithm and the point feature extraction algorithm. Some improvements of this algorithm were as followings: point feature was introduced into the coarse mesh feature, the absolute address was converted to relative address, and point features have been changed grid and positio...

Feature extraction using fractal codes

NARCIS (Netherlands)

B.A.M. Ben Schouten; Paul M. de Zeeuw

1999-01-01

Fast and successful searching for an object in a multimedia database is a highly desirable functionality. Several approaches to content based retrieval for multimedia databases can be found in the literature [9,10,12,14,17]. The approach we consider is feature extraction. A feature can be seen as a

Fourier transform infrared spectroscopy microscopic imaging classification based on spatial-spectral features

Science.gov (United States)

Liu, Lian; Yang, Xiukun; Zhong, Mingliang; Liu, Yao; Jing, Xiaojun; Yang, Qin

2018-04-01

The discrete fractional Brownian incremental random (DFBIR) field is used to describe the irregular, random, and highly complex shapes of natural objects such as coastlines and biological tissues, for which traditional Euclidean geometry cannot be used. In this paper, an anisotropic variable window (AVW) directional operator based on the DFBIR field model is proposed for extracting spatial characteristics of Fourier transform infrared spectroscopy (FTIR) microscopic imaging. Probabilistic principal component analysis first extracts spectral features, and then the spatial features of the proposed AVW directional operator are combined with the former to construct a spatial-spectral structure, which increases feature-related information and helps a support vector machine classifier to obtain more efficient distribution-related information. Compared to Haralick’s grey-level co-occurrence matrix, Gabor filters, and local binary patterns (e.g. uniform LBPs, rotation-invariant LBPs, uniform rotation-invariant LBPs), experiments on three FTIR spectroscopy microscopic imaging datasets show that the proposed AVW directional operator is more advantageous in terms of classification accuracy, particularly for low-dimensional spaces of spatial characteristics.

Gabor Deconvolution as Preliminary Method to Reduce Pitfall in Deeper Target Seismic Data

Science.gov (United States)

Oktariena, M.; Triyoso, W.

2018-03-01

Anelastic attenuation process during seismic wave propagation is the trigger of seismic non-stationary characteristic. An absorption and a scattering of energy are causing the seismic energy loss as the depth increasing. A series of thin reservoir layers found in the study area is located within Talang Akar Fm. Level, showing an indication of interpretation pitfall due to attenuation effect commonly occurred in deeper level seismic data. Attenuation effect greatly influences the seismic images of deeper target level, creating pitfalls in several aspect. Seismic amplitude in deeper target level often could not represent its real subsurface character due to a low amplitude value or a chaotic event nearing the Basement. Frequency wise, the decaying could be seen as the frequency content diminishing in deeper target. Meanwhile, seismic amplitude is the simple tool to point out Direct Hydrocarbon Indicator (DHI) in preliminary Geophysical study before a further advanced interpretation method applied. A quick-look of Post-Stack Seismic Data shows the reservoir associated with a bright spot DHI while another bigger bright spot body detected in the North East area near the field edge. A horizon slice confirms a possibility that the other bright spot zone has smaller delineation; an interpretation pitfall commonly occurs in deeper level of seismic. We evaluates this pitfall by applying Gabor Deconvolution to address the attenuation problem. Gabor Deconvolution forms a Partition of Unity to factorize the trace into smaller convolution window that could be processed as stationary packets. Gabor Deconvolution estimates both the magnitudes of source signature alongside its attenuation function. The enhanced seismic shows a better imaging in the pitfall area that previously detected as a vast bright spot zone. When the enhanced seismic is used for further advanced reprocessing process, the Seismic Impedance and Vp/Vs Ratio slices show a better reservoir delineation, in which the

Feature Extraction in Radar Target Classification

Directory of Open Access Journals (Sweden)

Z. Kus

1999-09-01

Full Text Available This paper presents experimental results of extracting features in the Radar Target Classification process using the J frequency band pulse radar. The feature extraction is based on frequency analysis methods, the discrete-time Fourier Transform (DFT and Multiple Signal Characterisation (MUSIC, based on the detection of Doppler effect. The analysis has turned to the preference of DFT with implemented Hanning windowing function. We assumed to classify targets-vehicles into two classes, the wheeled vehicle and tracked vehicle. The results show that it is possible to classify them only while moving. The feature of the class results from a movement of moving parts of the vehicle. However, we have not found any feature to classify the wheeled and tracked vehicles while non-moving, although their engines are on.

Face Recognition Using Local Quantized Patterns and Gabor Filters

Science.gov (United States)

Khryashchev, V.; Priorov, A.; Stepanova, O.; Nikitin, A.

2015-05-01

The problem of face recognition in a natural or artificial environment has received a great deal of researchers' attention over the last few years. A lot of methods for accurate face recognition have been proposed. Nevertheless, these methods often fail to accurately recognize the person in difficult scenarios, e.g. low resolution, low contrast, pose variations, etc. We therefore propose an approach for accurate and robust face recognition by using local quantized patterns and Gabor filters. The estimation of the eye centers is used as a preprocessing stage. The evaluation of our algorithm on different samples from a standardized FERET database shows that our method is invariant to the general variations of lighting, expression, occlusion and aging. The proposed approach allows about 20% correct recognition accuracy increase compared with the known face recognition algorithms from the OpenCV library. The additional use of Gabor filters can significantly improve the robustness to changes in lighting conditions.

Segmentation of Coronary Angiograms Using Gabor Filters and Boltzmann Univariate Marginal Distribution Algorithm

Directory of Open Access Journals (Sweden)

Fernando Cervantes-Sanchez

2016-01-01

Full Text Available This paper presents a novel method for improving the training step of the single-scale Gabor filters by using the Boltzmann univariate marginal distribution algorithm (BUMDA in X-ray angiograms. Since the single-scale Gabor filters (SSG are governed by three parameters, the optimal selection of the SSG parameters is highly desirable in order to maximize the detection performance of coronary arteries while reducing the computational time. To obtain the best set of parameters for the SSG, the area (Az under the receiver operating characteristic curve is used as fitness function. Moreover, to classify vessel and nonvessel pixels from the Gabor filter response, the interclass variance thresholding method has been adopted. The experimental results using the proposed method obtained the highest detection rate with Az=0.9502 over a training set of 40 images and Az=0.9583 with a test set of 40 images. In addition, the experimental results of vessel segmentation provided an accuracy of 0.944 with the test set of angiograms.

Iterative algorithms to approximate canonieal Gabor windows: Computational aspects

DEFF Research Database (Denmark)

Janssen, A. J. E. M.; Søndergaard, Peter Lempel

2007-01-01

In this article we investigate the computational aspects of some recently proposed iterative methods for approximating the canonical tight and canonical dual window of a Gabor frame (g, a, b). The iterations start with the window g while the iteration steps comprise the window g, the k(th) iteran...

Object feature extraction and recognition model

International Nuclear Information System (INIS)

Wan Min; Xiang Rujian; Wan Yongxing

2001-01-01

The characteristics of objects, especially flying objects, are analyzed, which include characteristics of spectrum, image and motion. Feature extraction is also achieved. To improve the speed of object recognition, a feature database is used to simplify the data in the source database. The feature vs. object relationship maps are stored in the feature database. An object recognition model based on the feature database is presented, and the way to achieve object recognition is also explained

Real-time hypothesis driven feature extraction on parallel processing architectures

DEFF Research Database (Denmark)

Granmo, O.-C.; Jensen, Finn Verner

2002-01-01

the problem of higher-order feature-content/feature-feature correlation, causally complexly interacting features are identified through Bayesian network d-separation analysis and combined into joint features. When used on a moderately complex object-tracking case, the technique is able to select...... extraction, which selectively extract relevant features one-by-one, have in some cases achieved real-time performance on single processing element architectures. In this paperwe propose a novel technique which combines the above two approaches. Features are selectively extracted in parallelizable sets...

Gabor's expansion and the Zak transform for continuous-time and discrete-time signals : critical sampling and rational oversampling

NARCIS (Netherlands)

Bastiaans, M.J.

1995-01-01

Gabor's expansion of a signal into a discrete set of shifted and modulated versions of an elementary signal is introduced and its relation to sampling of the sliding-window spectrum is shown. It is shown how Gabor's expansion coefficients can be found as samples of the sliding-window spectrum, where

Feature-based attentional modulation increases with stimulus separation in divided-attention tasks.

Science.gov (United States)

Sally, Sharon L; Vidnyánsky, Zoltán; Papathomas, Thomas V

2009-01-01

Attention modifies our visual experience by selecting certain aspects of a scene for further processing. It is therefore important to understand factors that govern the deployment of selective attention over the visual field. Both location and feature-specific mechanisms of attention have been identified and their modulatory effects can interact at a neural level (Treue and Martinez-Trujillo, 1999). The effects of spatial parameters on feature-based attentional modulation were examined for the feature dimensions of orientation, motion and color using three divided-attention tasks. Subjects performed concurrent discriminations of two briefly presented targets (Gabor patches) to the left and right of a central fixation point at eccentricities of +/-2.5 degrees , 5 degrees , 10 degrees and 15 degrees in the horizontal plane. Gabors were size-scaled to maintain consistent single-task performance across eccentricities. For all feature dimensions, the data show a linear increase in the attentional effects with target separation. In a control experiment, Gabors were presented on an isoeccentric viewing arc at 10 degrees and 15 degrees at the closest spatial separation (+/-2.5 degrees ) of the main experiment. Under these conditions, the effects of feature-based attentional effects were largely eliminated. Our results are consistent with the hypothesis that feature-based attention prioritizes the processing of attended features. Feature-based attentional mechanisms may have helped direct the attentional focus to the appropriate target locations at greater separations, whereas similar assistance may not have been necessary at closer target spacings. The results of the present study specify conditions under which dual-task performance benefits from sharing similar target features and may therefore help elucidate the processes by which feature-based attention operates.

Uniform competency-based local feature extraction for remote sensing images

Science.gov (United States)

Sedaghat, Amin; Mohammadi, Nazila

2018-01-01

Local feature detectors are widely used in many photogrammetry and remote sensing applications. The quantity and distribution of the local features play a critical role in the quality of the image matching process, particularly for multi-sensor high resolution remote sensing image registration. However, conventional local feature detectors cannot extract desirable matched features either in terms of the number of correct matches or the spatial and scale distribution in multi-sensor remote sensing images. To address this problem, this paper proposes a novel method for uniform and robust local feature extraction for remote sensing images, which is based on a novel competency criterion and scale and location distribution constraints. The proposed method, called uniform competency (UC) local feature extraction, can be easily applied to any local feature detector for various kinds of applications. The proposed competency criterion is based on a weighted ranking process using three quality measures, including robustness, spatial saliency and scale parameters, which is performed in a multi-layer gridding schema. For evaluation, five state-of-the-art local feature detector approaches, namely, scale-invariant feature transform (SIFT), speeded up robust features (SURF), scale-invariant feature operator (SFOP), maximally stable extremal region (MSER) and hessian-affine, are used. The proposed UC-based feature extraction algorithms were successfully applied to match various synthetic and real satellite image pairs, and the results demonstrate its capability to increase matching performance and to improve the spatial distribution. The code to carry out the UC feature extraction is available from href="https://www.researchgate.net/publication/317956777_UC-Feature_Extraction.

Image segmentation-based robust feature extraction for color image watermarking

Science.gov (United States)

Li, Mianjie; Deng, Zeyu; Yuan, Xiaochen

2018-04-01

This paper proposes a local digital image watermarking method based on Robust Feature Extraction. The segmentation is achieved by Simple Linear Iterative Clustering (SLIC) based on which an Image Segmentation-based Robust Feature Extraction (ISRFE) method is proposed for feature extraction. Our method can adaptively extract feature regions from the blocks segmented by SLIC. This novel method can extract the most robust feature region in every segmented image. Each feature region is decomposed into low-frequency domain and high-frequency domain by Discrete Cosine Transform (DCT). Watermark images are then embedded into the coefficients in the low-frequency domain. The Distortion-Compensated Dither Modulation (DC-DM) algorithm is chosen as the quantization method for embedding. The experimental results indicate that the method has good performance under various attacks. Furthermore, the proposed method can obtain a trade-off between high robustness and good image quality.

RESEARCH ON FEATURE POINTS EXTRACTION METHOD FOR BINARY MULTISCALE AND ROTATION INVARIANT LOCAL FEATURE DESCRIPTOR

Directory of Open Access Journals (Sweden)

Hongwei Ying

2014-08-01

Full Text Available An extreme point of scale space extraction method for binary multiscale and rotation invariant local feature descriptor is studied in this paper in order to obtain a robust and fast method for local image feature descriptor. Classic local feature description algorithms often select neighborhood information of feature points which are extremes of image scale space, obtained by constructing the image pyramid using certain signal transform method. But build the image pyramid always consumes a large amount of computing and storage resources, is not conducive to the actual applications development. This paper presents a dual multiscale FAST algorithm, it does not need to build the image pyramid, but can extract feature points of scale extreme quickly. Feature points extracted by proposed method have the characteristic of multiscale and rotation Invariant and are fit to construct the local feature descriptor.

Hierarchical graph-based segmentation for extracting road networks from high-resolution satellite images

Science.gov (United States)

Alshehhi, Rasha; Marpu, Prashanth Reddy

2017-04-01

Extraction of road networks in urban areas from remotely sensed imagery plays an important role in many urban applications (e.g. road navigation, geometric correction of urban remote sensing images, updating geographic information systems, etc.). It is normally difficult to accurately differentiate road from its background due to the complex geometry of the buildings and the acquisition geometry of the sensor. In this paper, we present a new method for extracting roads from high-resolution imagery based on hierarchical graph-based image segmentation. The proposed method consists of: 1. Extracting features (e.g., using Gabor and morphological filtering) to enhance the contrast between road and non-road pixels, 2. Graph-based segmentation consisting of (i) Constructing a graph representation of the image based on initial segmentation and (ii) Hierarchical merging and splitting of image segments based on color and shape features, and 3. Post-processing to remove irregularities in the extracted road segments. Experiments are conducted on three challenging datasets of high-resolution images to demonstrate the proposed method and compare with other similar approaches. The results demonstrate the validity and superior performance of the proposed method for road extraction in urban areas.

On the Gabor frame set for compactly supported continuous functions

DEFF Research Database (Denmark)

Christensen, Ole; Kim, Hong Oh; Kim, Rae Young

2016-01-01

We identify a class of continuous compactly supported functions for which the known part of the Gabor frame set can be extended. At least for functions with support on an interval of length two, the curve determining the set touches the known obstructions. Easy verifiable sufficient conditions fo...

Gabor's signal expansion based on a non-orthogonal sampling geometry

NARCIS (Netherlands)

Bastiaans, M.J.; Caulfield, H. J.

2002-01-01

Gabor’s signal expansion and the Gabor transform are formulated on a nonorthogonal time-frequency lattice instead of on the traditional rectangular lattice. The reason for doing so is that a non-orthogonal sampling geometry might be better adapted to the form of the window functions (in the

The Two-Dimensional Gabor Function Adapted to Natural Image Statistics: A Model of Simple-Cell Receptive Fields and Sparse Structure in Images.

Science.gov (United States)

Loxley, P N

2017-10-01

The two-dimensional Gabor function is adapted to natural image statistics, leading to a tractable probabilistic generative model that can be used to model simple cell receptive field profiles, or generate basis functions for sparse coding applications. Learning is found to be most pronounced in three Gabor function parameters representing the size and spatial frequency of the two-dimensional Gabor function and characterized by a nonuniform probability distribution with heavy tails. All three parameters are found to be strongly correlated, resulting in a basis of multiscale Gabor functions with similar aspect ratios and size-dependent spatial frequencies. A key finding is that the distribution of receptive-field sizes is scale invariant over a wide range of values, so there is no characteristic receptive field size selected by natural image statistics. The Gabor function aspect ratio is found to be approximately conserved by the learning rules and is therefore not well determined by natural image statistics. This allows for three distinct solutions: a basis of Gabor functions with sharp orientation resolution at the expense of spatial-frequency resolution, a basis of Gabor functions with sharp spatial-frequency resolution at the expense of orientation resolution, or a basis with unit aspect ratio. Arbitrary mixtures of all three cases are also possible. Two parameters controlling the shape of the marginal distributions in a probabilistic generative model fully account for all three solutions. The best-performing probabilistic generative model for sparse coding applications is found to be a gaussian copula with Pareto marginal probability density functions.

Integrated Phoneme Subspace Method for Speech Feature Extraction

Directory of Open Access Journals (Sweden)

Park Hyunsin

2009-01-01

Full Text Available Speech feature extraction has been a key focus in robust speech recognition research. In this work, we discuss data-driven linear feature transformations applied to feature vectors in the logarithmic mel-frequency filter bank domain. Transformations are based on principal component analysis (PCA, independent component analysis (ICA, and linear discriminant analysis (LDA. Furthermore, this paper introduces a new feature extraction technique that collects the correlation information among phoneme subspaces and reconstructs feature space for representing phonemic information efficiently. The proposed speech feature vector is generated by projecting an observed vector onto an integrated phoneme subspace (IPS based on PCA or ICA. The performance of the new feature was evaluated for isolated word speech recognition. The proposed method provided higher recognition accuracy than conventional methods in clean and reverberant environments.

Measurements on a Gabor lens for neutralizing and focusing a 30 keV proton beam

International Nuclear Information System (INIS)

Palkovic, J.A.; Hren, R.; Lee, G.; Mills, F.E.; Schmidt, C.W.; Wendt, J.; Young, D.E.

1989-01-01

The authors have reported previously on the use of a Gabor lens (also referred to as a plasma or space charge lens) to focus and neutralize a low energy proton beam. A different lens geometry and a higher anode voltage have been adopted to overcome a lack of stability present in the previous design. They report on studies in progress to measure the focusing properties of the Gabor lens and determine whether it can be used to match a 30 keV proton beam into radio frequency quadrupole (RFQ) Accelerator. 10 refs., 4 figs

Coronary artery segmentation in X-ray angiogram using Gabor filters and differential evolution

International Nuclear Information System (INIS)

Cervantes S, F.; Hernandez A, A.; Cruz A, I.; Solorio M, S.; Cordova F, T.; Avina C, J. G.

2016-10-01

Segmentation of coronary arteries in X-ray angiograms represents an essential task for computer-aided diagnosis, since it can help cardiologists in diagnosing and monitoring vascular abnormalities. Due to the main disadvantages of the X-ray angiograms are the nonuniform illumination, and the weak contrast between blood vessels and image background, different vessel enhancement methods have been introduced. In this paper, a novel method for blood vessel enhancement based on Gabor filters tuned using the optimization strategy of Differential evolution (De) is proposed. Because the Gabor filters are governed by three different parameters, the optimal selection of those parameters is highly desirable in order to maximize the vessel detection rate while reducing the computational cost of the training stage. To obtain the optimal set of parameters for the Gabor filters, the area (Az) under the receiver operating characteristic curve is used as objective function. In the experimental results, the proposed method obtained the highest detection performance with Az = 0.956 using a test set of 60 angiograms, and Az = 0.934 with a training set of 20 angiograms compared with different state-of-the-art vessel detection methods. In addition, the experimental results in terms of computational time have also shown that the proposed method can be highly suitable for clinical decision support. (Author)

Coronary artery segmentation in X-ray angiogram using Gabor filters and differential evolution

Energy Technology Data Exchange (ETDEWEB)

Cervantes S, F.; Hernandez A, A.; Cruz A, I. [Centro de Investigacion en Matematicas, A. C., Jalisco s/n, Col. Valenciana, 36240 Guanajuato, Gto. (Mexico); Solorio M, S. [IMSS, Unidad de Investigacion, UMAE Hospital de Especialidades No. 1 del Centro Medico Nacional del Bajio, 37260 Leon, Guanajuato (Mexico); Cordova F, T. [Universidad de Guanajuato, Departamento de Ingenieria Fisica, 37150 Leon, Guanajuato (Mexico); Avina C, J. G., E-mail: ivan.cruz@cimat.mx [Universidad de Guanajuato, Departamento de Electronica, 36885 Salamanca, Guanajuato (Mexico)

2016-10-15

Segmentation of coronary arteries in X-ray angiograms represents an essential task for computer-aided diagnosis, since it can help cardiologists in diagnosing and monitoring vascular abnormalities. Due to the main disadvantages of the X-ray angiograms are the nonuniform illumination, and the weak contrast between blood vessels and image background, different vessel enhancement methods have been introduced. In this paper, a novel method for blood vessel enhancement based on Gabor filters tuned using the optimization strategy of Differential evolution (De) is proposed. Because the Gabor filters are governed by three different parameters, the optimal selection of those parameters is highly desirable in order to maximize the vessel detection rate while reducing the computational cost of the training stage. To obtain the optimal set of parameters for the Gabor filters, the area (Az) under the receiver operating characteristic curve is used as objective function. In the experimental results, the proposed method obtained the highest detection performance with Az = 0.956 using a test set of 60 angiograms, and Az = 0.934 with a training set of 20 angiograms compared with different state-of-the-art vessel detection methods. In addition, the experimental results in terms of computational time have also shown that the proposed method can be highly suitable for clinical decision support. (Author)

[Feature extraction for breast cancer data based on geometric algebra theory and feature selection using differential evolution].

Science.gov (United States)

Li, Jing; Hong, Wenxue

2014-12-01

The feature extraction and feature selection are the important issues in pattern recognition. Based on the geometric algebra representation of vector, a new feature extraction method using blade coefficient of geometric algebra was proposed in this study. At the same time, an improved differential evolution (DE) feature selection method was proposed to solve the elevated high dimension issue. The simple linear discriminant analysis was used as the classifier. The result of the 10-fold cross-validation (10 CV) classification of public breast cancer biomedical dataset was more than 96% and proved superior to that of the original features and traditional feature extraction method.

Feature extraction for classification in the data mining process

NARCIS (Netherlands)

Pechenizkiy, M.; Puuronen, S.; Tsymbal, A.

2003-01-01

Dimensionality reduction is a very important step in the data mining process. In this paper, we consider feature extraction for classification tasks as a technique to overcome problems occurring because of "the curse of dimensionality". Three different eigenvector-based feature extraction approaches

Multirate-based fast parallel algorithms for 2-D DHT-based real-valued discrete Gabor transform.

Science.gov (United States)

Tao, Liang; Kwan, Hon Keung

2012-07-01

Novel algorithms for the multirate and fast parallel implementation of the 2-D discrete Hartley transform (DHT)-based real-valued discrete Gabor transform (RDGT) and its inverse transform are presented in this paper. A 2-D multirate-based analysis convolver bank is designed for the 2-D RDGT, and a 2-D multirate-based synthesis convolver bank is designed for the 2-D inverse RDGT. The parallel channels in each of the two convolver banks have a unified structure and can apply the 2-D fast DHT algorithm to speed up their computations. The computational complexity of each parallel channel is low and is independent of the Gabor oversampling rate. All the 2-D RDGT coefficients of an image are computed in parallel during the analysis process and can be reconstructed in parallel during the synthesis process. The computational complexity and time of the proposed parallel algorithms are analyzed and compared with those of the existing fastest algorithms for 2-D discrete Gabor transforms. The results indicate that the proposed algorithms are the fastest, which make them attractive for real-time image processing.

Prediction of troponin-T degradation using color image texture features in 10d aged beef longissimus steaks.

Science.gov (United States)

Sun, X; Chen, K J; Berg, E P; Newman, D J; Schwartz, C A; Keller, W L; Maddock Carlin, K R

2014-02-01

The objective was to use digital color image texture features to predict troponin-T degradation in beef. Image texture features, including 88 gray level co-occurrence texture features, 81 two-dimension fast Fourier transformation texture features, and 48 Gabor wavelet filter texture features, were extracted from color images of beef strip steaks (longissimus dorsi, n = 102) aged for 10d obtained using a digital camera and additional lighting. Steaks were designated degraded or not-degraded based on troponin-T degradation determined on d 3 and d 10 postmortem by immunoblotting. Statistical analysis (STEPWISE regression model) and artificial neural network (support vector machine model, SVM) methods were designed to classify protein degradation. The d 3 and d 10 STEPWISE models were 94% and 86% accurate, respectively, while the d 3 and d 10 SVM models were 63% and 71%, respectively, in predicting protein degradation in aged meat. STEPWISE and SVM models based on image texture features show potential to predict troponin-T degradation in meat. © 2013.

Product forms in Gabor analysis for a quincunx-type sampling geometry

NARCIS (Netherlands)

Bastiaans, M.J.; Leest, van A.J.; Veen, J.P.

1998-01-01

Recently a new sampling lattice - the quincunx lattice - has been introduced [1] as a sampling geometry in the Gabor scheme, which geometry is different from the traditional rectangular sampling geometry. In this paper we will show how results that hold for rectangular sampling (see, for instance,

Multistage feature extraction for accurate face alignment

NARCIS (Netherlands)

Zuo, F.; With, de P.H.N.

2004-01-01

We propose a novel multistage facial feature extraction approach using a combination of 'global' and 'local' techniques. At the first stage, we use template matching, based on an Edge-Orientation-Map for fast feature position estimation. Using this result, a statistical framework applying the Active

Prominent feature extraction for review analysis: an empirical study

Science.gov (United States)

Agarwal, Basant; Mittal, Namita

2016-05-01

Sentiment analysis (SA) research has increased tremendously in recent times. SA aims to determine the sentiment orientation of a given text into positive or negative polarity. Motivation for SA research is the need for the industry to know the opinion of the users about their product from online portals, blogs, discussion boards and reviews and so on. Efficient features need to be extracted for machine-learning algorithm for better sentiment classification. In this paper, initially various features are extracted such as unigrams, bi-grams and dependency features from the text. In addition, new bi-tagged features are also extracted that conform to predefined part-of-speech patterns. Furthermore, various composite features are created using these features. Information gain (IG) and minimum redundancy maximum relevancy (mRMR) feature selection methods are used to eliminate the noisy and irrelevant features from the feature vector. Finally, machine-learning algorithms are used for classifying the review document into positive or negative class. Effects of different categories of features are investigated on four standard data-sets, namely, movie review and product (book, DVD and electronics) review data-sets. Experimental results show that composite features created from prominent features of unigram and bi-tagged features perform better than other features for sentiment classification. mRMR is a better feature selection method as compared with IG for sentiment classification. Boolean Multinomial Naïve Bayes) algorithm performs better than support vector machine classifier for SA in terms of accuracy and execution time.

Alexnet Feature Extraction and Multi-Kernel Learning for Objectoriented Classification

Science.gov (United States)

Ding, L.; Li, H.; Hu, C.; Zhang, W.; Wang, S.

2018-04-01

In view of the fact that the deep convolutional neural network has stronger ability of feature learning and feature expression, an exploratory research is done on feature extraction and classification for high resolution remote sensing images. Taking the Google image with 0.3 meter spatial resolution in Ludian area of Yunnan Province as an example, the image segmentation object was taken as the basic unit, and the pre-trained AlexNet deep convolution neural network model was used for feature extraction. And the spectral features, AlexNet features and GLCM texture features are combined with multi-kernel learning and SVM classifier, finally the classification results were compared and analyzed. The results show that the deep convolution neural network can extract more accurate remote sensing image features, and significantly improve the overall accuracy of classification, and provide a reference value for earthquake disaster investigation and remote sensing disaster evaluation.

ALEXNET FEATURE EXTRACTION AND MULTI-KERNEL LEARNING FOR OBJECTORIENTED CLASSIFICATION

Directory of Open Access Journals (Sweden)

L. Ding

2018-04-01

Full Text Available In view of the fact that the deep convolutional neural network has stronger ability of feature learning and feature expression, an exploratory research is done on feature extraction and classification for high resolution remote sensing images. Taking the Google image with 0.3 meter spatial resolution in Ludian area of Yunnan Province as an example, the image segmentation object was taken as the basic unit, and the pre-trained AlexNet deep convolution neural network model was used for feature extraction. And the spectral features, AlexNet features and GLCM texture features are combined with multi-kernel learning and SVM classifier, finally the classification results were compared and analyzed. The results show that the deep convolution neural network can extract more accurate remote sensing image features, and significantly improve the overall accuracy of classification, and provide a reference value for earthquake disaster investigation and remote sensing disaster evaluation.

Binary gabor statistical features for palmprint template protection

NARCIS (Netherlands)

Mu, Meiru; Ruan, Qiuqi; Shao, X.; Spreeuwers, Lieuwe Jan; Veldhuis, Raymond N.J.

2012-01-01

The biometric template protection system requires a highquality biometric channel and a well-designed error correction code (ECC). Due to the intra-class variations of biometric data, an efficient fixed-length binary feature extractor is required to provide a high-quality biometric channel so that

FEATURE EXTRACTION FOR EMG BASED PROSTHESES CONTROL

Directory of Open Access Journals (Sweden)

R. Aishwarya

2013-01-01

Full Text Available The control of prosthetic limb would be more effective if it is based on Surface Electromyogram (SEMG signals from remnant muscles. The analysis of SEMG signals depend on a number of factors, such as amplitude as well as time- and frequency-domain properties. Time series analysis using Auto Regressive (AR model and Mean frequency which is tolerant to white Gaussian noise are used as feature extraction techniques. EMG Histogram is used as another feature vector that was seen to give more distinct classification. The work was done with SEMG dataset obtained from the NINAPRO DATABASE, a resource for bio robotics community. Eight classes of hand movements hand open, hand close, Wrist extension, Wrist flexion, Pointing index, Ulnar deviation, Thumbs up, Thumb opposite to little finger are taken into consideration and feature vectors are extracted. The feature vectors can be given to an artificial neural network for further classification in controlling the prosthetic arm which is not dealt in this paper.

Raamidest välja mõtlemine pole piisav / Gabor George Burt ; interv. Harli Uljas

Index Scriptorium Estoniae

Burt, Gabor George

2006-01-01

Juhtimisstrateegia Blue Ocean Strategy eestkõneleja Gabor George Burti sõnul tuleb edu saavutamiseks keskenduda kliendile ning tegeleda personaalselt kliendi jaoks sobiva lahenduse loomisega. Kommenteerib Priit Põldoja

An Effective Fault Feature Extraction Method for Gas Turbine Generator System Diagnosis

Directory of Open Access Journals (Sweden)

Jian-Hua Zhong

2016-01-01

Full Text Available Fault diagnosis is very important to maintain the operation of a gas turbine generator system (GTGS in power plants, where any abnormal situations will interrupt the electricity supply. The fault diagnosis of the GTGS faces the main challenge that the acquired data, vibration or sound signals, contain a great deal of redundant information which extends the fault identification time and degrades the diagnostic accuracy. To improve the diagnostic performance in the GTGS, an effective fault feature extraction framework is proposed to solve the problem of the signal disorder and redundant information in the acquired signal. The proposed framework combines feature extraction with a general machine learning method, support vector machine (SVM, to implement an intelligent fault diagnosis. The feature extraction method adopts wavelet packet transform and time-domain statistical features to extract the features of faults from the vibration signal. To further reduce the redundant information in extracted features, kernel principal component analysis is applied in this study. Experimental results indicate that the proposed feature extracted technique is an effective method to extract the useful features of faults, resulting in improvement of the performance of fault diagnosis for the GTGS.

Statistical Feature Extraction and Recognition of Beverages Using Electronic Tongue

Directory of Open Access Journals (Sweden)

P. C. PANCHARIYA

2010-01-01

Full Text Available This paper describes an approach for extraction of features from data generated from an electronic tongue based on large amplitude pulse voltammetry. In this approach statistical features of the meaningful selected variables from current response signals are extracted and used for recognition of beverage samples. The proposed feature extraction approach not only reduces the computational complexity but also reduces the computation time and requirement of storage of data for the development of E-tongue for field applications. With the reduced information, a probabilistic neural network (PNN was trained for qualitative analysis of different beverages. Before the qualitative analysis of the beverages, the methodology has been tested for the basic artificial taste solutions i.e. sweet, sour, salt, bitter, and umami. The proposed procedure was compared with the more conventional and linear feature extraction technique employing principal component analysis combined with PNN. Using the extracted feature vectors, highly correct classification by PNN was achieved for eight types of juices and six types of soft drinks. The results indicated that the electronic tongue based on large amplitude pulse voltammetry with reduced feature was capable of discriminating not only basic artificial taste solutions but also the various sorts of the same type of natural beverages (fruit juices, vegetable juices, soft drinks, etc..

Large datasets: Segmentation, feature extraction, and compression

Energy Technology Data Exchange (ETDEWEB)

Downing, D.J.; Fedorov, V.; Lawkins, W.F.; Morris, M.D.; Ostrouchov, G.

1996-07-01

Large data sets with more than several mission multivariate observations (tens of megabytes or gigabytes of stored information) are difficult or impossible to analyze with traditional software. The amount of output which must be scanned quickly dilutes the ability of the investigator to confidently identify all the meaningful patterns and trends which may be present. The purpose of this project is to develop both a theoretical foundation and a collection of tools for automated feature extraction that can be easily customized to specific applications. Cluster analysis techniques are applied as a final step in the feature extraction process, which helps make data surveying simple and effective.

Feature Extraction and Selection Strategies for Automated Target Recognition

Science.gov (United States)

Greene, W. Nicholas; Zhang, Yuhan; Lu, Thomas T.; Chao, Tien-Hsin

2010-01-01

Several feature extraction and selection methods for an existing automatic target recognition (ATR) system using JPLs Grayscale Optical Correlator (GOC) and Optimal Trade-Off Maximum Average Correlation Height (OT-MACH) filter were tested using MATLAB. The ATR system is composed of three stages: a cursory region of-interest (ROI) search using the GOC and OT-MACH filter, a feature extraction and selection stage, and a final classification stage. Feature extraction and selection concerns transforming potential target data into more useful forms as well as selecting important subsets of that data which may aide in detection and classification. The strategies tested were built around two popular extraction methods: Principal Component Analysis (PCA) and Independent Component Analysis (ICA). Performance was measured based on the classification accuracy and free-response receiver operating characteristic (FROC) output of a support vector machine(SVM) and a neural net (NN) classifier.

On Gabor frames generated by sign-changing windows and B-splines

DEFF Research Database (Denmark)

Christensen, Ole; Kim, Hong Oh; Kim, Rae Young

2015-01-01

For a class of compactly supported windows we characterize the frame property for a Gabor system {EmbTnag}m,nZ, for translation parameters a belonging to a certain range depending on the support size. We show that the obstructions to the frame property are located on a countable number of "curves...

A Hierarchical Feature Extraction Model for Multi-Label Mechanical Patent Classification

Directory of Open Access Journals (Sweden)

Jie Hu

2018-01-01

Full Text Available Various studies have focused on feature extraction methods for automatic patent classification in recent years. However, most of these approaches are based on the knowledge from experts in related domains. Here we propose a hierarchical feature extraction model (HFEM for multi-label mechanical patent classification, which is able to capture both local features of phrases as well as global and temporal semantics. First, a n-gram feature extractor based on convolutional neural networks (CNNs is designed to extract salient local lexical-level features. Next, a long dependency feature extraction model based on the bidirectional long–short-term memory (BiLSTM neural network model is proposed to capture sequential correlations from higher-level sequence representations. Then the HFEM algorithm and its hierarchical feature extraction architecture are detailed. We establish the training, validation and test datasets, containing 72,532, 18,133, and 2679 mechanical patent documents, respectively, and then check the performance of HFEMs. Finally, we compared the results of the proposed HFEM and three other single neural network models, namely CNN, long–short-term memory (LSTM, and BiLSTM. The experimental results indicate that our proposed HFEM outperforms the other compared models in both precision and recall.

Deep Learning Methods for Underwater Target Feature Extraction and Recognition

Directory of Open Access Journals (Sweden)

Gang Hu

2018-01-01

Full Text Available The classification and recognition technology of underwater acoustic signal were always an important research content in the field of underwater acoustic signal processing. Currently, wavelet transform, Hilbert-Huang transform, and Mel frequency cepstral coefficients are used as a method of underwater acoustic signal feature extraction. In this paper, a method for feature extraction and identification of underwater noise data based on CNN and ELM is proposed. An automatic feature extraction method of underwater acoustic signals is proposed using depth convolution network. An underwater target recognition classifier is based on extreme learning machine. Although convolution neural networks can execute both feature extraction and classification, their function mainly relies on a full connection layer, which is trained by gradient descent-based; the generalization ability is limited and suboptimal, so an extreme learning machine (ELM was used in classification stage. Firstly, CNN learns deep and robust features, followed by the removing of the fully connected layers. Then ELM fed with the CNN features is used as the classifier to conduct an excellent classification. Experiments on the actual data set of civil ships obtained 93.04% recognition rate; compared to the traditional Mel frequency cepstral coefficients and Hilbert-Huang feature, recognition rate greatly improved.

A method for real-time implementation of HOG feature extraction

Science.gov (United States)

Luo, Hai-bo; Yu, Xin-rong; Liu, Hong-mei; Ding, Qing-hai

2011-08-01

Histogram of oriented gradient (HOG) is an efficient feature extraction scheme, and HOG descriptors are feature descriptors which is widely used in computer vision and image processing for the purpose of biometrics, target tracking, automatic target detection(ATD) and automatic target recognition(ATR) etc. However, computation of HOG feature extraction is unsuitable for hardware implementation since it includes complicated operations. In this paper, the optimal design method and theory frame for real-time HOG feature extraction based on FPGA were proposed. The main principle is as follows: firstly, the parallel gradient computing unit circuit based on parallel pipeline structure was designed. Secondly, the calculation of arctangent and square root operation was simplified. Finally, a histogram generator based on parallel pipeline structure was designed to calculate the histogram of each sub-region. Experimental results showed that the HOG extraction can be implemented in a pixel period by these computing units.

Fully automated muscle quality assessment by Gabor filtering of second harmonic generation images

Science.gov (United States)

Paesen, Rik; Smolders, Sophie; Vega, José Manolo de Hoyos; Eijnde, Bert O.; Hansen, Dominique; Ameloot, Marcel

2016-02-01

Although structural changes on the sarcomere level of skeletal muscle are known to occur due to various pathologies, rigorous studies of the reduced sarcomere quality remain scarce. This can possibly be explained by the lack of an objective tool for analyzing and comparing sarcomere images across biological conditions. Recent developments in second harmonic generation (SHG) microscopy and increasing insight into the interpretation of sarcomere SHG intensity profiles have made SHG microscopy a valuable tool to study microstructural properties of sarcomeres. Typically, sarcomere integrity is analyzed by fitting a set of manually selected, one-dimensional SHG intensity profiles with a supramolecular SHG model. To circumvent this tedious manual selection step, we developed a fully automated image analysis procedure to map the sarcomere disorder for the entire image at once. The algorithm relies on a single-frequency wavelet-based Gabor approach and includes a newly developed normalization procedure allowing for unambiguous data interpretation. The method was validated by showing the correlation between the sarcomere disorder, quantified by the M-band size obtained from manually selected profiles, and the normalized Gabor value ranging from 0 to 1 for decreasing disorder. Finally, to elucidate the applicability of our newly developed protocol, Gabor analysis was used to study the effect of experimental autoimmune encephalomyelitis on the sarcomere regularity. We believe that the technique developed in this work holds great promise for high-throughput, unbiased, and automated image analysis to study sarcomere integrity by SHG microscopy.

Feature extraction for magnetic domain images of magneto-optical recording films using gradient feature segmentation

International Nuclear Information System (INIS)

Quanqing, Zhu.; Xinsai, Wang; Xuecheng, Zou; Haihua, Li; Xiaofei, Yang

2002-01-01

In this paper, we present a method to realize feature extraction on low contrast magnetic domain images of magneto-optical recording films. The method is based on the following three steps: first, Lee-filtering method is adopted to realize pre-filtering and noise reduction; this is followed by gradient feature segmentation, which separates the object area from the background area; finally the common linking method is adopted and the characteristic parameters of magnetic domain are calculated. We describe these steps with particular emphasis on the gradient feature segmentation. The results show that this method has advantages over other traditional ones for feature extraction of low contrast images

Efficient Algorithms for the Discrete Gabor Transform with a Long Fir Window

DEFF Research Database (Denmark)

Søndergaard, Peter Lempel

2012-01-01

The Discrete Gabor Transform (DGT) is the most commonly used signal transform for signal analysis and synthesis using a linear frequency scale. The development of the Linear Time-Frequency Analysis Toolbox (LTFAT) has been based on a detailed study of many variants of the relevant algorithms. As ...

Stacked Denoise Autoencoder Based Feature Extraction and Classification for Hyperspectral Images

Directory of Open Access Journals (Sweden)

Chen Xing

2016-01-01

Full Text Available Deep learning methods have been successfully applied to learn feature representations for high-dimensional data, where the learned features are able to reveal the nonlinear properties exhibited in the data. In this paper, deep learning method is exploited for feature extraction of hyperspectral data, and the extracted features can provide good discriminability for classification task. Training a deep network for feature extraction and classification includes unsupervised pretraining and supervised fine-tuning. We utilized stacked denoise autoencoder (SDAE method to pretrain the network, which is robust to noise. In the top layer of the network, logistic regression (LR approach is utilized to perform supervised fine-tuning and classification. Since sparsity of features might improve the separation capability, we utilized rectified linear unit (ReLU as activation function in SDAE to extract high level and sparse features. Experimental results using Hyperion, AVIRIS, and ROSIS hyperspectral data demonstrated that the SDAE pretraining in conjunction with the LR fine-tuning and classification (SDAE_LR can achieve higher accuracies than the popular support vector machine (SVM classifier.

Application of eigen value expansion to feature extraction from MRI images

International Nuclear Information System (INIS)

Kinosada, Yasutomi; Takeda, Kan; Nakagawa, Tsuyoshi

1991-01-01

The eigen value expansion technique was utilized for feature extraction of magnetic resonance (MR) images. The eigen value expansion is an orthonormal transformation method which decomposes a set of images into some statistically uncorrelated images. The technique was applied to MR images obtained with various imaging parameters at the same anatomical site. It generated one mean image and another set of images called bases for the images. Each basis corresponds to a feature in the images. A basis is, therefore, utilized for the feature extraction from MR images and a weighted sum of bases is also used for the feature enhancement. Furthermore, any MR image with specific feature can be obtained from a linear combination of the mean image and all of the bases. Images of hemorrhaged brain with a spin echo sequence and a series of cinematic cerebro spinal fluid flow images with ECG gated gradient refocused echo sequence were employed to estimate the ability of the feature extraction and the contrast enhancement. Results showed us that proposed application of an eigen value expansion technique to the feature extraction of MR images is good enough to clinical use and superior to other feature extraction methods such as producing a calculated MR image with a given TR and TE or the matched-filter method in processing speed and reproducibility of results. (author)

The feature-weighted receptive field: an interpretable encoding model for complex feature spaces.

Science.gov (United States)

St-Yves, Ghislain; Naselaris, Thomas

2017-06-20

We introduce the feature-weighted receptive field (fwRF), an encoding model designed to balance expressiveness, interpretability and scalability. The fwRF is organized around the notion of a feature map-a transformation of visual stimuli into visual features that preserves the topology of visual space (but not necessarily the native resolution of the stimulus). The key assumption of the fwRF model is that activity in each voxel encodes variation in a spatially localized region across multiple feature maps. This region is fixed for all feature maps; however, the contribution of each feature map to voxel activity is weighted. Thus, the model has two separable sets of parameters: "where" parameters that characterize the location and extent of pooling over visual features, and "what" parameters that characterize tuning to visual features. The "where" parameters are analogous to classical receptive fields, while "what" parameters are analogous to classical tuning functions. By treating these as separable parameters, the fwRF model complexity is independent of the resolution of the underlying feature maps. This makes it possible to estimate models with thousands of high-resolution feature maps from relatively small amounts of data. Once a fwRF model has been estimated from data, spatial pooling and feature tuning can be read-off directly with no (or very little) additional post-processing or in-silico experimentation. We describe an optimization algorithm for estimating fwRF models from data acquired during standard visual neuroimaging experiments. We then demonstrate the model's application to two distinct sets of features: Gabor wavelets and features supplied by a deep convolutional neural network. We show that when Gabor feature maps are used, the fwRF model recovers receptive fields and spatial frequency tuning functions consistent with known organizational principles of the visual cortex. We also show that a fwRF model can be used to regress entire deep

Imperfect pitch: Gabor's uncertainty principle and the pitch of extremely brief sounds.

Science.gov (United States)

Hsieh, I-Hui; Saberi, Kourosh

2016-02-01

How brief must a sound be before its pitch is no longer perceived? The uncertainty tradeoff between temporal and spectral resolution (Gabor's principle) limits the minimum duration required for accurate pitch identification or discrimination. Prior studies have reported that pitch can be extracted from sinusoidal pulses as brief as half a cycle. This finding has been used in a number of classic papers to develop models of pitch encoding. We have found that phase randomization, which eliminates timbre confounds, degrades this ability to chance, raising serious concerns over the foundation on which classic pitch models have been built. The current study investigated whether subthreshold pitch cues may still exist in partial-cycle pulses revealed through statistical integration in a time series containing multiple pulses. To this end, we measured frequency-discrimination thresholds in a two-interval forced-choice task for trains of partial-cycle random-phase tone pulses. We found that residual pitch cues exist in these pulses but discriminating them requires an order of magnitude (ten times) larger frequency difference than that reported previously, necessitating a re-evaluation of pitch models built on earlier findings. We also found that as pulse duration is decreased to less than two cycles its pitch becomes biased toward higher frequencies, consistent with predictions of an auto-correlation model of pitch extraction.

PyEEG: an open source Python module for EEG/MEG feature extraction.

Science.gov (United States)

Bao, Forrest Sheng; Liu, Xin; Zhang, Christina

2011-01-01

Computer-aided diagnosis of neural diseases from EEG signals (or other physiological signals that can be treated as time series, e.g., MEG) is an emerging field that has gained much attention in past years. Extracting features is a key component in the analysis of EEG signals. In our previous works, we have implemented many EEG feature extraction functions in the Python programming language. As Python is gaining more ground in scientific computing, an open source Python module for extracting EEG features has the potential to save much time for computational neuroscientists. In this paper, we introduce PyEEG, an open source Python module for EEG feature extraction.

Osteoarthritis Severity Determination using Self Organizing Map Based Gabor Kernel

Science.gov (United States)

Anifah, L.; Purnomo, M. H.; Mengko, T. L. R.; Purnama, I. K. E.

2018-02-01

The number of osteoarthritis patients in Indonesia is enormous, so early action is needed in order for this disease to be handled. The aim of this paper to determine osteoarthritis severity based on x-ray image template based on gabor kernel. This research is divided into 3 stages, the first step is image processing that is using gabor kernel. The second stage is the learning stage, and the third stage is the testing phase. The image processing stage is by normalizing the image dimension to be template to 50 □ 200 image. Learning stage is done with parameters initial learning rate of 0.5 and the total number of iterations of 1000. The testing stage is performed using the weights generated at the learning stage. The testing phase has been done and the results were obtained. The result shows KL-Grade 0 has an accuracy of 36.21%, accuracy for KL-Grade 2 is 40,52%, while accuracy for KL-Grade 2 and KL-Grade 3 are 15,52%, and 25,86%. The implication of this research is expected that this research as decision support system for medical practitioners in determining KL-Grade on X-ray images of knee osteoarthritis.

Multi-stage classification method oriented to aerial image based on low-rank recovery and multi-feature fusion sparse representation.

Science.gov (United States)

Ma, Xu; Cheng, Yongmei; Hao, Shuai

2016-12-10

Automatic classification of terrain surfaces from an aerial image is essential for an autonomous unmanned aerial vehicle (UAV) landing at an unprepared site by using vision. Diverse terrain surfaces may show similar spectral properties due to the illumination and noise that easily cause poor classification performance. To address this issue, a multi-stage classification algorithm based on low-rank recovery and multi-feature fusion sparse representation is proposed. First, color moments and Gabor texture feature are extracted from training data and stacked as column vectors of a dictionary. Then we perform low-rank matrix recovery for the dictionary by using augmented Lagrange multipliers and construct a multi-stage terrain classifier. Experimental results on an aerial map database that we prepared verify the classification accuracy and robustness of the proposed method.

Extraction of Lesion-Partitioned Features and Retrieval of Contrast-Enhanced Liver Images

Directory of Open Access Journals (Sweden)

Mei Yu

2012-01-01

Full Text Available The most critical step in grayscale medical image retrieval systems is feature extraction. Understanding the interrelatedness between the characteristics of lesion images and corresponding imaging features is crucial for image training, as well as for features extraction. A feature-extraction algorithm is developed based on different imaging properties of lesions and on the discrepancy in density between the lesions and their surrounding normal liver tissues in triple-phase contrast-enhanced computed tomographic (CT scans. The algorithm includes mainly two processes: (1 distance transformation, which is used to divide the lesion into distinct regions and represents the spatial structure distribution and (2 representation using bag of visual words (BoW based on regions. The evaluation of this system based on the proposed feature extraction algorithm shows excellent retrieval results for three types of liver lesions visible on triple-phase scans CT images. The results of the proposed feature extraction algorithm show that although single-phase scans achieve the average precision of 81.9%, 80.8%, and 70.2%, dual- and triple-phase scans achieve 86.3% and 88.0%.

Combining Deep and Handcrafted Image Features for Presentation Attack Detection in Face Recognition Systems Using Visible-Light Camera Sensors

Directory of Open Access Journals (Sweden)

Dat Tien Nguyen

2018-02-01

Full Text Available Although face recognition systems have wide application, they are vulnerable to presentation attack samples (fake samples. Therefore, a presentation attack detection (PAD method is required to enhance the security level of face recognition systems. Most of the previously proposed PAD methods for face recognition systems have focused on using handcrafted image features, which are designed by expert knowledge of designers, such as Gabor filter, local binary pattern (LBP, local ternary pattern (LTP, and histogram of oriented gradients (HOG. As a result, the extracted features reflect limited aspects of the problem, yielding a detection accuracy that is low and varies with the characteristics of presentation attack face images. The deep learning method has been developed in the computer vision research community, which is proven to be suitable for automatically training a feature extractor that can be used to enhance the ability of handcrafted features. To overcome the limitations of previously proposed PAD methods, we propose a new PAD method that uses a combination of deep and handcrafted features extracted from the images by visible-light camera sensor. Our proposed method uses the convolutional neural network (CNN method to extract deep image features and the multi-level local binary pattern (MLBP method to extract skin detail features from face images to discriminate the real and presentation attack face images. By combining the two types of image features, we form a new type of image features, called hybrid features, which has stronger discrimination ability than single image features. Finally, we use the support vector machine (SVM method to classify the image features into real or presentation attack class. Our experimental results indicate that our proposed method outperforms previous PAD methods by yielding the smallest error rates on the same image databases.

Combining Deep and Handcrafted Image Features for Presentation Attack Detection in Face Recognition Systems Using Visible-Light Camera Sensors.

Science.gov (United States)

Nguyen, Dat Tien; Pham, Tuyen Danh; Baek, Na Rae; Park, Kang Ryoung

2018-02-26

Although face recognition systems have wide application, they are vulnerable to presentation attack samples (fake samples). Therefore, a presentation attack detection (PAD) method is required to enhance the security level of face recognition systems. Most of the previously proposed PAD methods for face recognition systems have focused on using handcrafted image features, which are designed by expert knowledge of designers, such as Gabor filter, local binary pattern (LBP), local ternary pattern (LTP), and histogram of oriented gradients (HOG). As a result, the extracted features reflect limited aspects of the problem, yielding a detection accuracy that is low and varies with the characteristics of presentation attack face images. The deep learning method has been developed in the computer vision research community, which is proven to be suitable for automatically training a feature extractor that can be used to enhance the ability of handcrafted features. To overcome the limitations of previously proposed PAD methods, we propose a new PAD method that uses a combination of deep and handcrafted features extracted from the images by visible-light camera sensor. Our proposed method uses the convolutional neural network (CNN) method to extract deep image features and the multi-level local binary pattern (MLBP) method to extract skin detail features from face images to discriminate the real and presentation attack face images. By combining the two types of image features, we form a new type of image features, called hybrid features, which has stronger discrimination ability than single image features. Finally, we use the support vector machine (SVM) method to classify the image features into real or presentation attack class. Our experimental results indicate that our proposed method outperforms previous PAD methods by yielding the smallest error rates on the same image databases.

Combining Deep and Handcrafted Image Features for Presentation Attack Detection in Face Recognition Systems Using Visible-Light Camera Sensors

Science.gov (United States)

Nguyen, Dat Tien; Pham, Tuyen Danh; Baek, Na Rae; Park, Kang Ryoung

2018-01-01

Although face recognition systems have wide application, they are vulnerable to presentation attack samples (fake samples). Therefore, a presentation attack detection (PAD) method is required to enhance the security level of face recognition systems. Most of the previously proposed PAD methods for face recognition systems have focused on using handcrafted image features, which are designed by expert knowledge of designers, such as Gabor filter, local binary pattern (LBP), local ternary pattern (LTP), and histogram of oriented gradients (HOG). As a result, the extracted features reflect limited aspects of the problem, yielding a detection accuracy that is low and varies with the characteristics of presentation attack face images. The deep learning method has been developed in the computer vision research community, which is proven to be suitable for automatically training a feature extractor that can be used to enhance the ability of handcrafted features. To overcome the limitations of previously proposed PAD methods, we propose a new PAD method that uses a combination of deep and handcrafted features extracted from the images by visible-light camera sensor. Our proposed method uses the convolutional neural network (CNN) method to extract deep image features and the multi-level local binary pattern (MLBP) method to extract skin detail features from face images to discriminate the real and presentation attack face images. By combining the two types of image features, we form a new type of image features, called hybrid features, which has stronger discrimination ability than single image features. Finally, we use the support vector machine (SVM) method to classify the image features into real or presentation attack class. Our experimental results indicate that our proposed method outperforms previous PAD methods by yielding the smallest error rates on the same image databases. PMID:29495417

A graph-Laplacian-based feature extraction algorithm for neural spike sorting.

Science.gov (United States)

Ghanbari, Yasser; Spence, Larry; Papamichalis, Panos

2009-01-01

Analysis of extracellular neural spike recordings is highly dependent upon the accuracy of neural waveform classification, commonly referred to as spike sorting. Feature extraction is an important stage of this process because it can limit the quality of clustering which is performed in the feature space. This paper proposes a new feature extraction method (which we call Graph Laplacian Features, GLF) based on minimizing the graph Laplacian and maximizing the weighted variance. The algorithm is compared with Principal Components Analysis (PCA, the most commonly-used feature extraction method) using simulated neural data. The results show that the proposed algorithm produces more compact and well-separated clusters compared to PCA. As an added benefit, tentative cluster centers are output which can be used to initialize a subsequent clustering stage.

A Novel Marking Reader for Progressive Addition Lenses Based on Gabor Holography.

Science.gov (United States)

Perucho, Beatriz; Picazo-Bueno, José Angel; Micó, Vicente

2016-05-01

Progressive addition lenses (PALs) are marked with permanent engraved marks (PEMs) at standardized locations. Permanent engraved marks are very useful through the manufacturing and mounting processes, act as locator marks to re-ink the removable marks, and contain useful information about the PAL. However, PEMs are often faint and weak, obscured by scratches, partially occluded, and difficult to recognize on tinted lenses or with antireflection or scratch-resistant coatings. The aim of this article is to present a new generation of portable marking reader based on an extremely simplified concept for visualization and identification of PEMs in PALs. Permanent engraved marks on different PALs are visualized using classical Gabor holography as underlying principle. Gabor holography allows phase sample visualization with adjustable magnification and can be implemented in either classical or digital versions. Here, visual Gabor holography is used to provide a magnified defocused image of the PEMs onto a translucent visualization screen where the PEM is clearly identified. Different types of PALs (conventional, personalized, old and scratched, sunglasses, etc.) have been tested to visualize PEMs with the proposed marking reader. The PEMs are visible in every case, and variable magnification factor can be achieved simply moving up and down the PAL in the instrument. In addition, a second illumination wavelength is also tested, showing the applicability of this novel marking reader for different illuminations. A new concept of marking reader ophthalmic instrument has been presented and validated in the laboratory. The configuration involves only a commercial-grade laser diode and a visualization screen for PEM identification. The instrument is portable, economic, and easy to use, and it can be used for identifying patient's current PAL model and for marking removable PALs again or finding test points regardless of the age of the PAL, its scratches, tints, or coatings.

Ethnicity distinctiveness through iris texture features using Gabor filters

CSIR Research Space (South Africa)

Mabuza-Hocquet, Gugulethu P

2017-02-01

Full Text Available Research in iris biometrics has been focused on utilizing iris features as a means of identity verification and authentication. However, not enough research work has been done to explore iris textures to determine soft biometrics such as gender...

Airborne LIDAR and high resolution satellite data for rapid 3D feature extraction

Science.gov (United States)

Jawak, S. D.; Panditrao, S. N.; Luis, A. J.

2014-11-01

This work uses the canopy height model (CHM) based workflow for individual tree crown delineation and 3D feature extraction approach (Overwatch Geospatial's proprietary algorithm) for building feature delineation from high-density light detection and ranging (LiDAR) point cloud data in an urban environment and evaluates its accuracy by using very high-resolution panchromatic (PAN) (spatial) and 8-band (multispectral) WorldView-2 (WV-2) imagery. LiDAR point cloud data over San Francisco, California, USA, recorded in June 2010, was used to detect tree and building features by classifying point elevation values. The workflow employed includes resampling of LiDAR point cloud to generate a raster surface or digital terrain model (DTM), generation of a hill-shade image and an intensity image, extraction of digital surface model, generation of bare earth digital elevation model (DEM) and extraction of tree and building features. First, the optical WV-2 data and the LiDAR intensity image were co-registered using ground control points (GCPs). The WV-2 rational polynomial coefficients model (RPC) was executed in ERDAS Leica Photogrammetry Suite (LPS) using supplementary *.RPB file. In the second stage, ortho-rectification was carried out using ERDAS LPS by incorporating well-distributed GCPs. The root mean square error (RMSE) for the WV-2 was estimated to be 0.25 m by using more than 10 well-distributed GCPs. In the second stage, we generated the bare earth DEM from LiDAR point cloud data. In most of the cases, bare earth DEM does not represent true ground elevation. Hence, the model was edited to get the most accurate DEM/ DTM possible and normalized the LiDAR point cloud data based on DTM in order to reduce the effect of undulating terrain. We normalized the vegetation point cloud values by subtracting the ground points (DEM) from the LiDAR point cloud. A normalized digital surface model (nDSM) or CHM was calculated from the LiDAR data by subtracting the DEM from the DSM

Optimized Feature Extraction for Temperature-Modulated Gas Sensors

Directory of Open Access Journals (Sweden)

Alexander Vergara

2009-01-01

Full Text Available One of the most serious limitations to the practical utilization of solid-state gas sensors is the drift of their signal. Even if drift is rooted in the chemical and physical processes occurring in the sensor, improved signal processing is generally considered as a methodology to increase sensors stability. Several studies evidenced the augmented stability of time variable signals elicited by the modulation of either the gas concentration or the operating temperature. Furthermore, when time-variable signals are used, the extraction of features can be accomplished in shorter time with respect to the time necessary to calculate the usual features defined in steady-state conditions. In this paper, we discuss the stability properties of distinct dynamic features using an array of metal oxide semiconductors gas sensors whose working temperature is modulated with optimized multisinusoidal signals. Experiments were aimed at measuring the dispersion of sensors features in repeated sequences of a limited number of experimental conditions. Results evidenced that the features extracted during the temperature modulation reduce the multidimensional data dispersion among repeated measurements. In particular, the Energy Signal Vector provided an almost constant classification rate along the time with respect to the temperature modulation.

Multi-scale salient feature extraction on mesh models

KAUST Repository

Yang, Yongliang; Shen, ChaoHui

2012-01-01

We present a new method of extracting multi-scale salient features on meshes. It is based on robust estimation of curvature on multiple scales. The coincidence between salient feature and the scale of interest can be established straightforwardly, where detailed feature appears on small scale and feature with more global shape information shows up on large scale. We demonstrate this multi-scale description of features accords with human perception and can be further used for several applications as feature classification and viewpoint selection. Experiments exhibit that our method as a multi-scale analysis tool is very helpful for studying 3D shapes. © 2012 Springer-Verlag.

Compact and Hybrid Feature Description for Building Extraction

Science.gov (United States)

Li, Z.; Liu, Y.; Hu, Y.; Li, P.; Ding, Y.

2017-05-01

Building extraction in aerial orthophotos is crucial for various applications. Currently, deep learning has been shown to be successful in addressing building extraction with high accuracy and high robustness. However, quite a large number of samples is required in training a classifier when using deep learning model. In order to realize accurate and semi-interactive labelling, the performance of feature description is crucial, as it has significant effect on the accuracy of classification. In this paper, we bring forward a compact and hybrid feature description method, in order to guarantees desirable classification accuracy of the corners on the building roof contours. The proposed descriptor is a hybrid description of an image patch constructed from 4 sets of binary intensity tests. Experiments show that benefiting from binary description and making full use of color channels, this descriptor is not only computationally frugal, but also accurate than SURF for building extraction.

A Transform-Based Feature Extraction Approach for Motor Imagery Tasks Classification

Science.gov (United States)

Khorshidtalab, Aida; Mesbah, Mostefa; Salami, Momoh J. E.

2015-01-01

In this paper, we present a new motor imagery classification method in the context of electroencephalography (EEG)-based brain–computer interface (BCI). This method uses a signal-dependent orthogonal transform, referred to as linear prediction singular value decomposition (LP-SVD), for feature extraction. The transform defines the mapping as the left singular vectors of the LP coefficient filter impulse response matrix. Using a logistic tree-based model classifier; the extracted features are classified into one of four motor imagery movements. The proposed approach was first benchmarked against two related state-of-the-art feature extraction approaches, namely, discrete cosine transform (DCT) and adaptive autoregressive (AAR)-based methods. By achieving an accuracy of 67.35%, the LP-SVD approach outperformed the other approaches by large margins (25% compared with DCT and 6 % compared with AAR-based methods). To further improve the discriminatory capability of the extracted features and reduce the computational complexity, we enlarged the extracted feature subset by incorporating two extra features, namely, Q- and the Hotelling’s \\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{upgreek} \\usepackage{mathrsfs} \\setlength{\\oddsidemargin}{-69pt} \\begin{document} }{}$T^{2}$ \\end{document} statistics of the transformed EEG and introduced a new EEG channel selection method. The performance of the EEG classification based on the expanded feature set and channel selection method was compared with that of a number of the state-of-the-art classification methods previously reported with the BCI IIIa competition data set. Our method came second with an average accuracy of 81.38%. PMID:27170898

Analysis of Feature Extraction Methods for Speaker Dependent Speech Recognition

Directory of Open Access Journals (Sweden)

Gurpreet Kaur

2017-02-01

Full Text Available Speech recognition is about what is being said, irrespective of who is saying. Speech recognition is a growing field. Major progress is taking place on the technology of automatic speech recognition (ASR. Still, there are lots of barriers in this field in terms of recognition rate, background noise, speaker variability, speaking rate, accent etc. Speech recognition rate mainly depends on the selection of features and feature extraction methods. This paper outlines the feature extraction techniques for speaker dependent speech recognition for isolated words. A brief survey of different feature extraction techniques like Mel-Frequency Cepstral Coefficients (MFCC, Linear Predictive Coding Coefficients (LPCC, Perceptual Linear Prediction (PLP, Relative Spectra Perceptual linear Predictive (RASTA-PLP analysis are presented and evaluation is done. Speech recognition has various applications from daily use to commercial use. We have made a speaker dependent system and this system can be useful in many areas like controlling a patient vehicle using simple commands.

A novel murmur-based heart sound feature extraction technique using envelope-morphological analysis

Science.gov (United States)

Yao, Hao-Dong; Ma, Jia-Li; Fu, Bin-Bin; Wang, Hai-Yang; Dong, Ming-Chui

2015-07-01

Auscultation of heart sound (HS) signals serves as an important primary approach to diagnose cardiovascular diseases (CVDs) for centuries. Confronting the intrinsic drawbacks of traditional HS auscultation, computer-aided automatic HS auscultation based on feature extraction technique has witnessed explosive development. Yet, most existing HS feature extraction methods adopt acoustic or time-frequency features which exhibit poor relationship with diagnostic information, thus restricting the performance of further interpretation and analysis. Tackling such a bottleneck problem, this paper innovatively proposes a novel murmur-based HS feature extraction method since murmurs contain massive pathological information and are regarded as the first indications of pathological occurrences of heart valves. Adapting discrete wavelet transform (DWT) and Shannon envelope, the envelope-morphological characteristics of murmurs are obtained and three features are extracted accordingly. Validated by discriminating normal HS and 5 various abnormal HS signals with extracted features, the proposed method provides an attractive candidate in automatic HS auscultation.

Prostate cancer multi-feature analysis using trans-rectal ultrasound images

International Nuclear Information System (INIS)

Mohamed, S S; Salama, M M A; Kamel, M; El-Saadany, E F; Rizkalla, K; Chin, J

2005-01-01

This note focuses on extracting and analysing prostate texture features from trans-rectal ultrasound (TRUS) images for tissue characterization. One of the principal contributions of this investigation is the use of the information of the images' frequency domain features and spatial domain features to attain a more accurate diagnosis. Each image is divided into regions of interest (ROIs) by the Gabor multi-resolution analysis, a crucial stage, in which segmentation is achieved according to the frequency response of the image pixels. The pixels with a similar response to the same filter are grouped to form one ROI. Next, from each ROI two different statistical feature sets are constructed; the first set includes four grey level dependence matrix (GLDM) features and the second set consists of five grey level difference vector (GLDV) features. These constructed feature sets are then ranked by the mutual information feature selection (MIFS) algorithm. Here, the features that provide the maximum mutual information of each feature and class (cancerous and non-cancerous) and the minimum mutual information of the selected features are chosen, yeilding a reduced feature subset. The two constructed feature sets, GLDM and GLDV, as well as the reduced feature subset, are examined in terms of three different classifiers: the condensed k-nearest neighbour (CNN), the decision tree (DT) and the support vector machine (SVM). The accuracy classification results range from 87.5% to 93.75%, where the performance of the SVM and that of the DT are significantly better than the performance of the CNN. (note)

Opinion mining feature-level using Naive Bayes and feature extraction based analysis dependencies

Science.gov (United States)

Sanda, Regi; Baizal, Z. K. Abdurahman; Nhita, Fhira

2015-12-01

Development of internet and technology, has major impact and providing new business called e-commerce. Many e-commerce sites that provide convenience in transaction, and consumers can also provide reviews or opinions on products that purchased. These opinions can be used by consumers and producers. Consumers to know the advantages and disadvantages of particular feature of the product. Procuders can analyse own strengths and weaknesses as well as it's competitors products. Many opinions need a method that the reader can know the point of whole opinion. The idea emerged from review summarization that summarizes the overall opinion based on sentiment and features contain. In this study, the domain that become the main focus is about the digital camera. This research consisted of four steps 1) giving the knowledge to the system to recognize the semantic orientation of an opinion 2) indentify the features of product 3) indentify whether the opinion gives a positive or negative 4) summarizing the result. In this research discussed the methods such as Naï;ve Bayes for sentiment classification, and feature extraction algorithm based on Dependencies Analysis, which is one of the tools in Natural Language Processing (NLP) and knowledge based dictionary which is useful for handling implicit features. The end result of research is a summary that contains a bunch of reviews from consumers on the features and sentiment. With proposed method, accuration for sentiment classification giving 81.2 % for positive test data, 80.2 % for negative test data, and accuration for feature extraction reach 90.3 %.

Feature Extraction from 3D Point Cloud Data Based on Discrete Curves

Directory of Open Access Journals (Sweden)

Yi An

2013-01-01

Full Text Available Reliable feature extraction from 3D point cloud data is an important problem in many application domains, such as reverse engineering, object recognition, industrial inspection, and autonomous navigation. In this paper, a novel method is proposed for extracting the geometric features from 3D point cloud data based on discrete curves. We extract the discrete curves from 3D point cloud data and research the behaviors of chord lengths, angle variations, and principal curvatures at the geometric features in the discrete curves. Then, the corresponding similarity indicators are defined. Based on the similarity indicators, the geometric features can be extracted from the discrete curves, which are also the geometric features of 3D point cloud data. The threshold values of the similarity indicators are taken from [0,1], which characterize the relative relationship and make the threshold setting easier and more reasonable. The experimental results demonstrate that the proposed method is efficient and reliable.

Nonredundant sparse feature extraction using autoencoders with receptive fields clustering.

Science.gov (United States)

Ayinde, Babajide O; Zurada, Jacek M

2017-09-01

This paper proposes new techniques for data representation in the context of deep learning using agglomerative clustering. Existing autoencoder-based data representation techniques tend to produce a number of encoding and decoding receptive fields of layered autoencoders that are duplicative, thereby leading to extraction of similar features, thus resulting in filtering redundancy. We propose a way to address this problem and show that such redundancy can be eliminated. This yields smaller networks and produces unique receptive fields that extract distinct features. It is also shown that autoencoders with nonnegativity constraints on weights are capable of extracting fewer redundant features than conventional sparse autoencoders. The concept is illustrated using conventional sparse autoencoder and nonnegativity-constrained autoencoders with MNIST digits recognition, NORB normalized-uniform object data and Yale face dataset. Copyright © 2017 Elsevier Ltd. All rights reserved.

Annotation-based feature extraction from sets of SBML models.

Science.gov (United States)

Alm, Rebekka; Waltemath, Dagmar; Wolfien, Markus; Wolkenhauer, Olaf; Henkel, Ron

2015-01-01

Model repositories such as BioModels Database provide computational models of biological systems for the scientific community. These models contain rich semantic annotations that link model entities to concepts in well-established bio-ontologies such as Gene Ontology. Consequently, thematically similar models are likely to share similar annotations. Based on this assumption, we argue that semantic annotations are a suitable tool to characterize sets of models. These characteristics improve model classification, allow to identify additional features for model retrieval tasks, and enable the comparison of sets of models. In this paper we discuss four methods for annotation-based feature extraction from model sets. We tested all methods on sets of models in SBML format which were composed from BioModels Database. To characterize each of these sets, we analyzed and extracted concepts from three frequently used ontologies, namely Gene Ontology, ChEBI and SBO. We find that three out of the methods are suitable to determine characteristic features for arbitrary sets of models: The selected features vary depending on the underlying model set, and they are also specific to the chosen model set. We show that the identified features map on concepts that are higher up in the hierarchy of the ontologies than the concepts used for model annotations. Our analysis also reveals that the information content of concepts in ontologies and their usage for model annotation do not correlate. Annotation-based feature extraction enables the comparison of model sets, as opposed to existing methods for model-to-keyword comparison, or model-to-model comparison.

A window-based time series feature extraction method.

Science.gov (United States)

Katircioglu-Öztürk, Deniz; Güvenir, H Altay; Ravens, Ursula; Baykal, Nazife

2017-10-01

This study proposes a robust similarity score-based time series feature extraction method that is termed as Window-based Time series Feature ExtraCtion (WTC). Specifically, WTC generates domain-interpretable results and involves significantly low computational complexity thereby rendering itself useful for densely sampled and populated time series datasets. In this study, WTC is applied to a proprietary action potential (AP) time series dataset on human cardiomyocytes and three precordial leads from a publicly available electrocardiogram (ECG) dataset. This is followed by comparing WTC in terms of predictive accuracy and computational complexity with shapelet transform and fast shapelet transform (which constitutes an accelerated variant of the shapelet transform). The results indicate that WTC achieves a slightly higher classification performance with significantly lower execution time when compared to its shapelet-based alternatives. With respect to its interpretable features, WTC has a potential to enable medical experts to explore definitive common trends in novel datasets. Copyright © 2017 Elsevier Ltd. All rights reserved.

An introductory analysis of digital infrared thermal imaging guided oral cancer detection using multiresolution rotation invariant texture features

Science.gov (United States)

Chakraborty, M.; Das Gupta, R.; Mukhopadhyay, S.; Anjum, N.; Patsa, S.; Ray, J. G.

2017-03-01

This manuscript presents an analytical treatment on the feasibility of multi-scale Gabor filter bank response for non-invasive oral cancer pre-screening and detection in the long infrared spectrum. Incapability of present healthcare technology to detect oral cancer in budding stage manifests in high mortality rate. The paper contributes a step towards automation in non-invasive computer-aided oral cancer detection using an amalgamation of image processing and machine intelligence paradigms. Previous works have shown the discriminative difference of facial temperature distribution between a normal subject and a patient. The proposed work, for the first time, exploits this difference further by representing the facial Region of Interest(ROI) using multiscale rotation invariant Gabor filter bank responses followed by classification using Radial Basis Function(RBF) kernelized Support Vector Machine(SVM). The proposed study reveals an initial increase in classification accuracy with incrementing image scales followed by degradation of performance; an indication that addition of more and more finer scales tend to embed noisy information instead of discriminative texture patterns. Moreover, the performance is consistently better for filter responses from profile faces compared to frontal faces.This is primarily attributed to the ineptness of Gabor kernels to analyze low spatial frequency components over a small facial surface area. On our dataset comprising of 81 malignant, 59 pre-cancerous, and 63 normal subjects, we achieve state-of-the-art accuracy of 85.16% for normal v/s precancerous and 84.72% for normal v/s malignant classification. This sets a benchmark for further investigation of multiscale feature extraction paradigms in IR spectrum for oral cancer detection.

Facial Feature Extraction Using Frequency Map Series in PCNN

Directory of Open Access Journals (Sweden)

Rencan Nie

2016-01-01

Full Text Available Pulse coupled neural network (PCNN has been widely used in image processing. The 3D binary map series (BMS generated by PCNN effectively describes image feature information such as edges and regional distribution, so BMS can be treated as the basis of extracting 1D oscillation time series (OTS for an image. However, the traditional methods using BMS did not consider the correlation of the binary sequence in BMS and the space structure for every map. By further processing for BMS, a novel facial feature extraction method is proposed. Firstly, consider the correlation among maps in BMS; a method is put forward to transform BMS into frequency map series (FMS, and the method lessens the influence of noncontinuous feature regions in binary images on OTS-BMS. Then, by computing the 2D entropy for every map in FMS, the 3D FMS is transformed into 1D OTS (OTS-FMS, which has good geometry invariance for the facial image, and contains the space structure information of the image. Finally, by analyzing the OTS-FMS, the standard Euclidean distance is used to measure the distances for OTS-FMS. Experimental results verify the effectiveness of OTS-FMS in facial recognition, and it shows better recognition performance than other feature extraction methods.

Automated Feature Extraction from Hyperspectral Imagery, Phase II

Data.gov (United States)

National Aeronautics and Space Administration — The proposed activities will result in the development of a novel hyperspectral feature-extraction toolkit that will provide a simple, automated, and accurate...

Coding visual features extracted from video sequences.

Science.gov (United States)

Baroffio, Luca; Cesana, Matteo; Redondi, Alessandro; Tagliasacchi, Marco; Tubaro, Stefano

2014-05-01

Visual features are successfully exploited in several applications (e.g., visual search, object recognition and tracking, etc.) due to their ability to efficiently represent image content. Several visual analysis tasks require features to be transmitted over a bandwidth-limited network, thus calling for coding techniques to reduce the required bit budget, while attaining a target level of efficiency. In this paper, we propose, for the first time, a coding architecture designed for local features (e.g., SIFT, SURF) extracted from video sequences. To achieve high coding efficiency, we exploit both spatial and temporal redundancy by means of intraframe and interframe coding modes. In addition, we propose a coding mode decision based on rate-distortion optimization. The proposed coding scheme can be conveniently adopted to implement the analyze-then-compress (ATC) paradigm in the context of visual sensor networks. That is, sets of visual features are extracted from video frames, encoded at remote nodes, and finally transmitted to a central controller that performs visual analysis. This is in contrast to the traditional compress-then-analyze (CTA) paradigm, in which video sequences acquired at a node are compressed and then sent to a central unit for further processing. In this paper, we compare these coding paradigms using metrics that are routinely adopted to evaluate the suitability of visual features in the context of content-based retrieval, object recognition, and tracking. Experimental results demonstrate that, thanks to the significant coding gains achieved by the proposed coding scheme, ATC outperforms CTA with respect to all evaluation metrics.

Extraction and representation of common feature from uncertain facial expressions with cloud model.

Science.gov (United States)

Wang, Shuliang; Chi, Hehua; Yuan, Hanning; Geng, Jing

2017-12-01

Human facial expressions are key ingredient to convert an individual's innate emotion in communication. However, the variation of facial expressions affects the reliable identification of human emotions. In this paper, we present a cloud model to extract facial features for representing human emotion. First, the uncertainties in facial expression are analyzed in the context of cloud model. The feature extraction and representation algorithm is established under cloud generators. With forward cloud generator, facial expression images can be re-generated as many as we like for visually representing the extracted three features, and each feature shows different roles. The effectiveness of the computing model is tested on Japanese Female Facial Expression database. Three common features are extracted from seven facial expression images. Finally, the paper is concluded and remarked.

Feature Extraction and Fusion Using Deep Convolutional Neural Networks for Face Detection

Directory of Open Access Journals (Sweden)

Xiaojun Lu

2017-01-01

Full Text Available This paper proposes a method that uses feature fusion to represent images better for face detection after feature extraction by deep convolutional neural network (DCNN. First, with Clarifai net and VGG Net-D (16 layers, we learn features from data, respectively; then we fuse features extracted from the two nets. To obtain more compact feature representation and mitigate computation complexity, we reduce the dimension of the fused features by PCA. Finally, we conduct face classification by SVM classifier for binary classification. In particular, we exploit offset max-pooling to extract features with sliding window densely, which leads to better matches of faces and detection windows; thus the detection result is more accurate. Experimental results show that our method can detect faces with severe occlusion and large variations in pose and scale. In particular, our method achieves 89.24% recall rate on FDDB and 97.19% average precision on AFW.

Fixed kernel regression for voltammogram feature extraction

International Nuclear Information System (INIS)

Acevedo Rodriguez, F J; López-Sastre, R J; Gil-Jiménez, P; Maldonado Bascón, S; Ruiz-Reyes, N

2009-01-01

Cyclic voltammetry is an electroanalytical technique for obtaining information about substances under analysis without the need for complex flow systems. However, classifying the information in voltammograms obtained using this technique is difficult. In this paper, we propose the use of fixed kernel regression as a method for extracting features from these voltammograms, reducing the information to a few coefficients. The proposed approach has been applied to a wine classification problem with accuracy rates of over 98%. Although the method is described here for extracting voltammogram information, it can be used for other types of signals

Approximately dual frames in Hilbert spaces and applications to Gabor frames

OpenAIRE

Christensen, Ole; Laugesen, Richard S.

2011-01-01

Approximately dual frames are studied in the Hilbert space setting. Approximate duals are easier to construct than classical dual frames, and can be tailored to yield almost perfect reconstruction. Bounds on the deviation from perfect reconstruction are obtained for approximately dual frames constructed via perturbation theory. An alternative bound is derived for the rich class of Gabor frames, by using the Walnut representation of the frame operator to estimate the deviation from equality in...

a Statistical Texture Feature for Building Collapse Information Extraction of SAR Image

Science.gov (United States)

Li, L.; Yang, H.; Chen, Q.; Liu, X.

2018-04-01

Synthetic Aperture Radar (SAR) has become one of the most important ways to extract post-disaster collapsed building information, due to its extreme versatility and almost all-weather, day-and-night working capability, etc. In view of the fact that the inherent statistical distribution of speckle in SAR images is not used to extract collapsed building information, this paper proposed a novel texture feature of statistical models of SAR images to extract the collapsed buildings. In the proposed feature, the texture parameter of G0 distribution from SAR images is used to reflect the uniformity of the target to extract the collapsed building. This feature not only considers the statistical distribution of SAR images, providing more accurate description of the object texture, but also is applied to extract collapsed building information of single-, dual- or full-polarization SAR data. The RADARSAT-2 data of Yushu earthquake which acquired on April 21, 2010 is used to present and analyze the performance of the proposed method. In addition, the applicability of this feature to SAR data with different polarizations is also analysed, which provides decision support for the data selection of collapsed building information extraction.

VITALAS at TRECVID-2008

NARCIS (Netherlands)

Diou, Christos; Papachristou, Christos; Panagiotopoulos, Panagiotis; Stephanopoulos, George; Dimitriou, Nikos; Delopoulos, Anastasios; Rode, H.; Aly, Robin; de Vries, A.P.; Tsikrika, Theodora

In this paper, we present our experiments in TRECVID 2008 about High-Level feature extraction task. This is the first year for our participation in TRECVID, our system adopts some popular approaches that other workgroups proposed before. We proposed 2 advanced low-level features NEW Gabor texture

Dominant color and texture feature extraction for banknote discrimination

Science.gov (United States)

Wang, Junmin; Fan, Yangyu; Li, Ning

2017-07-01

Banknote discrimination with image recognition technology is significant in many applications. The traditional methods based on image recognition only recognize the banknote denomination without discriminating the counterfeit banknote. To solve this problem, we propose a systematical banknote discrimination approach with the dominant color and texture features. After capturing the visible and infrared images of the test banknote, we first implement the tilt correction based on the principal component analysis (PCA) algorithm. Second, we extract the dominant color feature of the visible banknote image to recognize the denomination. Third, we propose an adaptively weighted local binary pattern with "delta" tolerance algorithm to extract the texture features of the infrared banknote image. At last, we discriminate the genuine or counterfeit banknote by comparing the texture features between the test banknote and the benchmark banknote. The proposed approach is tested using 14,000 banknotes of six different denominations from Chinese yuan (CNY). The experimental results show 100% accuracy for denomination recognition and 99.92% accuracy for counterfeit banknote discrimination.

Feature extraction from multiple data sources using genetic programming.

Energy Technology Data Exchange (ETDEWEB)

Szymanski, J. J. (John J.); Brumby, Steven P.; Pope, P. A. (Paul A.); Eads, D. R. (Damian R.); Galassi, M. C. (Mark C.); Harvey, N. R. (Neal R.); Perkins, S. J. (Simon J.); Porter, R. B. (Reid B.); Theiler, J. P. (James P.); Young, A. C. (Aaron Cody); Bloch, J. J. (Jeffrey J.); David, N. A. (Nancy A.); Esch-Mosher, D. M. (Diana M.)

2002-01-01

Feature extration from imagery is an important and long-standing problem in remote sensing. In this paper, we report on work using genetic programming to perform feature extraction simultaneously from multispectral and digital elevation model (DEM) data. The tool used is the GENetic Imagery Exploitation (GENIE) software, which produces image-processing software that inherently combines spatial and spectral processing. GENIE is particularly useful in exploratory studies of imagery, such as one often does in combining data from multiple sources. The user trains the software by painting the feature of interest with a simple graphical user interface. GENIE then uses genetic programming techniques to produce an image-processing pipeline. Here, we demonstrate evolution of image processing algorithms that extract a range of land-cover features including towns, grasslands, wild fire burn scars, and several types of forest. We use imagery from the DOE/NNSA Multispectral Thermal Imager (MTI) spacecraft, fused with USGS 1:24000 scale DEM data.

Comparisons of feature extraction algorithm based on unmanned aerial vehicle image

Directory of Open Access Journals (Sweden)

Xi Wenfei

2017-07-01

Full Text Available Feature point extraction technology has become a research hotspot in the photogrammetry and computer vision. The commonly used point feature extraction operators are SIFT operator, Forstner operator, Harris operator and Moravec operator, etc. With the high spatial resolution characteristics, UAV image is different from the traditional aviation image. Based on these characteristics of the unmanned aerial vehicle (UAV, this paper uses several operators referred above to extract feature points from the building images, grassland images, shrubbery images, and vegetable greenhouses images. Through the practical case analysis, the performance, advantages, disadvantages and adaptability of each algorithm are compared and analyzed by considering their speed and accuracy. Finally, the suggestions of how to adapt different algorithms in diverse environment are proposed.

Feature extraction for dynamic integration of classifiers

NARCIS (Netherlands)

Pechenizkiy, M.; Tsymbal, A.; Puuronen, S.; Patterson, D.W.

2007-01-01

Recent research has shown the integration of multiple classifiers to be one of the most important directions in machine learning and data mining. In this paper, we present an algorithm for the dynamic integration of classifiers in the space of extracted features (FEDIC). It is based on the technique

Feature extraction with deep neural networks by a generalized discriminant analysis.

Science.gov (United States)

Stuhlsatz, André; Lippel, Jens; Zielke, Thomas

2012-04-01

We present an approach to feature extraction that is a generalization of the classical linear discriminant analysis (LDA) on the basis of deep neural networks (DNNs). As for LDA, discriminative features generated from independent Gaussian class conditionals are assumed. This modeling has the advantages that the intrinsic dimensionality of the feature space is bounded by the number of classes and that the optimal discriminant function is linear. Unfortunately, linear transformations are insufficient to extract optimal discriminative features from arbitrarily distributed raw measurements. The generalized discriminant analysis (GerDA) proposed in this paper uses nonlinear transformations that are learnt by DNNs in a semisupervised fashion. We show that the feature extraction based on our approach displays excellent performance on real-world recognition and detection tasks, such as handwritten digit recognition and face detection. In a series of experiments, we evaluate GerDA features with respect to dimensionality reduction, visualization, classification, and detection. Moreover, we show that GerDA DNNs can preprocess truly high-dimensional input data to low-dimensional representations that facilitate accurate predictions even if simple linear predictors or measures of similarity are used.

UNLABELED SELECTED SAMPLES IN FEATURE EXTRACTION FOR CLASSIFICATION OF HYPERSPECTRAL IMAGES WITH LIMITED TRAINING SAMPLES

Directory of Open Access Journals (Sweden)

A. Kianisarkaleh

2015-12-01

Full Text Available Feature extraction plays a key role in hyperspectral images classification. Using unlabeled samples, often unlimitedly available, unsupervised and semisupervised feature extraction methods show better performance when limited number of training samples exists. This paper illustrates the importance of selecting appropriate unlabeled samples that used in feature extraction methods. Also proposes a new method for unlabeled samples selection using spectral and spatial information. The proposed method has four parts including: PCA, prior classification, posterior classification and sample selection. As hyperspectral image passes these parts, selected unlabeled samples can be used in arbitrary feature extraction methods. The effectiveness of the proposed unlabeled selected samples in unsupervised and semisupervised feature extraction is demonstrated using two real hyperspectral datasets. Results show that through selecting appropriate unlabeled samples, the proposed method can improve the performance of feature extraction methods and increase classification accuracy.

DCTNet and PCANet for acoustic signal feature extraction

OpenAIRE

Xian, Yin; Thompson, Andrew; Sun, Xiaobai; Nowacek, Douglas; Nolte, Loren

2016-01-01

We introduce the use of DCTNet, an efficient approximation and alternative to PCANet, for acoustic signal classification. In PCANet, the eigenfunctions of the local sample covariance matrix (PCA) are used as filterbanks for convolution and feature extraction. When the eigenfunctions are well approximated by the Discrete Cosine Transform (DCT) functions, each layer of of PCANet and DCTNet is essentially a time-frequency representation. We relate DCTNet to spectral feature representation method...

Automatic feature extraction in large fusion databases by using deep learning approach

Energy Technology Data Exchange (ETDEWEB)

Farias, Gonzalo, E-mail: gonzalo.farias@ucv.cl [Pontificia Universidad Católica de Valparaíso, Valparaíso (Chile); Dormido-Canto, Sebastián [Departamento de Informática y Automática, UNED, Madrid (Spain); Vega, Jesús; Rattá, Giuseppe [Asociación EURATOM/CIEMAT Para Fusión, CIEMAT, Madrid (Spain); Vargas, Héctor; Hermosilla, Gabriel; Alfaro, Luis; Valencia, Agustín [Pontificia Universidad Católica de Valparaíso, Valparaíso (Chile)

2016-11-15

Highlights: • Feature extraction is a very critical stage in any machine learning algorithm. • The problem dimensionality can be reduced enormously when selecting suitable attributes. • Despite the importance of feature extraction, the process is commonly done manually by trial and error. • Fortunately, recent advances in deep learning approach have proposed an encouraging way to find a good feature representation automatically. • In this article, deep learning is applied to the TJ-II fusion database to get more robust and accurate classifiers in comparison to previous work. - Abstract: Feature extraction is one of the most important machine learning issues. Finding suitable attributes of datasets can enormously reduce the dimensionality of the input space, and from a computational point of view can help all of the following steps of pattern recognition problems, such as classification or information retrieval. However, the feature extraction step is usually performed manually. Moreover, depending on the type of data, we can face a wide range of methods to extract features. In this sense, the process to select appropriate techniques normally takes a long time. This work describes the use of recent advances in deep learning approach in order to find a good feature representation automatically. The implementation of a special neural network called sparse autoencoder and its application to two classification problems of the TJ-II fusion database is shown in detail. Results have shown that it is possible to get robust classifiers with a high successful rate, in spite of the fact that the feature space is reduced to less than 0.02% from the original one.

Automatic feature extraction in large fusion databases by using deep learning approach

International Nuclear Information System (INIS)

Farias, Gonzalo; Dormido-Canto, Sebastián; Vega, Jesús; Rattá, Giuseppe; Vargas, Héctor; Hermosilla, Gabriel; Alfaro, Luis; Valencia, Agustín

2016-01-01

Highlights: • Feature extraction is a very critical stage in any machine learning algorithm. • The problem dimensionality can be reduced enormously when selecting suitable attributes. • Despite the importance of feature extraction, the process is commonly done manually by trial and error. • Fortunately, recent advances in deep learning approach have proposed an encouraging way to find a good feature representation automatically. • In this article, deep learning is applied to the TJ-II fusion database to get more robust and accurate classifiers in comparison to previous work. - Abstract: Feature extraction is one of the most important machine learning issues. Finding suitable attributes of datasets can enormously reduce the dimensionality of the input space, and from a computational point of view can help all of the following steps of pattern recognition problems, such as classification or information retrieval. However, the feature extraction step is usually performed manually. Moreover, depending on the type of data, we can face a wide range of methods to extract features. In this sense, the process to select appropriate techniques normally takes a long time. This work describes the use of recent advances in deep learning approach in order to find a good feature representation automatically. The implementation of a special neural network called sparse autoencoder and its application to two classification problems of the TJ-II fusion database is shown in detail. Results have shown that it is possible to get robust classifiers with a high successful rate, in spite of the fact that the feature space is reduced to less than 0.02% from the original one.

Kernel-based discriminant feature extraction using a representative dataset

Science.gov (United States)

Li, Honglin; Sancho Gomez, Jose-Luis; Ahalt, Stanley C.

2002-07-01

Discriminant Feature Extraction (DFE) is widely recognized as an important pre-processing step in classification applications. Most DFE algorithms are linear and thus can only explore the linear discriminant information among the different classes. Recently, there has been several promising attempts to develop nonlinear DFE algorithms, among which is Kernel-based Feature Extraction (KFE). The efficacy of KFE has been experimentally verified by both synthetic data and real problems. However, KFE has some known limitations. First, KFE does not work well for strongly overlapped data. Second, KFE employs all of the training set samples during the feature extraction phase, which can result in significant computation when applied to very large datasets. Finally, KFE can result in overfitting. In this paper, we propose a substantial improvement to KFE that overcomes the above limitations by using a representative dataset, which consists of critical points that are generated from data-editing techniques and centroid points that are determined by using the Frequency Sensitive Competitive Learning (FSCL) algorithm. Experiments show that this new KFE algorithm performs well on significantly overlapped datasets, and it also reduces computational complexity. Further, by controlling the number of centroids, the overfitting problem can be effectively alleviated.

Driver drowsiness classification using fuzzy wavelet-packet-based feature-extraction algorithm.

Science.gov (United States)

Khushaba, Rami N; Kodagoda, Sarath; Lal, Sara; Dissanayake, Gamini

2011-01-01

Driver drowsiness and loss of vigilance are a major cause of road accidents. Monitoring physiological signals while driving provides the possibility of detecting and warning of drowsiness and fatigue. The aim of this paper is to maximize the amount of drowsiness-related information extracted from a set of electroencephalogram (EEG), electrooculogram (EOG), and electrocardiogram (ECG) signals during a simulation driving test. Specifically, we develop an efficient fuzzy mutual-information (MI)- based wavelet packet transform (FMIWPT) feature-extraction method for classifying the driver drowsiness state into one of predefined drowsiness levels. The proposed method estimates the required MI using a novel approach based on fuzzy memberships providing an accurate-information content-estimation measure. The quality of the extracted features was assessed on datasets collected from 31 drivers on a simulation test. The experimental results proved the significance of FMIWPT in extracting features that highly correlate with the different drowsiness levels achieving a classification accuracy of 95%-- 97% on an average across all subjects.

Hierarchical Feature Extraction With Local Neural Response for Image Recognition.

Science.gov (United States)

Li, Hong; Wei, Yantao; Li, Luoqing; Chen, C L P

2013-04-01

In this paper, a hierarchical feature extraction method is proposed for image recognition. The key idea of the proposed method is to extract an effective feature, called local neural response (LNR), of the input image with nontrivial discrimination and invariance properties by alternating between local coding and maximum pooling operation. The local coding, which is carried out on the locally linear manifold, can extract the salient feature of image patches and leads to a sparse measure matrix on which maximum pooling is carried out. The maximum pooling operation builds the translation invariance into the model. We also show that other invariant properties, such as rotation and scaling, can be induced by the proposed model. In addition, a template selection algorithm is presented to reduce computational complexity and to improve the discrimination ability of the LNR. Experimental results show that our method is robust to local distortion and clutter compared with state-of-the-art algorithms.

A PCA aided cross-covariance scheme for discriminative feature extraction from EEG signals.

Science.gov (United States)

Zarei, Roozbeh; He, Jing; Siuly, Siuly; Zhang, Yanchun

2017-07-01

Feature extraction of EEG signals plays a significant role in Brain-computer interface (BCI) as it can significantly affect the performance and the computational time of the system. The main aim of the current work is to introduce an innovative algorithm for acquiring reliable discriminating features from EEG signals to improve classification performances and to reduce the time complexity. This study develops a robust feature extraction method combining the principal component analysis (PCA) and the cross-covariance technique (CCOV) for the extraction of discriminatory information from the mental states based on EEG signals in BCI applications. We apply the correlation based variable selection method with the best first search on the extracted features to identify the best feature set for characterizing the distribution of mental state signals. To verify the robustness of the proposed feature extraction method, three machine learning techniques: multilayer perceptron neural networks (MLP), least square support vector machine (LS-SVM), and logistic regression (LR) are employed on the obtained features. The proposed methods are evaluated on two publicly available datasets. Furthermore, we evaluate the performance of the proposed methods by comparing it with some recently reported algorithms. The experimental results show that all three classifiers achieve high performance (above 99% overall classification accuracy) for the proposed feature set. Among these classifiers, the MLP and LS-SVM methods yield the best performance for the obtained feature. The average sensitivity, specificity and classification accuracy for these two classifiers are same, which are 99.32%, 100%, and 99.66%, respectively for the BCI competition dataset IVa and 100%, 100%, and 100%, for the BCI competition dataset IVb. The results also indicate the proposed methods outperform the most recently reported methods by at least 0.25% average accuracy improvement in dataset IVa. The execution time

A multi-approach feature extractions for iris recognition

Science.gov (United States)

Sanpachai, H.; Settapong, M.

2014-04-01

Biometrics is a promising technique that is used to identify individual traits and characteristics. Iris recognition is one of the most reliable biometric methods. As iris texture and color is fully developed within a year of birth, it remains unchanged throughout a person's life. Contrary to fingerprint, which can be altered due to several aspects including accidental damage, dry or oily skin and dust. Although iris recognition has been studied for more than a decade, there are limited commercial products available due to its arduous requirement such as camera resolution, hardware size, expensive equipment and computational complexity. However, at the present time, technology has overcome these obstacles. Iris recognition can be done through several sequential steps which include pre-processing, features extractions, post-processing, and matching stage. In this paper, we adopted the directional high-low pass filter for feature extraction. A box-counting fractal dimension and Iris code have been proposed as feature representations. Our approach has been tested on CASIA Iris Image database and the results are considered successful.

Difet: Distributed Feature Extraction Tool for High Spatial Resolution Remote Sensing Images

Science.gov (United States)

Eken, S.; Aydın, E.; Sayar, A.

2017-11-01

In this paper, we propose distributed feature extraction tool from high spatial resolution remote sensing images. Tool is based on Apache Hadoop framework and Hadoop Image Processing Interface. Two corner detection (Harris and Shi-Tomasi) algorithms and five feature descriptors (SIFT, SURF, FAST, BRIEF, and ORB) are considered. Robustness of the tool in the task of feature extraction from LandSat-8 imageries are evaluated in terms of horizontal scalability.

Fusing Facial Features for Face Recognition

Directory of Open Access Journals (Sweden)

Jamal Ahmad Dargham

2012-06-01

Full Text Available Face recognition is an important biometric method because of its potential applications in many fields, such as access control, surveillance, and human-computer interaction. In this paper, a face recognition system that fuses the outputs of three face recognition systems based on Gabor jets is presented. The first system uses the magnitude, the second uses the phase, and the third uses the phase-weighted magnitude of the jets. The jets are generated from facial landmarks selected using three selection methods. It was found out that fusing the facial features gives better recognition rate than either facial feature used individually regardless of the landmark selection method.

Extraction Of Audio Features For Emotion Recognition System Based On Music

Directory of Open Access Journals (Sweden)

Kee Moe Han

2015-08-01

Full Text Available Music is the combination of melody linguistic information and the vocalists emotion. Since music is a work of art analyzing emotion in music by computer is a difficult task. Many approaches have been developed to detect the emotions included in music but the results are not satisfactory because emotion is very complex. In this paper the evaluations of audio features from the music files are presented. The extracted features are used to classify the different emotion classes of the vocalists. Musical features extraction is done by using Music Information Retrieval MIR tool box in this paper. The database of 100 music clips are used to classify the emotions perceived in music clips. Music may contain many emotions according to the vocalists mood such as happy sad nervous bored peace etc. In this paper the audio features related to the emotions of the vocalists are extracted to use in emotion recognition system based on music.

A Study of Feature Extraction Using Divergence Analysis of Texture Features

Science.gov (United States)

Hallada, W. A.; Bly, B. G.; Boyd, R. K.; Cox, S.

1982-01-01

An empirical study of texture analysis for feature extraction and classification of high spatial resolution remotely sensed imagery (10 meters) is presented in terms of specific land cover types. The principal method examined is the use of spatial gray tone dependence (SGTD). The SGTD method reduces the gray levels within a moving window into a two-dimensional spatial gray tone dependence matrix which can be interpreted as a probability matrix of gray tone pairs. Haralick et al (1973) used a number of information theory measures to extract texture features from these matrices, including angular second moment (inertia), correlation, entropy, homogeneity, and energy. The derivation of the SGTD matrix is a function of: (1) the number of gray tones in an image; (2) the angle along which the frequency of SGTD is calculated; (3) the size of the moving window; and (4) the distance between gray tone pairs. The first three parameters were varied and tested on a 10 meter resolution panchromatic image of Maryville, Tennessee using the five SGTD measures. A transformed divergence measure was used to determine the statistical separability between four land cover categories forest, new residential, old residential, and industrial for each variation in texture parameters.

Pornographic image detection with Gabor filters

Science.gov (United States)

Durrell, Kevan; Murray, Daniel J. C.

2002-04-01

As Internet-enabled computers become ubiquitous in homes, schools, and other publicly accessible locations, there are more people 'surfing the net' who would prefer not to be exposed to offensive material. There is a lot of material freely available on the Internet that we, as a responsible and caring society, would like to keep our children from viewing. Pornographic image content is one category of material over which we would like some control. We have been conducting experiments to determine the effectiveness of using characteristic feature vectors and neural networks to identify semantic image content. This paper will describe our approach to identifying pornographic images using Gabor filters, Principal Component Analysis (PCA), Correllograms, and Neural Networks. In brief, we used a set of 5,000 typical images available from the Internet, 20% of which were judged to be pornographic, to train a neural network. We then apply the trained neural network to feature vectors from images that had not been used in training. We measure our performance as Recall, how many of the verification images labeled pornographic were correctly identified, and Precision, how many images deemed pornographic by the neural network are in fact pornographic. The set of images that were used in the experiment described in this paper for its training and validation sets are freely available on the Internet. Freely available is an important qualifier, since high-resolution, studio-quality pornographic images are often protected by portals that charge members a fee to gain access to their material. Although this is not a hard and fast rule, many of the pornographic images that are available easily and without charge on the Internet are of low image quality. Some of these images are collages or contain textual elements or have had their resolution intentionally lowered to reduce their file size. These are the offensive images that a user, without a credit card, might inadvertently come

DIFET: DISTRIBUTED FEATURE EXTRACTION TOOL FOR HIGH SPATIAL RESOLUTION REMOTE SENSING IMAGES

Directory of Open Access Journals (Sweden)

S. Eken

2017-11-01

Full Text Available In this paper, we propose distributed feature extraction tool from high spatial resolution remote sensing images. Tool is based on Apache Hadoop framework and Hadoop Image Processing Interface. Two corner detection (Harris and Shi-Tomasi algorithms and five feature descriptors (SIFT, SURF, FAST, BRIEF, and ORB are considered. Robustness of the tool in the task of feature extraction from LandSat-8 imageries are evaluated in terms of horizontal scalability.

Feature extraction and sensor selection for NPP initiating event identification

International Nuclear Information System (INIS)

Lin, Ting-Han; Wu, Shun-Chi; Chen, Kuang-You; Chou, Hwai-Pwu

2017-01-01

Highlights: • A two-stage feature extraction scheme for NPP initiating event identification. • With stBP, interrelations among the sensors can be retained for identification. • With dSFS, sensors that are crucial for identification can be efficiently selected. • Efficacy of the scheme is illustrated with data from the Maanshan NPP simulator. - Abstract: Initiating event identification is essential in managing nuclear power plant (NPP) severe accidents. In this paper, a novel two-stage feature extraction scheme that incorporates the proposed sensor type-wise block projection (stBP) and deflatable sequential forward selection (dSFS) is used to elicit the discriminant information in the data obtained from various NPP sensors to facilitate event identification. With the stBP, the primal features can be extracted without eliminating the interrelations among the sensors of the same type. The extracted features are then subjected to a further dimensionality reduction by selecting the sensors that are most relevant to the events under consideration. This selection is not easy, and a combinatorial optimization technique is normally required. With the dSFS, an optimal sensor set can be found with less computational load. Moreover, its sensor deflation stage allows sensors in the preselected set to be iteratively refined to avoid being trapped into a local optimum. Results from detailed experiments containing data of 12 event categories and a total of 112 events generated with a Taiwan’s Maanshan NPP simulator are presented to illustrate the efficacy of the proposed scheme.

Human listening studies reveal insights into object features extracted by echolocating dolphins

Science.gov (United States)

Delong, Caroline M.; Au, Whitlow W. L.; Roitblat, Herbert L.

2004-05-01

Echolocating dolphins extract object feature information from the acoustic parameters of object echoes. However, little is known about which object features are salient to dolphins or how they extract those features. To gain insight into how dolphins might be extracting feature information, human listeners were presented with echoes from objects used in a dolphin echoic-visual cross-modal matching task. Human participants performed a task similar to the one the dolphin had performed; however, echoic samples consisting of 23-echo trains were presented via headphones. The participants listened to the echoic sample and then visually selected the correct object from among three alternatives. The participants performed as well as or better than the dolphin (M=88.0% correct), and reported using a combination of acoustic cues to extract object features (e.g., loudness, pitch, timbre). Participants frequently reported using the pattern of aural changes in the echoes across the echo train to identify the shape and structure of the objects (e.g., peaks in loudness or pitch). It is likely that dolphins also attend to the pattern of changes across echoes as objects are echolocated from different angles.

Level Sets and Voronoi based Feature Extraction from any Imagery

DEFF Research Database (Denmark)

Sharma, O.; Anton, François; Mioc, Darka

2012-01-01

Polygon features are of interest in many GEOProcessing applications like shoreline mapping, boundary delineation, change detection, etc. This paper presents a unique new GPU-based methodology to automate feature extraction combining level sets, or mean shift based segmentation together with Voron...

Gabor windows supported on [-1,1] and compactly supported dual windows

DEFF Research Database (Denmark)

Christensen, Ole; Kim, H. O.; Rae Young, Kim

2010-01-01

window. More precisely, we show that if b window supported on [-N, N]. Under the additional assumption that g is continuous and only has a finite number of zeros on inverted left perpendicular-1, 1inverted right perpendicular, we...... characterize the frame property of {E(mb)T(n)g}(m,n is an element of Z). As a consequence we obtain easily verifiable criteria for a function g to generate a Gabor frame with a dual window having compact support of prescribed size....

Accurate facade feature extraction method for buildings from three-dimensional point cloud data considering structural information

Science.gov (United States)

Wang, Yongzhi; Ma, Yuqing; Zhu, A.-xing; Zhao, Hui; Liao, Lixia

2018-05-01

Facade features represent segmentations of building surfaces and can serve as a building framework. Extracting facade features from three-dimensional (3D) point cloud data (3D PCD) is an efficient method for 3D building modeling. By combining the advantages of 3D PCD and two-dimensional optical images, this study describes the creation of a highly accurate building facade feature extraction method from 3D PCD with a focus on structural information. The new extraction method involves three major steps: image feature extraction, exploration of the mapping method between the image features and 3D PCD, and optimization of the initial 3D PCD facade features considering structural information. Results show that the new method can extract the 3D PCD facade features of buildings more accurately and continuously. The new method is validated using a case study. In addition, the effectiveness of the new method is demonstrated by comparing it with the range image-extraction method and the optical image-extraction method in the absence of structural information. The 3D PCD facade features extracted by the new method can be applied in many fields, such as 3D building modeling and building information modeling.

Crowding with conjunctions of simple features.

Science.gov (United States)

Põder, Endel; Wagemans, Johan

2007-11-20

Several recent studies have related crowding with the feature integration stage in visual processing. In order to understand the mechanisms involved in this stage, it is important to use stimuli that have several features to integrate, and these features should be clearly defined and measurable. In this study, Gabor patches were used as target and distractor stimuli. The stimuli differed in three dimensions: spatial frequency, orientation, and color. A group of 3, 5, or 7 objects was presented briefly at 4 deg eccentricity of the visual field. The observers' task was to identify the object located in the center of the group. A strong effect of the number of distractors was observed, consistent with various spatial pooling models. The analysis of incorrect responses revealed that these were a mix of feature errors and mislocalizations of the target object. Feature errors were not purely random, but biased by the features of distractors. We propose a simple feature integration model that predicts most of the observed regularities.

Image features for misalignment correction in medical flat-detector CT

International Nuclear Information System (INIS)

Wicklein, Julia; Kunze, Holger; Kalender, Willi A.; Kyriakou, Yiannis

2012-01-01

Purpose: Misalignment artifacts are a serious problem in medical flat-detector computed tomography. Generally, the geometrical parameters, which are essential for reconstruction, are provided by preceding calibration routines. These procedures are time consuming and the later use of stored parameters is sensitive toward external impacts or patient movement. The method of choice in a clinical environment would be a markerless online-calibration procedure that allows flexible scan trajectories and simultaneously corrects misalignment and motion artifacts during the reconstruction process. Therefore, different image features were evaluated according to their capability of quantifying misalignment. Methods: Projections of the FORBILD head and thorax phantoms were simulated. Additionally, acquisitions of a head phantom and patient data were used for evaluation. For the reconstruction different sources and magnitudes of misalignment were introduced in the geometry description. The resulting volumes were analyzed by entropy (based on the gray-level histogram), total variation, Gabor filter texture features, Haralick co-occurrence features, and Tamura texture features. The feature results were compared to the back-projection mismatch of the disturbed geometry. Results: The evaluations demonstrate the ability of several well-established image features to classify misalignment. The authors elaborated the particular suitability of the gray-level histogram-based entropy on identifying misalignment artifacts, after applying an appropriate window level (bone window). Conclusions: Some of the proposed feature extraction algorithms show a strong correlation with the misalignment level. Especially, entropy-based methods showed very good correspondence, with the best of these being the type that uses the gray-level histogram for calculation. This makes it a suitable image feature for online-calibration.

The algorithm of fast image stitching based on multi-feature extraction

Science.gov (United States)

Yang, Chunde; Wu, Ge; Shi, Jing

2018-05-01

This paper proposed an improved image registration method combining Hu-based invariant moment contour information and feature points detection, aiming to solve the problems in traditional image stitching algorithm, such as time-consuming feature points extraction process, redundant invalid information overload and inefficiency. First, use the neighborhood of pixels to extract the contour information, employing the Hu invariant moment as similarity measure to extract SIFT feature points in those similar regions. Then replace the Euclidean distance with Hellinger kernel function to improve the initial matching efficiency and get less mismatching points, further, estimate affine transformation matrix between the images. Finally, local color mapping method is adopted to solve uneven exposure, using the improved multiresolution fusion algorithm to fuse the mosaic images and realize seamless stitching. Experimental results confirm high accuracy and efficiency of method proposed in this paper.

PyEEG: An Open Source Python Module for EEG/MEG Feature Extraction

OpenAIRE

Bao, Forrest Sheng; Liu, Xin; Zhang, Christina

2011-01-01

Computer-aided diagnosis of neural diseases from EEG signals (or other physiological signals that can be treated as time series, e.g., MEG) is an emerging field that has gained much attention in past years. Extracting features is a key component in the analysis of EEG signals. In our previous works, we have implemented many EEG feature extraction functions in the Python programming language. As Python is gaining more ground in scientific computing, an open source Python module for extracting ...

Research on feature extraction techniques of Hainan Li brocade pattern

Science.gov (United States)

Zhou, Yuping; Chen, Fuqiang; Zhou, Yuhua

2016-03-01

Hainan Li brocade skills has been listed as world non-material cultural heritage preservation, therefore, the research on Hainan Li brocade patterns plays an important role in Li brocade culture inheritance. The meaning of Li brocade patterns was analyzed and the shape feature extraction techniques to original Li brocade patterns were advanced in this paper, based on the contour tracking algorithm. First, edge detection was made on the design patterns, and then the morphological closing operation was used to smooth the image, and finally contour tracking was used to extract the outer contours of Li brocade patterns. The extracted contour features were processed by means of morphology, and digital characteristics of contours are obtained by invariant moments. At last, different patterns of Li brocade design are briefly analyzed according to the digital characteristics. The results showed that the pattern extraction method to Li brocade pattern shapes is feasible and effective according to above method.

Forged Signature Distinction Using Convolutional Neural Network for Feature Extraction

Directory of Open Access Journals (Sweden)

Seungsoo Nam

2018-01-01

Full Text Available This paper proposes a dynamic verification scheme for finger-drawn signatures in smartphones. As a dynamic feature, the movement of a smartphone is recorded with accelerometer sensors in the smartphone, in addition to the moving coordinates of the signature. To extract high-level longitudinal and topological features, the proposed scheme uses a convolution neural network (CNN for feature extraction, and not as a conventional classifier. We assume that a CNN trained with forged signatures can extract effective features (called S-vector, which are common in forging activities such as hesitation and delay before drawing the complicated part. The proposed scheme also exploits an autoencoder (AE as a classifier, and the S-vector is used as the input vector to the AE. An AE has high accuracy for the one-class distinction problem such as signature verification, and is also greatly dependent on the accuracy of input data. S-vector is valuable as the input of AE, and, consequently, could lead to improved verification accuracy especially for distinguishing forged signatures. Compared to the previous work, i.e., the MLP-based finger-drawn signature verification scheme, the proposed scheme decreases the equal error rate by 13.7%, specifically, from 18.1% to 4.4%, for discriminating forged signatures.

Image feature extraction based on the camouflage effectiveness evaluation

Science.gov (United States)

Yuan, Xin; Lv, Xuliang; Li, Ling; Wang, Xinzhu; Zhang, Zhi

2018-04-01

The key step of camouflage effectiveness evaluation is how to combine the human visual physiological features, psychological features to select effectively evaluation indexes. Based on the predecessors' camo comprehensive evaluation method, this paper chooses the suitable indexes combining with the image quality awareness, and optimizes those indexes combining with human subjective perception. Thus, it perfects the theory of index extraction.

Feature-extraction algorithms for the PANDA electromagnetic calorimeter

NARCIS (Netherlands)

Kavatsyuk, M.; Guliyev, E.; Lemmens, P. J. J.; Loehner, H.; Poelman, T. P.; Tambave, G.; Yu, B

2009-01-01

The feature-extraction algorithms are discussed which have been developed for the digital front-end electronics of the electromagnetic calorimeter of the PANDA detector at the future FAIR facility. Performance parameters have been derived in test measurements with cosmic rays, particle and photon

Gabor windows supported on [ − 1, 1] and dual windows with small support

DEFF Research Database (Denmark)

Christensen, Ole; Kim, Hong Oh; Kim, Rae Young

2012-01-01

Consider a continuous function g ∈ L 2(ℝ) that is supported on [ − 1, 1] and generates a Gabor frame with translation parameter 1 and modulation parameter 0 for some N ∈ ℕ. Under an extra condition on the zeroset of the window g we show that there exists a continuous dual window supported on [ − N...

Joint Feature Extraction and Classifier Design for ECG-Based Biometric Recognition.

Science.gov (United States)

Gutta, Sandeep; Cheng, Qi

2016-03-01

Traditional biometric recognition systems often utilize physiological traits such as fingerprint, face, iris, etc. Recent years have seen a growing interest in electrocardiogram (ECG)-based biometric recognition techniques, especially in the field of clinical medicine. In existing ECG-based biometric recognition methods, feature extraction and classifier design are usually performed separately. In this paper, a multitask learning approach is proposed, in which feature extraction and classifier design are carried out simultaneously. Weights are assigned to the features within the kernel of each task. We decompose the matrix consisting of all the feature weights into sparse and low-rank components. The sparse component determines the features that are relevant to identify each individual, and the low-rank component determines the common feature subspace that is relevant to identify all the subjects. A fast optimization algorithm is developed, which requires only the first-order information. The performance of the proposed approach is demonstrated through experiments using the MIT-BIH Normal Sinus Rhythm database.

Pengenalan Wajah Pada Sistem Presensi Menggunakan Metode Dynamic Times Wrapping, Principal Component Analysis dan Gabor Wavelet

Directory of Open Access Journals (Sweden)

Romi Wiryadinata

2016-03-01

Full Text Available Presensi is a logging attendance, part of activity reporting an institution, or a component institution itself which contains the presence data compiled and arranged so that it is easy to search for and used when required at any time by the parties concerned. Computer application developed in the presensi system is a computer application that can recognize a person's face using only a webcam. Face recognition in this study using a webcam to capture an image of the room at any given time who later identified the existing faces. Some of the methods used in the research here is a method of the Dynamic Times Wrapping (DTW, Principal Component Analysis (PCA and Gabor Wavelet. This system, used in testing with normal facial image expression. The success rate of the introduction with the normal expression of face image using DTW amounting to 80%, 100% and PCA Gabor wavelet 97%

A Generic multi-dimensional feature extraction method using multiobjective genetic programming.

Science.gov (United States)

Zhang, Yang; Rockett, Peter I

2009-01-01

In this paper, we present a generic feature extraction method for pattern classification using multiobjective genetic programming. This not only evolves the (near-)optimal set of mappings from a pattern space to a multi-dimensional decision space, but also simultaneously optimizes the dimensionality of that decision space. The presented framework evolves vector-to-vector feature extractors that maximize class separability. We demonstrate the efficacy of our approach by making statistically-founded comparisons with a wide variety of established classifier paradigms over a range of datasets and find that for most of the pairwise comparisons, our evolutionary method delivers statistically smaller misclassification errors. At very worst, our method displays no statistical difference in a few pairwise comparisons with established classifier/dataset combinations; crucially, none of the misclassification results produced by our method is worse than any comparator classifier. Although principally focused on feature extraction, feature selection is also performed as an implicit side effect; we show that both feature extraction and selection are important to the success of our technique. The presented method has the practical consequence of obviating the need to exhaustively evaluate a large family of conventional classifiers when faced with a new pattern recognition problem in order to attain a good classification accuracy.

FAST DISCRETE CURVELET TRANSFORM BASED ANISOTROPIC FEATURE EXTRACTION FOR IRIS RECOGNITION

Directory of Open Access Journals (Sweden)

Amol D. Rahulkar

2010-11-01

Full Text Available The feature extraction plays a very important role in iris recognition. Recent researches on multiscale analysis provide good opportunity to extract more accurate information for iris recognition. In this work, a new directional iris texture features based on 2-D Fast Discrete Curvelet Transform (FDCT is proposed. The proposed approach divides the normalized iris image into six sub-images and the curvelet transform is applied independently on each sub-image. The anisotropic feature vector for each sub-image is derived using the directional energies of the curvelet coefficients. These six feature vectors are combined to create the resultant feature vector. During recognition, the nearest neighbor classifier based on Euclidean distance has been used for authentication. The effectiveness of the proposed approach has been tested on two different databases namely UBIRIS and MMU1. Experimental results show the superiority of the proposed approach.

An Accurate Integral Method for Vibration Signal Based on Feature Information Extraction

Directory of Open Access Journals (Sweden)

Yong Zhu

2015-01-01

Full Text Available After summarizing the advantages and disadvantages of current integral methods, a novel vibration signal integral method based on feature information extraction was proposed. This method took full advantage of the self-adaptive filter characteristic and waveform correction feature of ensemble empirical mode decomposition in dealing with nonlinear and nonstationary signals. This research merged the superiorities of kurtosis, mean square error, energy, and singular value decomposition on signal feature extraction. The values of the four indexes aforementioned were combined into a feature vector. Then, the connotative characteristic components in vibration signal were accurately extracted by Euclidean distance search, and the desired integral signals were precisely reconstructed. With this method, the interference problem of invalid signal such as trend item and noise which plague traditional methods is commendably solved. The great cumulative error from the traditional time-domain integral is effectively overcome. Moreover, the large low-frequency error from the traditional frequency-domain integral is successfully avoided. Comparing with the traditional integral methods, this method is outstanding at removing noise and retaining useful feature information and shows higher accuracy and superiority.

Towards Home-Made Dictionaries for Musical Feature Extraction

DEFF Research Database (Denmark)

Harbo, Anders La-Cour

2003-01-01

arguably unnecessary limitations on the ability of the transform to extract and identify features. However, replacing the nicely structured dictionary of the Fourier transform (or indeed other nice transform such as the wavelet transform) with a home-made dictionary is a dangerous task, since even the most...

A threshold auto-adjustment algorithm of feature points extraction based on grid

Science.gov (United States)

Yao, Zili; Li, Jun; Dong, Gaojie

2018-02-01

When dealing with high-resolution digital images, detection of feature points is usually the very first important step. Valid feature points depend on the threshold. If the threshold is too low, plenty of feature points will be detected, and they may be aggregated in the rich texture regions, which consequently not only affects the speed of feature description, but also aggravates the burden of following processing; if the threshold is set high, the feature points in poor texture area will lack. To solve these problems, this paper proposes a threshold auto-adjustment method of feature extraction based on grid. By dividing the image into numbers of grid, threshold is set in every local grid for extracting the feature points. When the number of feature points does not meet the threshold requirement, the threshold will be adjusted automatically to change the final number of feature points The experimental results show that feature points produced by our method is more uniform and representative, which avoids the aggregation of feature points and greatly reduces the complexity of following work.

A Relation Extraction Framework for Biomedical Text Using Hybrid Feature Set

Directory of Open Access Journals (Sweden)

Abdul Wahab Muzaffar

2015-01-01

Full Text Available The information extraction from unstructured text segments is a complex task. Although manual information extraction often produces the best results, it is harder to manage biomedical data extraction manually because of the exponential increase in data size. Thus, there is a need for automatic tools and techniques for information extraction in biomedical text mining. Relation extraction is a significant area under biomedical information extraction that has gained much importance in the last two decades. A lot of work has been done on biomedical relation extraction focusing on rule-based and machine learning techniques. In the last decade, the focus has changed to hybrid approaches showing better results. This research presents a hybrid feature set for classification of relations between biomedical entities. The main contribution of this research is done in the semantic feature set where verb phrases are ranked using Unified Medical Language System (UMLS and a ranking algorithm. Support Vector Machine and Naïve Bayes, the two effective machine learning techniques, are used to classify these relations. Our approach has been validated on the standard biomedical text corpus obtained from MEDLINE 2001. Conclusively, it can be articulated that our framework outperforms all state-of-the-art approaches used for relation extraction on the same corpus.

Extracted facial feature of racial closely related faces

Science.gov (United States)

Liewchavalit, Chalothorn; Akiba, Masakazu; Kanno, Tsuneo; Nagao, Tomoharu

2010-02-01

Human faces contain a lot of demographic information such as identity, gender, age, race and emotion. Human being can perceive these pieces of information and use it as an important clue in social interaction with other people. Race perception is considered the most delicacy and sensitive parts of face perception. There are many research concerning image-base race recognition, but most of them are focus on major race group such as Caucasoid, Negroid and Mongoloid. This paper focuses on how people classify race of the racial closely related group. As a sample of racial closely related group, we choose Japanese and Thai face to represents difference between Northern and Southern Mongoloid. Three psychological experiment was performed to study the strategies of face perception on race classification. As a result of psychological experiment, it can be suggested that race perception is an ability that can be learn. Eyes and eyebrows are the most attention point and eyes is a significant factor in race perception. The Principal Component Analysis (PCA) was performed to extract facial features of sample race group. Extracted race features of texture and shape were used to synthesize faces. As the result, it can be suggested that racial feature is rely on detailed texture rather than shape feature. This research is a indispensable important fundamental research on the race perception which are essential in the establishment of human-like race recognition system.

Feature extraction using convolutional neural network for classifying breast density in mammographic images

Science.gov (United States)

Thomaz, Ricardo L.; Carneiro, Pedro C.; Patrocinio, Ana C.

2017-03-01

Breast cancer is the leading cause of death for women in most countries. The high levels of mortality relate mostly to late diagnosis and to the direct proportionally relationship between breast density and breast cancer development. Therefore, the correct assessment of breast density is important to provide better screening for higher risk patients. However, in modern digital mammography the discrimination among breast densities is highly complex due to increased contrast and visual information for all densities. Thus, a computational system for classifying breast density might be a useful tool for aiding medical staff. Several machine-learning algorithms are already capable of classifying small number of classes with good accuracy. However, machinelearning algorithms main constraint relates to the set of features extracted and used for classification. Although well-known feature extraction techniques might provide a good set of features, it is a complex task to select an initial set during design of a classifier. Thus, we propose feature extraction using a Convolutional Neural Network (CNN) for classifying breast density by a usual machine-learning classifier. We used 307 mammographic images downsampled to 260x200 pixels to train a CNN and extract features from a deep layer. After training, the activation of 8 neurons from a deep fully connected layer are extracted and used as features. Then, these features are feedforward to a single hidden layer neural network that is cross-validated using 10-folds to classify among four classes of breast density. The global accuracy of this method is 98.4%, presenting only 1.6% of misclassification. However, the small set of samples and memory constraints required the reuse of data in both CNN and MLP-NN, therefore overfitting might have influenced the results even though we cross-validated the network. Thus, although we presented a promising method for extracting features and classifying breast density, a greater database is

Image Processing and Features Extraction of Fingerprint Images ...

African Journals Online (AJOL)

To demonstrate the importance of the image processing of fingerprint images prior to image enrolment or comparison, the set of fingerprint images in databases (a) and (b) of the FVC (Fingerprint Verification Competition) 2000 database were analyzed using a features extraction algorithm. This paper presents the results of ...

Extracting foreground ensemble features to detect abnormal crowd behavior in intelligent video-surveillance systems

Science.gov (United States)

Chan, Yi-Tung; Wang, Shuenn-Jyi; Tsai, Chung-Hsien

2017-09-01

Public safety is a matter of national security and people's livelihoods. In recent years, intelligent video-surveillance systems have become important active-protection systems. A surveillance system that provides early detection and threat assessment could protect people from crowd-related disasters and ensure public safety. Image processing is commonly used to extract features, e.g., people, from a surveillance video. However, little research has been conducted on the relationship between foreground detection and feature extraction. Most current video-surveillance research has been developed for restricted environments, in which the extracted features are limited by having information from a single foreground; they do not effectively represent the diversity of crowd behavior. This paper presents a general framework based on extracting ensemble features from the foreground of a surveillance video to analyze a crowd. The proposed method can flexibly integrate different foreground-detection technologies to adapt to various monitored environments. Furthermore, the extractable representative features depend on the heterogeneous foreground data. Finally, a classification algorithm is applied to these features to automatically model crowd behavior and distinguish an abnormal event from normal patterns. The experimental results demonstrate that the proposed method's performance is both comparable to that of state-of-the-art methods and satisfies the requirements of real-time applications.

Javanese Character Feature Extraction Based on Shape Energy

Directory of Open Access Journals (Sweden)

Galih Hendra Wibowo

2017-07-01

Full Text Available Javanese character is one of Indonesia's noble culture, especially in Java. However, the number of Javanese people who are able to read the letter has decreased so that there need to be conservation efforts in the form of a system that is able to recognize the characters. One solution to these problem lies in Optical Character Recognition (OCR studies, where one of its heaviest points lies in feature extraction which is to distinguish each character. Shape Energy is one of feature extraction method with the basic idea of how the character can be distinguished simply through its skeleton. Based on the basic idea, then the development of feature extraction is done based on its components to produce an angular histogram with various variations of multiples angle. Furthermore, the performance test of this method and its basic method is performed in Javanese character dataset, which has been obtained from various images, is 240 data with 19 labels by using K-Nearest Neighbors as its classification method. Performance values were obtained based on the accuracy which is generated through the Cross-Validation process of 80.83% in the angular histogram with an angle of 20 degrees, 23% better than Shape Energy. In addition, other test results show that this method is able to recognize rotated character with the lowest performance value of 86% at 180-degree rotation and the highest performance value of 96.97% at 90-degree rotation. It can be concluded that this method is able to improve the performance of Shape Energy in the form of recognition of Javanese characters as well as robust to the rotation.

A feature extraction algorithm based on corner and spots in self-driving vehicles

Directory of Open Access Journals (Sweden)

Yupeng FENG

2017-06-01

Full Text Available To solve the poor real-time performance problem of the visual odometry based on embedded system with limited computing resources, an image matching method based on Harris and SIFT is proposed, namely the Harris-SIFT algorithm. On the basis of the review of SIFT algorithm, the principle of Harris-SIFT algorithm is provided. First, Harris algorithm is used to extract the corners of the image as candidate feature points, and scale invariant feature transform (SIFT features are extracted from those candidate feature points. At last, through an example, the algorithm is simulated by Matlab, then the complexity and other performance of the algorithm are analyzed. The experimental results show that the proposed method reduces the computational complexity and improves the speed of feature extraction. Harris-SIFT algorithm can be used in the real-time vision odometer system, and will bring about a wide application of visual odometry in embedded navigation system.

Chemical-induced disease relation extraction with various linguistic features.

Science.gov (United States)

Gu, Jinghang; Qian, Longhua; Zhou, Guodong

2016-01-01

Understanding the relations between chemicals and diseases is crucial in various biomedical tasks such as new drug discoveries and new therapy developments. While manually mining these relations from the biomedical literature is costly and time-consuming, such a procedure is often difficult to keep up-to-date. To address these issues, the BioCreative-V community proposed a challenging task of automatic extraction of chemical-induced disease (CID) relations in order to benefit biocuration. This article describes our work on the CID relation extraction task on the BioCreative-V tasks. We built a machine learning based system that utilized simple yet effective linguistic features to extract relations with maximum entropy models. In addition to leveraging various features, the hypernym relations between entity concepts derived from the Medical Subject Headings (MeSH)-controlled vocabulary were also employed during both training and testing stages to obtain more accurate classification models and better extraction performance, respectively. We demoted relation extraction between entities in documents to relation extraction between entity mentions. In our system, pairs of chemical and disease mentions at both intra- and inter-sentence levels were first constructed as relation instances for training and testing, then two classification models at both levels were trained from the training examples and applied to the testing examples. Finally, we merged the classification results from mention level to document level to acquire final relations between chemicals and diseases. Our system achieved promisingF-scores of 60.4% on the development dataset and 58.3% on the test dataset using gold-standard entity annotations, respectively. Database URL:https://github.com/JHnlp/BC5CIDTask. © The Author(s) 2016. Published by Oxford University Press.

Analysis of Time n Frequency EEG Feature Extraction Methods for Mental Task Classification

Directory of Open Access Journals (Sweden)

Caglar Uyulan

2017-01-01

Full Text Available Many endogenous and external components may affect the physiological, mental and behavioral states in humans. Monitoring tools are required to evaluate biomarkers, identify biological events, and predict their outcomes. Being one of the valuable indicators, brain biomarkers derived from temporal or spectral electroencephalography (EEG signals processing, allow for the classification of mental disorders and mental tasks. An EEG signal has a nonstationary nature and individual frequency feature, hence it can be concluded that each subject has peculiar timing and data to extract unique features. In order to classify data, which are collected by performing four mental task (reciting the alphabet backwards, imagination of rotation of a cube, imagination of right hand movements (open/close and performing mathematical operations, discriminative features were extracted using four competitive time-frequency techniques; Wavelet Packet Decomposition (WPD, Morlet Wavelet Transform (MWT, Short Time Fourier Transform (STFT and Wavelet Filter Bank (WFB, respectively. The extracted features using both time and frequency domain information were then reduced using a principal component analysis for subset reduction. Finally, the reduced subsets were fed into a multi-layer perceptron neural network (MP-NN trained with back propagation (BP algorithm to generate a predictive model. This study mainly focuses on comparing the relative performance of time-frequency feature extraction methods that are used to classify mental tasks. The real-time (RT conducted experimental results underlined that the WPD feature extraction method outperforms with 92% classification accuracy compared to three other aforementioned methods for four different mental tasks.

Automatic segmentation of blood vessels from retinal fundus images ...

Indian Academy of Sciences (India)

The retinal blood vessels were segmented through color space conversion and color channel extraction, image pre-processing, Gabor filtering, image postprocessing, feature construction through application of principal component analysis, k-means clustering and first level classification using Naïve–Bayes classification ...

SAR Data Fusion Imaging Method Oriented to Target Feature Extraction

Directory of Open Access Journals (Sweden)

Yang Wei

2015-02-01

Full Text Available To deal with the difficulty for target outlines extracting precisely due to neglect of target scattering characteristic variation during the processing of high-resolution space-borne SAR data, a novel fusion imaging method is proposed oriented to target feature extraction. Firstly, several important aspects that affect target feature extraction and SAR image quality are analyzed, including curved orbit, stop-and-go approximation, atmospheric delay, and high-order residual phase error. Furthermore, the corresponding compensation methods are addressed as well. Based on the analysis, the mathematical model of SAR echo combined with target space-time spectrum is established for explaining the space-time-frequency change rule of target scattering characteristic. Moreover, a fusion imaging strategy and method under high-resolution and ultra-large observation angle range conditions are put forward to improve SAR quality by fusion processing in range-doppler and image domain. Finally, simulations based on typical military targets are used to verify the effectiveness of the fusion imaging method.

Sensor-Based Auto-Focusing System Using Multi-Scale Feature Extraction and Phase Correlation Matching

Directory of Open Access Journals (Sweden)

Jinbeum Jang

2015-03-01

Full Text Available This paper presents a novel auto-focusing system based on a CMOS sensor containing pixels with different phases. Robust extraction of features in a severely defocused image is the fundamental problem of a phase-difference auto-focusing system. In order to solve this problem, a multi-resolution feature extraction algorithm is proposed. Given the extracted features, the proposed auto-focusing system can provide the ideal focusing position using phase correlation matching. The proposed auto-focusing (AF algorithm consists of four steps: (i acquisition of left and right images using AF points in the region-of-interest; (ii feature extraction in the left image under low illumination and out-of-focus blur; (iii the generation of two feature images using the phase difference between the left and right images; and (iv estimation of the phase shifting vector using phase correlation matching. Since the proposed system accurately estimates the phase difference in the out-of-focus blurred image under low illumination, it can provide faster, more robust auto focusing than existing systems.

Blood Vessel Extraction in Color Retinal Fundus Images with Enhancement Filtering and Unsupervised Classification

Directory of Open Access Journals (Sweden)

Zafer Yavuz

2017-01-01

Full Text Available Retinal blood vessels have a significant role in the diagnosis and treatment of various retinal diseases such as diabetic retinopathy, glaucoma, arteriosclerosis, and hypertension. For this reason, retinal vasculature extraction is important in order to help specialists for the diagnosis and treatment of systematic diseases. In this paper, a novel approach is developed to extract retinal blood vessel network. Our method comprises four stages: (1 preprocessing stage in order to prepare dataset for segmentation; (2 an enhancement procedure including Gabor, Frangi, and Gauss filters obtained separately before a top-hat transform; (3 a hard and soft clustering stage which includes K-means and Fuzzy C-means (FCM in order to get binary vessel map; and (4 a postprocessing step which removes falsely segmented isolated regions. The method is tested on color retinal images obtained from STARE and DRIVE databases which are available online. As a result, Gabor filter followed by K-means clustering method achieves 95.94% and 95.71% of accuracy for STARE and DRIVE databases, respectively, which are acceptable for diagnosis systems.

Feature extraction from mammographic images using fast marching methods

International Nuclear Information System (INIS)

Bottigli, U.; Golosio, B.

2002-01-01

Features extraction from medical images represents a fundamental step for shape recognition and diagnostic support. The present work faces the problem of the detection of large features, such as massive lesions and organ contours, from mammographic images. The regions of interest are often characterized by an average grayness intensity that is different from the surrounding. In most cases, however, the desired features cannot be extracted by simple gray level thresholding, because of image noise and non-uniform density of the surrounding tissue. In this work, edge detection is achieved through the fast marching method (Level Set Methods and Fast Marching Methods, Cambridge University Press, Cambridge, 1999), which is based on the theory of interface evolution. Starting from a seed point in the shape of interest, a front is generated which evolves according to an appropriate speed function. Such function is expressed in terms of geometric properties of the evolving interface and of image properties, and should become zero when the front reaches the desired boundary. Some examples of application of such method to mammographic images from the CALMA database (Nucl. Instr. and Meth. A 460 (2001) 107) are presented here and discussed

Feature extraction for SAR target recognition based on supervised manifold learning

International Nuclear Information System (INIS)

Du, C; Zhou, S; Sun, J; Zhao, J

2014-01-01

On the basis of manifold learning theory, a new feature extraction method for Synthetic aperture radar (SAR) target recognition is proposed. First, the proposed algorithm estimates the within-class and between-class local neighbourhood surrounding each SAR sample. After computing the local tangent space for each neighbourhood, the proposed algorithm seeks for the optimal projecting matrix by preserving the local within-class property and simultaneously maximizing the local between-class separability. The use of uncorrelated constraint can also enhance the discriminating power of the optimal projecting matrix. Finally, the nearest neighbour classifier is applied to recognize SAR targets in the projected feature subspace. Experimental results on MSTAR datasets demonstrate that the proposed method can provide a higher recognition rate than traditional feature extraction algorithms in SAR target recognition

Extraction of Coal and Gangue Geometric Features with Multifractal Detrending Fluctuation Analysis

Directory of Open Access Journals (Sweden)

Kai Liu

2018-03-01

Full Text Available The separation of coal and gangue is an important process of the coal preparation technology. The conventional way of manual selection and separation of gangue from the raw coal can be replaced by computer vision technology. In the literature, research on image recognition and classification of coal and gangue is mainly based on the grayscale and texture features of the coal and gangue. However, there are few studies on characteristics of coal and gangue from the perspective of their outline differences. Therefore, the multifractal detrended fluctuation analysis (MFDFA method is introduced in this paper to extract the geometric features of coal and gangue. Firstly, the outline curves of coal and gangue in polar coordinates are detected and achieved along the centroid, thereby the multifractal characteristics of the series are analyzed and compared. Subsequently, the modified local singular spectrum widths Δ h of the outline curve series are extracted as the characteristic variables of the coal and gangue for pattern recognition. Finally, the extracted geometric features by MFDFA combined with the grayscale and texture features of the images are compared with other methods, indicating that the recognition rate of coal gangue images can be increased by introducing the geometric features.

Arrhythmia Classification Based on Multi-Domain Feature Extraction for an ECG Recognition System

Directory of Open Access Journals (Sweden)

Hongqiang Li

2016-10-01

Full Text Available Automatic recognition of arrhythmias is particularly important in the diagnosis of heart diseases. This study presents an electrocardiogram (ECG recognition system based on multi-domain feature extraction to classify ECG beats. An improved wavelet threshold method for ECG signal pre-processing is applied to remove noise interference. A novel multi-domain feature extraction method is proposed; this method employs kernel-independent component analysis in nonlinear feature extraction and uses discrete wavelet transform to extract frequency domain features. The proposed system utilises a support vector machine classifier optimized with a genetic algorithm to recognize different types of heartbeats. An ECG acquisition experimental platform, in which ECG beats are collected as ECG data for classification, is constructed to demonstrate the effectiveness of the system in ECG beat classification. The presented system, when applied to the MIT-BIH arrhythmia database, achieves a high classification accuracy of 98.8%. Experimental results based on the ECG acquisition experimental platform show that the system obtains a satisfactory classification accuracy of 97.3% and is able to classify ECG beats efficiently for the automatic identification of cardiac arrhythmias.

A Phase Vocoder Based on Nonstationary Gabor Frames

DEFF Research Database (Denmark)

Ottosen, Emil Solsbæk; Dörfler, Monika

2017-01-01

We propose a new algorithm for time stretching music signals based on the theory of nonstationary Gabor frames (NSGFs). The algorithm extends the techniques of the classical phase vocoder (PV) by incorporating adaptive timefrequency (TF) representations and adaptive phase locking. The adaptive TF...... representations imply good time resolution for the onsets of attack transients and good frequency resolution for the sinusoidal components. We estimate the phase values only at peak channels and the remaining phases are then locked to the values of the peaks in an adaptive manner. During attack transients we keep...... that with just three times as many TF coefficients as signal samples, artifacts such as phasiness and transient smearing can be greatly reduced compared to the classical PV. The proposed algorithm is tested on both synthetic and real world signals and compared with state of the art algorithms in a reproducible...

Subject-based feature extraction by using fisher WPD-CSP in brain-computer interfaces.

Science.gov (United States)

Yang, Banghua; Li, Huarong; Wang, Qian; Zhang, Yunyuan

2016-06-01

Feature extraction of electroencephalogram (EEG) plays a vital role in brain-computer interfaces (BCIs). In recent years, common spatial pattern (CSP) has been proven to be an effective feature extraction method. However, the traditional CSP has disadvantages of requiring a lot of input channels and the lack of frequency information. In order to remedy the defects of CSP, wavelet packet decomposition (WPD) and CSP are combined to extract effective features. But WPD-CSP method considers less about extracting specific features that are fitted for the specific subject. So a subject-based feature extraction method using fisher WPD-CSP is proposed in this paper. The idea of proposed method is to adapt fisher WPD-CSP to each subject separately. It mainly includes the following six steps: (1) original EEG signals from all channels are decomposed into a series of sub-bands using WPD; (2) average power values of obtained sub-bands are computed; (3) the specified sub-bands with larger values of fisher distance according to average power are selected for that particular subject; (4) each selected sub-band is reconstructed to be regarded as a new EEG channel; (5) all new EEG channels are used as input of the CSP and a six-dimensional feature vector is obtained by the CSP. The subject-based feature extraction model is so formed; (6) the probabilistic neural network (PNN) is used as the classifier and the classification accuracy is obtained. Data from six subjects are processed by the subject-based fisher WPD-CSP, the non-subject-based fisher WPD-CSP and WPD-CSP, respectively. Compared with non-subject-based fisher WPD-CSP and WPD-CSP, the results show that the proposed method yields better performance (sensitivity: 88.7±0.9%, and specificity: 91±1%) and the classification accuracy from subject-based fisher WPD-CSP is increased by 6-12% and 14%, respectively. The proposed subject-based fisher WPD-CSP method can not only remedy disadvantages of CSP by WPD but also discriminate

Machinery running state identification based on discriminant semi-supervised local tangent space alignment for feature fusion and extraction

International Nuclear Information System (INIS)

Su, Zuqiang; Xiao, Hong; Zhang, Yi; Tang, Baoping; Jiang, Yonghua

2017-01-01

Extraction of sensitive features is a challenging but key task in data-driven machinery running state identification. Aimed at solving this problem, a method for machinery running state identification that applies discriminant semi-supervised local tangent space alignment (DSS-LTSA) for feature fusion and extraction is proposed. Firstly, in order to extract more distinct features, the vibration signals are decomposed by wavelet packet decomposition WPD, and a mixed-domain feature set consisted of statistical features, autoregressive (AR) model coefficients, instantaneous amplitude Shannon entropy and WPD energy spectrum is extracted to comprehensively characterize the properties of machinery running state(s). Then, the mixed-dimension feature set is inputted into DSS-LTSA for feature fusion and extraction to eliminate redundant information and interference noise. The proposed DSS-LTSA can extract intrinsic structure information of both labeled and unlabeled state samples, and as a result the over-fitting problem of supervised manifold learning and blindness problem of unsupervised manifold learning are overcome. Simultaneously, class discrimination information is integrated within the dimension reduction process in a semi-supervised manner to improve sensitivity of the extracted fusion features. Lastly, the extracted fusion features are inputted into a pattern recognition algorithm to achieve the running state identification. The effectiveness of the proposed method is verified by a running state identification case in a gearbox, and the results confirm the improved accuracy of the running state identification. (paper)

Breast cancer mitosis detection in histopathological images with spatial feature extraction

Science.gov (United States)

Albayrak, Abdülkadir; Bilgin, Gökhan

2013-12-01

In this work, cellular mitosis detection in histopathological images has been investigated. Mitosis detection is very expensive and time consuming process. Development of digital imaging in pathology has enabled reasonable and effective solution to this problem. Segmentation of digital images provides easier analysis of cell structures in histopathological data. To differentiate normal and mitotic cells in histopathological images, feature extraction step is very crucial step for the system accuracy. A mitotic cell has more distinctive textural dissimilarities than the other normal cells. Hence, it is important to incorporate spatial information in feature extraction or in post-processing steps. As a main part of this study, Haralick texture descriptor has been proposed with different spatial window sizes in RGB and La*b* color spaces. So, spatial dependencies of normal and mitotic cellular pixels can be evaluated within different pixel neighborhoods. Extracted features are compared with various sample sizes by Support Vector Machines using k-fold cross validation method. According to the represented results, it has been shown that separation accuracy on mitotic and non-mitotic cellular pixels gets better with the increasing size of spatial window.

Sparse kernel orthonormalized PLS for feature extraction in large datasets

DEFF Research Database (Denmark)

Arenas-García, Jerónimo; Petersen, Kaare Brandt; Hansen, Lars Kai

2006-01-01

In this paper we are presenting a novel multivariate analysis method for large scale problems. Our scheme is based on a novel kernel orthonormalized partial least squares (PLS) variant for feature extraction, imposing sparsity constrains in the solution to improve scalability. The algorithm...... is tested on a benchmark of UCI data sets, and on the analysis of integrated short-time music features for genre prediction. The upshot is that the method has strong expressive power even with rather few features, is clearly outperforming the ordinary kernel PLS, and therefore is an appealing method...

Extraction of multi-scale landslide morphological features based on local Gi* using airborne LiDAR-derived DEM

Science.gov (United States)

Shi, Wenzhong; Deng, Susu; Xu, Wenbing

2018-02-01

For automatic landslide detection, landslide morphological features should be quantitatively expressed and extracted. High-resolution Digital Elevation Models (DEMs) derived from airborne Light Detection and Ranging (LiDAR) data allow fine-scale morphological features to be extracted, but noise in DEMs influences morphological feature extraction, and the multi-scale nature of landslide features should be considered. This paper proposes a method to extract landslide morphological features characterized by homogeneous spatial patterns. Both profile and tangential curvature are utilized to quantify land surface morphology, and a local Gi* statistic is calculated for each cell to identify significant patterns of clustering of similar morphometric values. The method was tested on both synthetic surfaces simulating natural terrain and airborne LiDAR data acquired over an area dominated by shallow debris slides and flows. The test results of the synthetic data indicate that the concave and convex morphologies of the simulated terrain features at different scales and distinctness could be recognized using the proposed method, even when random noise was added to the synthetic data. In the test area, cells with large local Gi* values were extracted at a specified significance level from the profile and the tangential curvature image generated from the LiDAR-derived 1-m DEM. The morphologies of landslide main scarps, source areas and trails were clearly indicated, and the morphological features were represented by clusters of extracted cells. A comparison with the morphological feature extraction method based on curvature thresholds proved the proposed method's robustness to DEM noise. When verified against a landslide inventory, the morphological features of almost all recent (historical (> 10 years) landslides were extracted. This finding indicates that the proposed method can facilitate landslide detection, although the cell clusters extracted from curvature images should

A Novel Technique for Shape Feature Extraction Using Content Based Image Retrieval

Directory of Open Access Journals (Sweden)

Dhanoa Jaspreet Singh

2016-01-01

Full Text Available With the advent of technology and multimedia information, digital images are increasing very quickly. Various techniques are being developed to retrieve/search digital information or data contained in the image. Traditional Text Based Image Retrieval System is not plentiful. Since it is time consuming as it require manual image annotation. Also, the image annotation differs with different peoples. An alternate to this is Content Based Image Retrieval (CBIR system. It retrieves/search for image using its contents rather the text, keywords etc. A lot of exploration has been compassed in the range of Content Based Image Retrieval (CBIR with various feature extraction techniques. Shape is a significant image feature as it reflects the human perception. Moreover, Shape is quite simple to use by the user to define object in an image as compared to other features such as Color, texture etc. Over and above, if applied alone, no descriptor will give fruitful results. Further, by combining it with an improved classifier, one can use the positive features of both the descriptor and classifier. So, a tryout will be made to establish an algorithm for accurate feature (Shape extraction in Content Based Image Retrieval (CBIR. The main objectives of this project are: (a To propose an algorithm for shape feature extraction using CBIR, (b To evaluate the performance of proposed algorithm and (c To compare the proposed algorithm with state of art techniques.

Feature extraction through parallel Probabilistic Principal Component Analysis for heart disease diagnosis

Science.gov (United States)

Shah, Syed Muhammad Saqlain; Batool, Safeera; Khan, Imran; Ashraf, Muhammad Usman; Abbas, Syed Hussnain; Hussain, Syed Adnan

2017-09-01

Automatic diagnosis of human diseases are mostly achieved through decision support systems. The performance of these systems is mainly dependent on the selection of the most relevant features. This becomes harder when the dataset contains missing values for the different features. Probabilistic Principal Component Analysis (PPCA) has reputation to deal with the problem of missing values of attributes. This research presents a methodology which uses the results of medical tests as input, extracts a reduced dimensional feature subset and provides diagnosis of heart disease. The proposed methodology extracts high impact features in new projection by using Probabilistic Principal Component Analysis (PPCA). PPCA extracts projection vectors which contribute in highest covariance and these projection vectors are used to reduce feature dimension. The selection of projection vectors is done through Parallel Analysis (PA). The feature subset with the reduced dimension is provided to radial basis function (RBF) kernel based Support Vector Machines (SVM). The RBF based SVM serves the purpose of classification into two categories i.e., Heart Patient (HP) and Normal Subject (NS). The proposed methodology is evaluated through accuracy, specificity and sensitivity over the three datasets of UCI i.e., Cleveland, Switzerland and Hungarian. The statistical results achieved through the proposed technique are presented in comparison to the existing research showing its impact. The proposed technique achieved an accuracy of 82.18%, 85.82% and 91.30% for Cleveland, Hungarian and Switzerland dataset respectively.

The optimal extraction of feature algorithm based on KAZE

Science.gov (United States)

Yao, Zheyi; Gu, Guohua; Qian, Weixian; Wang, Pengcheng

2015-10-01

As a novel method of 2D features extraction algorithm over the nonlinear scale space, KAZE provide a special method. However, the computation of nonlinear scale space and the construction of KAZE feature vectors are more expensive than the SIFT and SURF significantly. In this paper, the given image is used to build the nonlinear space up to a maximum evolution time through the efficient Additive Operator Splitting (AOS) techniques and the variable conductance diffusion. Changing the parameter can improve the construction of nonlinear scale space and simplify the image conductivities for each dimension space, with the predigest computation. Then, the detection for points of interest can exhibit a maxima of the scale-normalized determinant with the Hessian response in the nonlinear scale space. At the same time, the detection of feature vectors is optimized by the Wavelet Transform method, which can avoid the second Gaussian smoothing in the KAZE Features and cut down the complexity of the algorithm distinctly in the building and describing vectors steps. In this way, the dominant orientation is obtained, similar to SURF, by summing the responses within a sliding circle segment covering an angle of π/3 in the circular area of radius 6σ with a sampling step of size σ one by one. Finally, the extraction in the multidimensional patch at the given scale, centered over the points of interest and rotated to align its dominant orientation to a canonical direction, is able to simplify the description of feature by reducing the description dimensions, just as the PCA-SIFT method. Even though the features are somewhat more expensive to compute than SIFT due to the construction of nonlinear scale space, but compared to SURF, the result revels a step forward in performance in detection, description and application against the previous ways by the following contrast experiments.

Automated Feature Extraction of Foredune Morphology from Terrestrial Lidar Data

Science.gov (United States)

Spore, N.; Brodie, K. L.; Swann, C.

2014-12-01

Foredune morphology is often described in storm impact prediction models using the elevation of the dune crest and dune toe and compared with maximum runup elevations to categorize the storm impact and predicted responses. However, these parameters do not account for other foredune features that may make them more or less erodible, such as alongshore variations in morphology, vegetation coverage, or compaction. The goal of this work is to identify other descriptive features that can be extracted from terrestrial lidar data that may affect the rate of dune erosion under wave attack. Daily, mobile-terrestrial lidar surveys were conducted during a 6-day nor'easter (Hs = 4 m in 6 m water depth) along 20km of coastline near Duck, North Carolina which encompassed a variety of foredune forms in close proximity to each other. This abstract will focus on the tools developed for the automated extraction of the morphological features from terrestrial lidar data, while the response of the dune will be presented by Brodie and Spore as an accompanying abstract. Raw point cloud data can be dense and is often under-utilized due to time and personnel constraints required for analysis, since many algorithms are not fully automated. In our approach, the point cloud is first projected into a local coordinate system aligned with the coastline, and then bare earth points are interpolated onto a rectilinear 0.5 m grid creating a high resolution digital elevation model. The surface is analyzed by identifying features along each cross-shore transect. Surface curvature is used to identify the position of the dune toe, and then beach and berm morphology is extracted shoreward of the dune toe, and foredune morphology is extracted landward of the dune toe. Changes in, and magnitudes of, cross-shore slope, curvature, and surface roughness are used to describe the foredune face and each cross-shore transect is then classified using its pre-storm morphology for storm-response analysis.

An Extended HITS Algorithm on Bipartite Network for Features Extraction of Online Customer Reviews

Directory of Open Access Journals (Sweden)

Chen Liu

2018-05-01

Full Text Available How to acquire useful information intelligently in the age of information explosion has become an important issue. In this context, sentiment analysis emerges with the growth of the need of information extraction. One of the most important tasks of sentiment analysis is feature extraction of entities in consumer reviews. This paper first constitutes a directed bipartite feature-sentiment relation network with a set of candidate features-sentiment pairs that is extracted by dependency syntax analysis from consumer reviews. Then, a novel method called MHITS which combines PMI with weighted HITS algorithm is proposed to rank these candidate product features to find out real product features. Empirical experiments indicate the effectiveness of our approach across different kinds and various data sizes of product. In addition, the effect of the proposed algorithm is not the same for the corpus with different proportions of the word pair that includes the “bad”, “good”, “poor”, “pretty good”, “not bad” these general collocation words.

Semantic feature extraction for interior environment understanding and retrieval

Science.gov (United States)

Lei, Zhibin; Liang, Yufeng

1998-12-01

In this paper, we propose a novel system of semantic feature extraction and retrieval for interior design and decoration application. The system, V2ID(Virtual Visual Interior Design), uses colored texture and spatial edge layout to obtain simple information about global room environment. We address the domain-specific segmentation problem in our application and present techniques for obtaining semantic features from a room environment. We also discuss heuristics for making use of these features (color, texture, edge layout, and shape), to retrieve objects from an existing database. The final resynthesized room environment, with the original scene and objects from the database, is created for the purpose of animation and virtual walk-through.

MODELLING AND RECONSTRUCTION OF GABOR-TYPE HOLOGRAMS

Directory of Open Access Journals (Sweden)

GABRIEL J. LORA

2011-01-01

Full Text Available Los procesos de modelación y reconstrucción de hologramas se soportan en el cálculo de la integral de difracción en su formulación de kirchhoff-fresnel o rayleight-sommerfeld. Dicha integral puede ser evaluada numéricamente por medio de diferentes formalismos: teorema de convolución, espectro angular y transformada de fresnel, entre otras. En este trabajo se presenta la modelación de hologramas en línea tipo gabor de partículas opacas de diferentes diámetros. Estos hologramas son reconstruidos por el cálculo numérico de la difracción que sufre una onda esférica cuando ilumina el holograma. El proceso de modelación reconstrucción se utiliza para estudiar el desempeño de la microscopia holográfi ca digital en línea en función del cambio en la concentración de monocapas mono-dispersadas de esferas opacas.

Wavelet processing and digital interferometric contrast to improve reconstructions from X-ray Gabor holograms.

Science.gov (United States)

Aguilar, Juan C; Misawa, Masaki; Matsuda, Kiyofumi; Suzuki, Yoshio; Takeuchi, Akihisa; Yasumoto, Masato

2018-05-01

In this work, the application of an undecimated wavelet transformation together with digital interferometric contrast to improve the resulting reconstructions in a digital hard X-ray Gabor holographic microscope is shown. Specifically, the starlet transform is used together with digital Zernike contrast. With this contrast, the results show that only a small set of scales from the hologram are, in effect, useful, and it is possible to enhance the details of the reconstruction.

Bits extraction for palmprint template protection with Gabor magnitude and multi-bit quantization

NARCIS (Netherlands)

Mu, Meiru; Shao, X.; Ruan, Qiuqi; Spreeuwers, Lieuwe Jan; Veldhuis, Raymond N.J.

2013-01-01

In this paper, we propose a method of fixed-length binary string extraction (denoted by LogGM_DROBA) from low-resolution palmprint image for developing palmprint template protection technology. In order to extract reliable (stable and discriminative) bits, multi-bit equal-probability-interval

Homomorphic encryption-based secure SIFT for privacy-preserving feature extraction

Science.gov (United States)

Hsu, Chao-Yung; Lu, Chun-Shien; Pei, Soo-Chang

2011-02-01

Privacy has received much attention but is still largely ignored in the multimedia community. Consider a cloud computing scenario, where the server is resource-abundant and is capable of finishing the designated tasks, it is envisioned that secure media retrieval and search with privacy-preserving will be seriously treated. In view of the fact that scale-invariant feature transform (SIFT) has been widely adopted in various fields, this paper is the first to address the problem of secure SIFT feature extraction and representation in the encrypted domain. Since all the operations in SIFT must be moved to the encrypted domain, we propose a homomorphic encryption-based secure SIFT method for privacy-preserving feature extraction and representation based on Paillier cryptosystem. In particular, homomorphic comparison is a must for SIFT feature detection but is still a challenging issue for homomorphic encryption methods. To conquer this problem, we investigate a quantization-like secure comparison strategy in this paper. Experimental results demonstrate that the proposed homomorphic encryption-based SIFT performs comparably to original SIFT on image benchmarks, while preserving privacy additionally. We believe that this work is an important step toward privacy-preserving multimedia retrieval in an environment, where privacy is a major concern.

Wavelet-Based Feature Extraction in Fault Diagnosis for Biquad High-Pass Filter Circuit

OpenAIRE

Yuehai Wang; Yongzheng Yan; Qinyong Wang

2016-01-01

Fault diagnosis for analog circuit has become a prominent factor in improving the reliability of integrated circuit due to its irreplaceability in modern integrated circuits. In fact fault diagnosis based on intelligent algorithms has become a popular research topic as efficient feature extraction and selection are a critical and intricate task in analog fault diagnosis. Further, it is extremely important to propose some general guidelines for the optimal feature extraction and selection. In ...

A novel automated spike sorting algorithm with adaptable feature extraction.

Science.gov (United States)

Bestel, Robert; Daus, Andreas W; Thielemann, Christiane

2012-10-15

To study the electrophysiological properties of neuronal networks, in vitro studies based on microelectrode arrays have become a viable tool for analysis. Although in constant progress, a challenging task still remains in this area: the development of an efficient spike sorting algorithm that allows an accurate signal analysis at the single-cell level. Most sorting algorithms currently available only extract a specific feature type, such as the principal components or Wavelet coefficients of the measured spike signals in order to separate different spike shapes generated by different neurons. However, due to the great variety in the obtained spike shapes, the derivation of an optimal feature set is still a very complex issue that current algorithms struggle with. To address this problem, we propose a novel algorithm that (i) extracts a variety of geometric, Wavelet and principal component-based features and (ii) automatically derives a feature subset, most suitable for sorting an individual set of spike signals. Thus, there is a new approach that evaluates the probability distribution of the obtained spike features and consequently determines the candidates most suitable for the actual spike sorting. These candidates can be formed into an individually adjusted set of spike features, allowing a separation of the various shapes present in the obtained neuronal signal by a subsequent expectation maximisation clustering algorithm. Test results with simulated data files and data obtained from chick embryonic neurons cultured on microelectrode arrays showed an excellent classification result, indicating the superior performance of the described algorithm approach. Copyright © 2012 Elsevier B.V. All rights reserved.

Effects of Feature Extraction and Classification Methods on Cyberbully Detection

OpenAIRE

ÖZEL, Selma Ayşe; SARAÇ, Esra

2016-01-01

Cyberbullying is defined as an aggressive, intentional action against a defenseless person by using the Internet, or other electronic contents. Researchers have found that many of the bullying cases have tragically ended in suicides; hence automatic detection of cyberbullying has become important. In this study we show the effects of feature extraction, feature selection, and classification methods that are used, on the performance of automatic detection of cyberbullying. To perform the exper...

Feature extraction & image processing for computer vision

CERN Document Server

Nixon, Mark

2012-01-01

This book is an essential guide to the implementation of image processing and computer vision techniques, with tutorial introductions and sample code in Matlab. Algorithms are presented and fully explained to enable complete understanding of the methods and techniques demonstrated. As one reviewer noted, ""The main strength of the proposed book is the exemplar code of the algorithms."" Fully updated with the latest developments in feature extraction, including expanded tutorials and new techniques, this new edition contains extensive new material on Haar wavelets, Viola-Jones, bilateral filt

A Method of Road Extraction from High-resolution Remote Sensing Images Based on Shape Features

Directory of Open Access Journals (Sweden)

LEI Xiaoqi

2016-02-01

Full Text Available Road extraction from high-resolution remote sensing image is an important and difficult task.Since remote sensing images include complicated information,the methods that extract roads by spectral,texture and linear features have certain limitations.Also,many methods need human-intervention to get the road seeds(semi-automatic extraction,which have the great human-dependence and low efficiency.The road-extraction method,which uses the image segmentation based on principle of local gray consistency and integration shape features,is proposed in this paper.Firstly,the image is segmented,and then the linear and curve roads are obtained by using several object shape features,so the method that just only extract linear roads are rectified.Secondly,the step of road extraction is carried out based on the region growth,the road seeds are automatic selected and the road network is extracted.Finally,the extracted roads are regulated by combining the edge information.In experiments,the images that including the better gray uniform of road and the worse illuminated of road surface were chosen,and the results prove that the method of this study is promising.

An Effective Combined Feature For Web Based Image Retrieval

Directory of Open Access Journals (Sweden)

H.M.R.B Herath

2015-08-01

Full Text Available Abstract Technology advances as well as the emergence of large scale multimedia applications and the revolution of the World Wide Web has changed the world into a digital age. Anybody can use their mobile phone to take a photo at any time anywhere and upload that image to ever growing image databases. Development of effective techniques for visual and multimedia retrieval systems is one of the most challenging and important directions of the future research. This paper proposes an effective combined feature for web based image retrieval. Frequently used colour and texture features are explored in order to develop a combined feature for this purpose. Widely used three colour features Colour moments Colour coherence vector and Colour Correlogram and three texture features Grey Level Co-occurrence matrix Tamura features and Gabor filter were analyzed for their performance. Precision and Recall were used to evaluate the performance of each of these techniques. By comparing precision and recall values the methods that performed best were taken and combined to form a hybrid feature. The developed combined feature was evaluated by developing a web based CBIR system. A web crawler was used to first crawl through Web sites and images found in those sites are downloaded and the combined feature representation technique was used to extract image features. The test results indicated that this web system can be used to index web images with the combined feature representation schema and to find similar images. Random image retrievals using the web system shows that the combined feature can be used to retrieve images belonging to the general image domain. Accuracy of the retrieval can be noted high for natural images like outdoor scenes images of flowers etc. Also images which have a similar colour and texture distribution were retrieved as similar even though the images were belonging to deferent semantic categories. This can be ideal for an artist who wants

Extracting product features and opinion words using pattern knowledge in customer reviews.

Science.gov (United States)

Htay, Su Su; Lynn, Khin Thidar

2013-01-01

Due to the development of e-commerce and web technology, most of online Merchant sites are able to write comments about purchasing products for customer. Customer reviews expressed opinion about products or services which are collectively referred to as customer feedback data. Opinion extraction about products from customer reviews is becoming an interesting area of research and it is motivated to develop an automatic opinion mining application for users. Therefore, efficient method and techniques are needed to extract opinions from reviews. In this paper, we proposed a novel idea to find opinion words or phrases for each feature from customer reviews in an efficient way. Our focus in this paper is to get the patterns of opinion words/phrases about the feature of product from the review text through adjective, adverb, verb, and noun. The extracted features and opinions are useful for generating a meaningful summary that can provide significant informative resource to help the user as well as merchants to track the most suitable choice of product.

Extracting Product Features and Opinion Words Using Pattern Knowledge in Customer Reviews

Directory of Open Access Journals (Sweden)

Su Su Htay

2013-01-01

Full Text Available Due to the development of e-commerce and web technology, most of online Merchant sites are able to write comments about purchasing products for customer. Customer reviews expressed opinion about products or services which are collectively referred to as customer feedback data. Opinion extraction about products from customer reviews is becoming an interesting area of research and it is motivated to develop an automatic opinion mining application for users. Therefore, efficient method and techniques are needed to extract opinions from reviews. In this paper, we proposed a novel idea to find opinion words or phrases for each feature from customer reviews in an efficient way. Our focus in this paper is to get the patterns of opinion words/phrases about the feature of product from the review text through adjective, adverb, verb, and noun. The extracted features and opinions are useful for generating a meaningful summary that can provide significant informative resource to help the user as well as merchants to track the most suitable choice of product.

Extracting Product Features and Opinion Words Using Pattern Knowledge in Customer Reviews

Science.gov (United States)

Lynn, Khin Thidar

2013-01-01

Due to the development of e-commerce and web technology, most of online Merchant sites are able to write comments about purchasing products for customer. Customer reviews expressed opinion about products or services which are collectively referred to as customer feedback data. Opinion extraction about products from customer reviews is becoming an interesting area of research and it is motivated to develop an automatic opinion mining application for users. Therefore, efficient method and techniques are needed to extract opinions from reviews. In this paper, we proposed a novel idea to find opinion words or phrases for each feature from customer reviews in an efficient way. Our focus in this paper is to get the patterns of opinion words/phrases about the feature of product from the review text through adjective, adverb, verb, and noun. The extracted features and opinions are useful for generating a meaningful summary that can provide significant informative resource to help the user as well as merchants to track the most suitable choice of product. PMID:24459430

Scale-invariant feature extraction of neural network and renormalization group flow

Science.gov (United States)

Iso, Satoshi; Shiba, Shotaro; Yokoo, Sumito

2018-05-01

Theoretical understanding of how a deep neural network (DNN) extracts features from input images is still unclear, but it is widely believed that the extraction is performed hierarchically through a process of coarse graining. It reminds us of the basic renormalization group (RG) concept in statistical physics. In order to explore possible relations between DNN and RG, we use the restricted Boltzmann machine (RBM) applied to an Ising model and construct a flow of model parameters (in particular, temperature) generated by the RBM. We show that the unsupervised RBM trained by spin configurations at various temperatures from T =0 to T =6 generates a flow along which the temperature approaches the critical value Tc=2.2 7 . This behavior is the opposite of the typical RG flow of the Ising model. By analyzing various properties of the weight matrices of the trained RBM, we discuss why it flows towards Tc and how the RBM learns to extract features of spin configurations.

Bubble feature extracting based on image processing of coal flotation froth

Energy Technology Data Exchange (ETDEWEB)

Wang, F.; Wang, Y.; Lu, M.; Liu, W. [China University of Mining and Technology, Beijing (China). Dept of Chemical Engineering and Environment

2001-11-01

Using image processing the contrast ratio between the bubble on the surface of flotation froth and the image background was enhanced, and the edges of bubble were extracted. Thus a model about the relation between the statistic feature of the bubbles in the image and the cleaned coal can be established. It is feasible to extract the bubble by processing the froth image of coal flotation on the basis of analysing the shape of the bubble. By means of processing the 51 group images sampled from laboratory column, it is thought that the use of the histogram equalization of image gradation and the medium filtering can obviously improve the dynamic contrast range and the brightness of bubbles. Finally, the method of threshold value cut and the bubble edge detecting for extracting the bubble were also discussed to describe the bubble feature, such as size and shape, in the froth image and to distinguish the froth image of coal flotation. 6 refs., 3 figs.

Dual pairs of gabor frames for trigonometric generators without the partition of unity property

DEFF Research Database (Denmark)

Christensen, Ole; Jakobsen, Mads Sielemann

2011-01-01

Frames is a strong tool to obtain series expansions in Hilbert spaces under less restrictive conditions than imposed by orthonormal bases. In order to apply frame theory it is necessary to construct a pair of so called dual frames. The goal of the article is to provide explicit constructions...... of dual pairs of frames having Gabor structure. Unlike the results presented in the literature we do not base the constructions on a generator satisfying the partition of unity constraint....

Feature Extraction on Brain Computer Interfaces using Discrete Dyadic Wavelet Transform: Preliminary Results

International Nuclear Information System (INIS)

Gareis, I; Gentiletti, G; Acevedo, R; Rufiner, L

2011-01-01

The purpose of this work is to evaluate different feature extraction alternatives to detect the event related evoked potential signal on brain computer interfaces, trying to minimize the time employed and the classification error, in terms of sensibility and specificity of the method, looking for alternatives to coherent averaging. In this context the results obtained performing the feature extraction using discrete dyadic wavelet transform using different mother wavelets are presented. For the classification a single layer perceptron was used. The results obtained with and without the wavelet decomposition were compared; showing an improvement on the classification rate, the specificity and the sensibility for the feature vectors obtained using some mother wavelets.

Fusion of Pixel-based and Object-based Features for Road Centerline Extraction from High-resolution Satellite Imagery

Directory of Open Access Journals (Sweden)

CAO Yungang

2016-10-01

Full Text Available A novel approach for road centerline extraction from high spatial resolution satellite imagery is proposed by fusing both pixel-based and object-based features. Firstly, texture and shape features are extracted at the pixel level, and spectral features are extracted at the object level based on multi-scale image segmentation maps. Then, extracted multiple features are utilized in the fusion framework of Dempster-Shafer evidence theory to roughly identify the road network regions. Finally, an automatic noise removing algorithm combined with the tensor voting strategy is presented to accurately extract the road centerline. Experimental results using high-resolution satellite imageries with different scenes and spatial resolutions showed that the proposed approach compared favorably with the traditional methods, particularly in the aspect of eliminating the salt noise and conglutination phenomenon.

Aircraft micro-doppler feature extraction from high range resolution profiles

CSIR Research Space (South Africa)

Berndt, RJ

2015-10-01

Full Text Available The use of high range resolution measurements and the micro-Doppler effect produced by rotating or vibrating parts of a target has been well documented. This paper presents a technique for extracting features related to helicopter rotors...

Low-Level Color and Texture Feature Extraction of Coral Reef Components

Directory of Open Access Journals (Sweden)

Ma. Sheila Angeli Marcos

2003-06-01

Full Text Available The purpose of this study is to develop a computer-based classifier that automates coral reef assessmentfrom digitized underwater video. We extract low-level color and texture features from coral images toserve as input to a high-level classifier. Low-level features for color were labeled blue, green, yellow/brown/orange, and gray/white, which are described by the normalized chromaticity histograms of thesemajor colors. The color matching capability of these features was determined through a technique called“Histogram Backprojection”. The low-level texture feature marks a region as coarse or fine dependingon the gray-level variance of the region.

A Novel Feature Extraction Technique Using Binarization of Bit Planes for Content Based Image Classification

Directory of Open Access Journals (Sweden)

Sudeep Thepade

2014-01-01

Full Text Available A number of techniques have been proposed earlier for feature extraction using image binarization. Efficiency of the techniques was dependent on proper threshold selection for the binarization method. In this paper, a new feature extraction technique using image binarization has been proposed. The technique has binarized the significant bit planes of an image by selecting local thresholds. The proposed algorithm has been tested on a public dataset and has been compared with existing widely used techniques using binarization for extraction of features. It has been inferred that the proposed method has outclassed all the existing techniques and has shown consistent classification performance.

Vibration Feature Extraction and Analysis for Fault Diagnosis of Rotating Machinery-A Literature Survey

OpenAIRE

Saleem Riaz; Hassan Elahi; Kashif Javaid; Tufail Shahzad

2017-01-01

Safety, reliability, efficiency and performance of rotating machinery in all industrial applications are the main concerns. Rotating machines are widely used in various industrial applications. Condition monitoring and fault diagnosis of rotating machinery faults are very important and often complex and labor-intensive. Feature extraction techniques play a vital role for a reliable, effective and efficient feature extraction for the diagnosis of rotating machinery. Therefore, deve...

Improving ELM-Based Service Quality Prediction by Concise Feature Extraction

Directory of Open Access Journals (Sweden)

Yuhai Zhao

2015-01-01

Full Text Available Web services often run on highly dynamic and changing environments, which generate huge volumes of data. Thus, it is impractical to monitor the change of every QoS parameter for the timely trigger precaution due to high computational costs associated with the process. To address the problem, this paper proposes an active service quality prediction method based on extreme learning machine. First, we extract web service trace logs and QoS information from the service log and convert them into feature vectors. Second, by the proposed EC rules, we are enabled to trigger the precaution of QoS as soon as possible with high confidence. An efficient prefix tree based mining algorithm together with some effective pruning rules is developed to mine such rules. Finally, we study how to extract a set of diversified features as the representative of all mined results. The problem is proved to be NP-hard. A greedy algorithm is presented to approximate the optimal solution. Experimental results show that ELM trained by the selected feature subsets can efficiently improve the reliability and the earliness of service quality prediction.

Hidden discriminative features extraction for supervised high-order time series modeling.

Science.gov (United States)

Nguyen, Ngoc Anh Thi; Yang, Hyung-Jeong; Kim, Sunhee

2016-11-01

In this paper, an orthogonal Tucker-decomposition-based extraction of high-order discriminative subspaces from a tensor-based time series data structure is presented, named as Tensor Discriminative Feature Extraction (TDFE). TDFE relies on the employment of category information for the maximization of the between-class scatter and the minimization of the within-class scatter to extract optimal hidden discriminative feature subspaces that are simultaneously spanned by every modality for supervised tensor modeling. In this context, the proposed tensor-decomposition method provides the following benefits: i) reduces dimensionality while robustly mining the underlying discriminative features, ii) results in effective interpretable features that lead to an improved classification and visualization, and iii) reduces the processing time during the training stage and the filtering of the projection by solving the generalized eigenvalue issue at each alternation step. Two real third-order tensor-structures of time series datasets (an epilepsy electroencephalogram (EEG) that is modeled as channel×frequency bin×time frame and a microarray data that is modeled as gene×sample×time) were used for the evaluation of the TDFE. The experiment results corroborate the advantages of the proposed method with averages of 98.26% and 89.63% for the classification accuracies of the epilepsy dataset and the microarray dataset, respectively. These performance averages represent an improvement on those of the matrix-based algorithms and recent tensor-based, discriminant-decomposition approaches; this is especially the case considering the small number of samples that are used in practice. Copyright © 2016 Elsevier Ltd. All rights reserved.

Extracting BI-RADS Features from Portuguese Clinical Texts.

Science.gov (United States)

Nassif, Houssam; Cunha, Filipe; Moreira, Inês C; Cruz-Correia, Ricardo; Sousa, Eliana; Page, David; Burnside, Elizabeth; Dutra, Inês

2012-01-01

In this work we build the first BI-RADS parser for Portuguese free texts, modeled after existing approaches to extract BI-RADS features from English medical records. Our concept finder uses a semantic grammar based on the BIRADS lexicon and on iterative transferred expert knowledge. We compare the performance of our algorithm to manual annotation by a specialist in mammography. Our results show that our parser's performance is comparable to the manual method.

Micro-Doppler Feature Extraction and Recognition Based on Netted Radar for Ballistic Targets

Directory of Open Access Journals (Sweden)

Feng Cun-qian

2015-12-01

Full Text Available This study examines the complexities of using netted radar to recognize and resolve ballistic midcourse targets. The application of micro-motion feature extraction to ballistic mid-course targets is analyzed, and the current status of application and research on micro-motion feature recognition is concluded for singlefunction radar networks such as low- and high-resolution imaging radar networks. Advantages and disadvantages of these networks are discussed with respect to target recognition. Hybrid-mode radar networks combine low- and high-resolution imaging radar and provide a specific reference frequency that is the basis for ballistic target recognition. Main research trends are discussed for hybrid-mode networks that apply micromotion feature extraction to ballistic mid-course targets.

Fault feature extraction method based on local mean decomposition Shannon entropy and improved kernel principal component analysis model

Directory of Open Access Journals (Sweden)

Jinlu Sheng

2016-07-01

Full Text Available To effectively extract the typical features of the bearing, a new method that related the local mean decomposition Shannon entropy and improved kernel principal component analysis model was proposed. First, the features are extracted by time–frequency domain method, local mean decomposition, and using the Shannon entropy to process the original separated product functions, so as to get the original features. However, the features been extracted still contain superfluous information; the nonlinear multi-features process technique, kernel principal component analysis, is introduced to fuse the characters. The kernel principal component analysis is improved by the weight factor. The extracted characteristic features were inputted in the Morlet wavelet kernel support vector machine to get the bearing running state classification model, bearing running state was thereby identified. Cases of test and actual were analyzed.

Applying Improved Multiscale Fuzzy Entropy for Feature Extraction of MI-EEG

Directory of Open Access Journals (Sweden)

Ming-ai Li

2017-01-01

Full Text Available Electroencephalography (EEG is considered the output of a brain and it is a bioelectrical signal with multiscale and nonlinear properties. Motor Imagery EEG (MI-EEG not only has a close correlation with the human imagination and movement intention but also contains a large amount of physiological or disease information. As a result, it has been fully studied in the field of rehabilitation. To correctly interpret and accurately extract the features of MI-EEG signals, many nonlinear dynamic methods based on entropy, such as Approximate Entropy (ApEn, Sample Entropy (SampEn, Fuzzy Entropy (FE, and Permutation Entropy (PE, have been proposed and exploited continuously in recent years. However, these entropy-based methods can only measure the complexity of MI-EEG based on a single scale and therefore fail to account for the multiscale property inherent in MI-EEG. To solve this problem, Multiscale Sample Entropy (MSE, Multiscale Permutation Entropy (MPE, and Multiscale Fuzzy Entropy (MFE are developed by introducing scale factor. However, MFE has not been widely used in analysis of MI-EEG, and the same parameter values are employed when the MFE method is used to calculate the fuzzy entropy values on multiple scales. Actually, each coarse-grained MI-EEG carries the characteristic information of the original signal on different scale factors. It is necessary to optimize MFE parameters to discover more feature information. In this paper, the parameters of MFE are optimized independently for each scale factor, and the improved MFE (IMFE is applied to the feature extraction of MI-EEG. Based on the event-related desynchronization (ERD/event-related synchronization (ERS phenomenon, IMFE features from multi channels are fused organically to construct the feature vector. Experiments are conducted on a public dataset by using Support Vector Machine (SVM as a classifier. The experiment results of 10-fold cross-validation show that the proposed method yields

The extraction of motion-onset VEP BCI features based on deep learning and compressed sensing.

Science.gov (United States)

Ma, Teng; Li, Hui; Yang, Hao; Lv, Xulin; Li, Peiyang; Liu, Tiejun; Yao, Dezhong; Xu, Peng

2017-01-01

Motion-onset visual evoked potentials (mVEP) can provide a softer stimulus with reduced fatigue, and it has potential applications for brain computer interface(BCI)systems. However, the mVEP waveform is seriously masked in the strong background EEG activities, and an effective approach is needed to extract the corresponding mVEP features to perform task recognition for BCI control. In the current study, we combine deep learning with compressed sensing to mine discriminative mVEP information to improve the mVEP BCI performance. The deep learning and compressed sensing approach can generate the multi-modality features which can effectively improve the BCI performance with approximately 3.5% accuracy incensement over all 11 subjects and is more effective for those subjects with relatively poor performance when using the conventional features. Compared with the conventional amplitude-based mVEP feature extraction approach, the deep learning and compressed sensing approach has a higher classification accuracy and is more effective for subjects with relatively poor performance. According to the results, the deep learning and compressed sensing approach is more effective for extracting the mVEP feature to construct the corresponding BCI system, and the proposed feature extraction framework is easy to extend to other types of BCIs, such as motor imagery (MI), steady-state visual evoked potential (SSVEP)and P300. Copyright © 2016 Elsevier B.V. All rights reserved.

Improving protein fold recognition by extracting fold-specific features from predicted residue-residue contacts.

Science.gov (United States)

Zhu, Jianwei; Zhang, Haicang; Li, Shuai Cheng; Wang, Chao; Kong, Lupeng; Sun, Shiwei; Zheng, Wei-Mou; Bu, Dongbo

2017-12-01

Accurate recognition of protein fold types is a key step for template-based prediction of protein structures. The existing approaches to fold recognition mainly exploit the features derived from alignments of query protein against templates. These approaches have been shown to be successful for fold recognition at family level, but usually failed at superfamily/fold levels. To overcome this limitation, one of the key points is to explore more structurally informative features of proteins. Although residue-residue contacts carry abundant structural information, how to thoroughly exploit these information for fold recognition still remains a challenge. In this study, we present an approach (called DeepFR) to improve fold recognition at superfamily/fold levels. The basic idea of our approach is to extract fold-specific features from predicted residue-residue contacts of proteins using deep convolutional neural network (DCNN) technique. Based on these fold-specific features, we calculated similarity between query protein and templates, and then assigned query protein with fold type of the most similar template. DCNN has showed excellent performance in image feature extraction and image recognition; the rational underlying the application of DCNN for fold recognition is that contact likelihood maps are essentially analogy to images, as they both display compositional hierarchy. Experimental results on the LINDAHL dataset suggest that even using the extracted fold-specific features alone, our approach achieved success rate comparable to the state-of-the-art approaches. When further combining these features with traditional alignment-related features, the success rate of our approach increased to 92.3%, 82.5% and 78.8% at family, superfamily and fold levels, respectively, which is about 18% higher than the state-of-the-art approach at fold level, 6% higher at superfamily level and 1% higher at family level. An independent assessment on SCOP_TEST dataset showed consistent

A novel framework for feature extraction in multi-sensor action potential sorting.

Science.gov (United States)

Wu, Shun-Chi; Swindlehurst, A Lee; Nenadic, Zoran

2015-09-30

Extracellular recordings of multi-unit neural activity have become indispensable in neuroscience research. The analysis of the recordings begins with the detection of the action potentials (APs), followed by a classification step where each AP is associated with a given neural source. A feature extraction step is required prior to classification in order to reduce the dimensionality of the data and the impact of noise, allowing source clustering algorithms to work more efficiently. In this paper, we propose a novel framework for multi-sensor AP feature extraction based on the so-called Matched Subspace Detector (MSD), which is shown to be a natural generalization of standard single-sensor algorithms. Clustering using both simulated data and real AP recordings taken in the locust antennal lobe demonstrates that the proposed approach yields features that are discriminatory and lead to promising results. Unlike existing methods, the proposed algorithm finds joint spatio-temporal feature vectors that match the dominant subspace observed in the two-dimensional data without needs for a forward propagation model and AP templates. The proposed MSD approach provides more discriminatory features for unsupervised AP sorting applications. Copyright © 2015 Elsevier B.V. All rights reserved.

a Landmark Extraction Method Associated with Geometric Features and Location Distribution

Science.gov (United States)

Zhang, W.; Li, J.; Wang, Y.; Xiao, Y.; Liu, P.; Zhang, S.

2018-04-01

Landmark plays an important role in spatial cognition and spatial knowledge organization. Significance measuring model is the main method of landmark extraction. It is difficult to take account of the spatial distribution pattern of landmarks because that the significance of landmark is built in one-dimensional space. In this paper, we start with the geometric features of the ground object, an extraction method based on the target height, target gap and field of view is proposed. According to the influence region of Voronoi Diagram, the description of target gap is established to the geometric representation of the distribution of adjacent targets. Then, segmentation process of the visual domain of Voronoi K order adjacent is given to set up target view under the multi view; finally, through three kinds of weighted geometric features, the landmarks are identified. Comparative experiments show that this method has a certain coincidence degree with the results of traditional significance measuring model, which verifies the effectiveness and reliability of the method and reduces the complexity of landmark extraction process without losing the reference value of landmark.

Extract the Relational Information of Static Features and Motion Features for Human Activities Recognition in Videos

Directory of Open Access Journals (Sweden)

Li Yao

2016-01-01

Full Text Available Both static features and motion features have shown promising performance in human activities recognition task. However, the information included in these features is insufficient for complex human activities. In this paper, we propose extracting relational information of static features and motion features for human activities recognition. The videos are represented by a classical Bag-of-Word (BoW model which is useful in many works. To get a compact and discriminative codebook with small dimension, we employ the divisive algorithm based on KL-divergence to reconstruct the codebook. After that, to further capture strong relational information, we construct a bipartite graph to model the relationship between words of different feature set. Then we use a k-way partition to create a new codebook in which similar words are getting together. With this new codebook, videos can be represented by a new BoW vector with strong relational information. Moreover, we propose a method to compute new clusters from the divisive algorithm’s projective function. We test our work on the several datasets and obtain very promising results.

Empirical evaluation of cross-site reproducibility in radiomic features for characterizing prostate MRI

Science.gov (United States)

Chirra, Prathyush; Leo, Patrick; Yim, Michael; Bloch, B. Nicolas; Rastinehad, Ardeshir R.; Purysko, Andrei; Rosen, Mark; Madabhushi, Anant; Viswanath, Satish

2018-02-01

The recent advent of radiomics has enabled the development of prognostic and predictive tools which use routine imaging, but a key question that still remains is how reproducible these features may be across multiple sites and scanners. This is especially relevant in the context of MRI data, where signal intensity values lack tissue specific, quantitative meaning, as well as being dependent on acquisition parameters (magnetic field strength, image resolution, type of receiver coil). In this paper we present the first empirical study of the reproducibility of 5 different radiomic feature families in a multi-site setting; specifically, for characterizing prostate MRI appearance. Our cohort comprised 147 patient T2w MRI datasets from 4 different sites, all of which were first pre-processed to correct acquisition-related for artifacts such as bias field, differing voxel resolutions, as well as intensity drift (non-standardness). 406 3D voxel wise radiomic features were extracted and evaluated in a cross-site setting to determine how reproducible they were within a relatively homogeneous non-tumor tissue region; using 2 different measures of reproducibility: Multivariate Coefficient of Variation and Instability Score. Our results demonstrated that Haralick features were most reproducible between all 4 sites. By comparison, Laws features were among the least reproducible between sites, as well as performing highly variably across their entire parameter space. Similarly, the Gabor feature family demonstrated good cross-site reproducibility, but for certain parameter combinations alone. These trends indicate that despite extensive pre-processing, only a subset of radiomic features and associated parameters may be reproducible enough for use within radiomics-based machine learning classifier schemes.

Fractal Complexity-Based Feature Extraction Algorithm of Communication Signals

Science.gov (United States)

Wang, Hui; Li, Jingchao; Guo, Lili; Dou, Zheng; Lin, Yun; Zhou, Ruolin

How to analyze and identify the characteristics of radiation sources and estimate the threat level by means of detecting, intercepting and locating has been the central issue of electronic support in the electronic warfare, and communication signal recognition is one of the key points to solve this issue. Aiming at accurately extracting the individual characteristics of the radiation source for the increasingly complex communication electromagnetic environment, a novel feature extraction algorithm for individual characteristics of the communication radiation source based on the fractal complexity of the signal is proposed. According to the complexity of the received signal and the situation of environmental noise, use the fractal dimension characteristics of different complexity to depict the subtle characteristics of the signal to establish the characteristic database, and then identify different broadcasting station by gray relation theory system. The simulation results demonstrate that the algorithm can achieve recognition rate of 94% even in the environment with SNR of -10dB, and this provides an important theoretical basis for the accurate identification of the subtle features of the signal at low SNR in the field of information confrontation.

Skipping the real world: Classification of PolSAR images without explicit feature extraction

Science.gov (United States)

Hänsch, Ronny; Hellwich, Olaf

2018-06-01

The typical processing chain for pixel-wise classification from PolSAR images starts with an optional preprocessing step (e.g. speckle reduction), continues with extracting features projecting the complex-valued data into the real domain (e.g. by polarimetric decompositions) which are then used as input for a machine-learning based classifier, and ends in an optional postprocessing (e.g. label smoothing). The extracted features are usually hand-crafted as well as preselected and represent (a somewhat arbitrary) projection from the complex to the real domain in order to fit the requirements of standard machine-learning approaches such as Support Vector Machines or Artificial Neural Networks. This paper proposes to adapt the internal node tests of Random Forests to work directly on the complex-valued PolSAR data, which makes any explicit feature extraction obsolete. This approach leads to a classification framework with a significantly decreased computation time and memory footprint since no image features have to be computed and stored beforehand. The experimental results on one fully-polarimetric and one dual-polarimetric dataset show that, despite the simpler approach, accuracy can be maintained (decreased by only less than 2 % for the fully-polarimetric dataset) or even improved (increased by roughly 9 % for the dual-polarimetric dataset).

EEMD Independent Extraction for Mixing Features of Rotating Machinery Reconstructed in Phase Space

Directory of Open Access Journals (Sweden)

Zaichao Ma

2015-04-01

Full Text Available Empirical Mode Decomposition (EMD, due to its adaptive decomposition property for the non-linear and non-stationary signals, has been widely used in vibration analyses for rotating machinery. However, EMD suffers from mode mixing, which is difficult to extract features independently. Although the improved EMD, well known as the ensemble EMD (EEMD, has been proposed, mode mixing is alleviated only to a certain degree. Moreover, EEMD needs to determine the amplitude of added noise. In this paper, we propose Phase Space Ensemble Empirical Mode Decomposition (PSEEMD integrating Phase Space Reconstruction (PSR and Manifold Learning (ML for modifying EEMD. We also provide the principle and detailed procedure of PSEEMD, and the analyses on a simulation signal and an actual vibration signal derived from a rubbing rotor are performed. The results show that PSEEMD is more efficient and convenient than EEMD in extracting the mixing features from the investigated signal and in optimizing the amplitude of the necessary added noise. Additionally PSEEMD can extract the weak features interfered with a certain amount of noise.

Three-Dimensional Precession Feature Extraction of Ballistic Targets Based on Narrowband Radar Network

Directory of Open Access Journals (Sweden)

Zhao Shuang

2017-02-01

Full Text Available Micro-motion is a crucial feature used in ballistic target recognition. To address the problem that single-view observations cannot extract true micro-motion parameters, we propose a novel algorithm based on the narrowband radar network to extract three-dimensional precession features. First, we construct a precession model of the cone-shaped target, and as a precondition, we consider the invisible problem of scattering centers. We then analyze in detail the micro-Doppler modulation trait caused by the precession. Then, we match each scattering center in different perspectives based on the ratio of the top scattering center’s micro-Doppler frequency modulation coefficient and extract the 3D coning vector of the target by establishing associated multi-aspect equation systems. In addition, we estimate feature parameters by utilizing the correlation of the micro-Doppler frequency modulation coefficient of the three scattering centers combined with the frequency compensation method. We then calculate the coordinates of the conical point in each moment and reconstruct the 3D spatial portion. Finally, we provide simulation results to validate the proposed algorithm.

Joint Markov Blankets in Feature Sets Extracted from Wavelet Packet Decompositions

Directory of Open Access Journals (Sweden)

Gert Van Dijck

2011-07-01

Full Text Available Since two decades, wavelet packet decompositions have been shown effective as a generic approach to feature extraction from time series and images for the prediction of a target variable. Redundancies exist between the wavelet coefficients and between the energy features that are derived from the wavelet coefficients. We assess these redundancies in wavelet packet decompositions by means of the Markov blanket filtering theory. We introduce the concept of joint Markov blankets. It is shown that joint Markov blankets are a natural extension of Markov blankets, which are defined for single features, to a set of features. We show that these joint Markov blankets exist in feature sets consisting of the wavelet coefficients. Furthermore, we prove that wavelet energy features from the highest frequency resolution level form a joint Markov blanket for all other wavelet energy features. The joint Markov blanket theory indicates that one can expect an increase of classification accuracy with the increase of the frequency resolution level of the energy features.

A Time-Frequency Approach to Feature Extraction for a Brain-Computer Interface with a Comparative Analysis of Performance Measures

Directory of Open Access Journals (Sweden)

T. M. McGinnity

2005-11-01

Full Text Available The paper presents an investigation into a time-frequency (TF method for extracting features from the electroencephalogram (EEG recorded from subjects performing imagination of left- and right-hand movements. The feature extraction procedure (FEP extracts frequency domain information to form features whilst time-frequency resolution is attained by localising the fast Fourier transformations (FFTs of the signals to specific windows localised in time. All features are extracted at the rate of the signal sampling interval from a main feature extraction (FE window through which all data passes. Subject-specific frequency bands are selected for optimal feature extraction and intraclass variations are reduced by smoothing the spectra for each signal by an interpolation (IP process. The TF features are classified using linear discriminant analysis (LDA. The FE window has potential advantages for the FEP to be applied in an online brain-computer interface (BCI. The approach achieves good performance when quantified by classification accuracy (CA rate, information transfer (IT rate, and mutual information (MI. The information that these performance measures provide about a BCI system is analysed and the importance of this is demonstrated through the results.

Vibration Feature Extraction and Analysis for Fault Diagnosis of Rotating Machinery-A Literature Survey

Directory of Open Access Journals (Sweden)

Saleem Riaz

2017-02-01

Full Text Available Safety, reliability, efficiency and performance of rotating machinery in all industrial applications are the main concerns. Rotating machines are widely used in various industrial applications. Condition monitoring and fault diagnosis of rotating machinery faults are very important and often complex and labor-intensive. Feature extraction techniques play a vital role for a reliable, effective and efficient feature extraction for the diagnosis of rotating machinery. Therefore, developing effective bearing fault diagnostic method using different fault features at different steps becomes more attractive. Bearings are widely used in medical applications, food processing industries, semi-conductor industries, paper making industries and aircraft components. This paper review has demonstrated that the latest reviews applied to rotating machinery on the available a variety of vibration feature extraction. Generally literature is classified into two main groups: frequency domain, time frequency analysis. However, fault detection and diagnosis of rotating machine vibration signal processing methods to present their own limitations. In practice, most healthy ingredients faulty vibration signal from background noise and mechanical vibration signals are buried. This paper also reviews that how the advanced signal processing methods, empirical mode decomposition and interference cancellation algorithm has been investigated and developed. The condition for rotating machines based rehabilitation, prevent failures increase the availability and reduce the cost of maintenance is becoming necessary too. Rotating machine fault detection and diagnostics in developing algorithms signal processing based on a key problem is the fault feature extraction or quantification. Currently, vibration signal, fault detection and diagnosis of rotating machinery based techniques most widely used techniques. Furthermore, the researchers are widely interested to make automatic

Representation and Metrics Extraction from Feature Basis: An Object Oriented Approach

Directory of Open Access Journals (Sweden)

Fausto Neri da Silva Vanin

2010-10-01

Full Text Available This tutorial presents an object oriented approach to data reading and metrics extraction from feature basis. Structural issues about basis are discussed first, then the Object Oriented Programming (OOP is aplied to modeling the main elements in this context. The model implementation is then discussed using C++ as programing language. To validate the proposed model, we apply on some feature basis from the University of Carolina, Irvine Machine Learning Database.

Pairs of dual Gabor frame generators with compact support and desired frequency localization

DEFF Research Database (Denmark)

Christensen, Ole

2006-01-01

Let g ∈ L2(R) be a compactly supported function, whose integer-translates {T(k)g}(k ∈ Z) form a partition of unity. We prove that for certain translation and modulation parameters, such a function g generates a Gabor frame, with a (noncanonical) dual generated by a finite linear combination h of ...... tilde (k) DTkBN, where both sums are finite. It is known that for N > 1, such functions cannot generate dual wavelet frames {D(j)T(k)g} (j.k∈ Z). {D(j)T(k)h} (j.k ∈ Z). (C) 2005 Elsevier Inc. All rights reserved....

Manifold Learning with Self-Organizing Mapping for Feature Extraction of Nonlinear Faults in Rotating Machinery

Directory of Open Access Journals (Sweden)

Lin Liang

2015-01-01

Full Text Available A new method for extracting the low-dimensional feature automatically with self-organization mapping manifold is proposed for the detection of rotating mechanical nonlinear faults (such as rubbing, pedestal looseness. Under the phase space reconstructed by single vibration signal, the self-organization mapping (SOM with expectation maximization iteration algorithm is used to divide the local neighborhoods adaptively without manual intervention. After that, the local tangent space alignment algorithm is adopted to compress the high-dimensional phase space into low-dimensional feature space. The proposed method takes advantages of the manifold learning in low-dimensional feature extraction and adaptive neighborhood construction of SOM and can extract intrinsic fault features of interest in two dimensional projection space. To evaluate the performance of the proposed method, the Lorenz system was simulated and rotation machinery with nonlinear faults was obtained for test purposes. Compared with the holospectrum approaches, the results reveal that the proposed method is superior in identifying faults and effective for rotating machinery condition monitoring.

An image-processing methodology for extracting bloodstain pattern features.

Science.gov (United States)

Arthur, Ravishka M; Humburg, Philomena J; Hoogenboom, Jerry; Baiker, Martin; Taylor, Michael C; de Bruin, Karla G

2017-08-01

There is a growing trend in forensic science to develop methods to make forensic pattern comparison tasks more objective. This has generally involved the application of suitable image-processing methods to provide numerical data for identification or comparison. This paper outlines a unique image-processing methodology that can be utilised by analysts to generate reliable pattern data that will assist them in forming objective conclusions about a pattern. A range of features were defined and extracted from a laboratory-generated impact spatter pattern. These features were based in part on bloodstain properties commonly used in the analysis of spatter bloodstain patterns. The values of these features were consistent with properties reported qualitatively for such patterns. The image-processing method developed shows considerable promise as a way to establish measurable discriminating pattern criteria that are lacking in current bloodstain pattern taxonomies. Copyright © 2017 Elsevier B.V. All rights reserved.

The extraction and use of facial features in low bit-rate visual communication.

Science.gov (United States)

Pearson, D

1992-01-29

A review is given of experimental investigations by the author and his collaborators into methods of extracting binary features from images of the face and hands. The aim of the research has been to enable deaf people to communicate by sign language over the telephone network. Other applications include model-based image coding and facial-recognition systems. The paper deals with the theoretical postulates underlying the successful experimental extraction of facial features. The basic philosophy has been to treat the face as an illuminated three-dimensional object and to identify features from characteristics of their Gaussian maps. It can be shown that in general a composite image operator linked to a directional-illumination estimator is required to accomplish this, although the latter can often be omitted in practice.

Average combination difference morphological filters for fault feature extraction of bearing

Science.gov (United States)

Lv, Jingxiang; Yu, Jianbo

2018-02-01

In order to extract impulse components from vibration signals with much noise and harmonics, a new morphological filter called average combination difference morphological filter (ACDIF) is proposed in this paper. ACDIF constructs firstly several new combination difference (CDIF) operators, and then integrates the best two CDIFs as the final morphological filter. This design scheme enables ACIDF to extract positive and negative impacts existing in vibration signals to enhance accuracy of bearing fault diagnosis. The length of structure element (SE) that affects the performance of ACDIF is determined adaptively by a new indicator called Teager energy kurtosis (TEK). TEK further improves the effectiveness of ACDIF for fault feature extraction. Experimental results on the simulation and bearing vibration signals demonstrate that ACDIF can effectively suppress noise and extract periodic impulses from bearing vibration signals.

A Novel 2.5D Feature Descriptor Compensating for Depth Rotation

DEFF Research Database (Denmark)

Hagelskjær, Frederik; Buch, Anders Glent; Krüger, Norbert

2017-01-01

We introduce a novel type of local image descriptor based on Gabor filter responses. Our method operates on RGB-D images. We use the depth information to compensate for perspective distortions caused by out-of-plane rotations. The descriptor contains the responses of a multi-resolution Gabor bank...

Rotation, scale, and translation invariant pattern recognition using feature extraction

Science.gov (United States)

Prevost, Donald; Doucet, Michel; Bergeron, Alain; Veilleux, Luc; Chevrette, Paul C.; Gingras, Denis J.

1997-03-01

A rotation, scale and translation invariant pattern recognition technique is proposed.It is based on Fourier- Mellin Descriptors (FMD). Each FMD is taken as an independent feature of the object, and a set of those features forms a signature. FMDs are naturally rotation invariant. Translation invariance is achieved through pre- processing. A proper normalization of the FMDs gives the scale invariance property. This approach offers the double advantage of providing invariant signatures of the objects, and a dramatic reduction of the amount of data to process. The compressed invariant feature signature is next presented to a multi-layered perceptron neural network. This final step provides some robustness to the classification of the signatures, enabling good recognition behavior under anamorphically scaled distortion. We also present an original feature extraction technique, adapted to optical calculation of the FMDs. A prototype optical set-up was built, and experimental results are presented.

Special features of SCF solid extraction of natural products: deoiling of wheat gluten and extraction of rose hip oil

Directory of Open Access Journals (Sweden)

Eggers R.

2000-01-01

Full Text Available Supercritical CO2 extraction has shown great potential in separating vegetable oils as well as removing undesirable oil residuals from natural products. The influence of process parameters, such as pressure, temperature, mass flow and particle size, on the mass transfer kinetics of different natural products has been studied by many authors. However, few publications have focused on specific features of the raw material (moisture, mechanical pretreatment, bed compressibility, etc., which could play an important role, particularly in the scale-up of extraction processes. A review of the influence of both process parameters and specific features of the material on oilseed extraction is given in Eggers (1996. Mechanical pretreatment has been commonly used in order to facilitate mass transfer from the material into the supercritical fluid. However, small particle sizes, especially when combined with high moisture contents, may lead to inefficient extraction results. This paper focuses on the problems that appear during scale-up in processes on a lab to pilot or industrial plant scale related to the pretreatment of material, the control of initial water content and vessel shape. Two applications were studied: deoiling of wheat gluten with supercritical carbon dioxide to produce a totally oil-free (< 0.1 % oil powder (wheat gluten and the extraction of oil from rose hip seeds. Different ways of pretreating the feed material were successfully tested in order to develop an industrial-scale gluten deoiling process. The influence of shape and size of the fixed bed on the extraction results was also studied. In the case of rose hip seeds, the present work discusses the influence of pretreatment of the seeds prior to the extraction process on extraction kinetics.

A Low Cost VLSI Architecture for Spike Sorting Based on Feature Extraction with Peak Search.

Science.gov (United States)

Chang, Yuan-Jyun; Hwang, Wen-Jyi; Chen, Chih-Chang

2016-12-07

The goal of this paper is to present a novel VLSI architecture for spike sorting with high classification accuracy, low area costs and low power consumption. A novel feature extraction algorithm with low computational complexities is proposed for the design of the architecture. In the feature extraction algorithm, a spike is separated into two portions based on its peak value. The area of each portion is then used as a feature. The algorithm is simple to implement and less susceptible to noise interference. Based on the algorithm, a novel architecture capable of identifying peak values and computing spike areas concurrently is proposed. To further accelerate the computation, a spike can be divided into a number of segments for the local feature computation. The local features are subsequently merged with the global ones by a simple hardware circuit. The architecture can also be easily operated in conjunction with the circuits for commonly-used spike detection algorithms, such as the Non-linear Energy Operator (NEO). The architecture has been implemented by an Application-Specific Integrated Circuit (ASIC) with 90-nm technology. Comparisons to the existing works show that the proposed architecture is well suited for real-time multi-channel spike detection and feature extraction requiring low hardware area costs, low power consumption and high classification accuracy.

A COMPARATIVE ANALYSIS OF SINGLE AND COMBINATION FEATURE EXTRACTION TECHNIQUES FOR DETECTING CERVICAL CANCER LESIONS

Directory of Open Access Journals (Sweden)

S. Pradeep Kumar Kenny

2016-02-01

Full Text Available Cervical cancer is the third most common form of cancer affecting women especially in third world countries. The predominant reason for such alarming rate of death is primarily due to lack of awareness and proper health care. As they say, prevention is better than cure, a better strategy has to be put in place to screen a large number of women so that an early diagnosis can help in saving their lives. One such strategy is to implement an automated system. For an automated system to function properly a proper set of features have to be extracted so that the cancer cell can be detected efficiently. In this paper we compare the performances of detecting a cancer cell using a single feature versus a combination feature set technique to see which will suit the automated system in terms of higher detection rate. For this each cell is segmented using multiscale morphological watershed segmentation technique and a series of features are extracted. This process is performed on 967 images and the data extracted is subjected to data mining techniques to determine which feature is best for which stage of cancer. The results thus obtained clearly show a higher percentage of success for combination feature set with 100% accurate detection rate.

The Feature Extraction Based on Texture Image Information for Emotion Sensing in Speech

Directory of Open Access Journals (Sweden)

Kun-Ching Wang

2014-09-01

Full Text Available In this paper, we present a novel texture image feature for Emotion Sensing in Speech (ESS. This idea is based on the fact that the texture images carry emotion-related information. The feature extraction is derived from time-frequency representation of spectrogram images. First, we transform the spectrogram as a recognizable image. Next, we use a cubic curve to enhance the image contrast. Then, the texture image information (TII derived from the spectrogram image can be extracted by using Laws’ masks to characterize emotional state. In order to evaluate the effectiveness of the proposed emotion recognition in different languages, we use two open emotional databases including the Berlin Emotional Speech Database (EMO-DB and eNTERFACE corpus and one self-recorded database (KHUSC-EmoDB, to evaluate the performance cross-corpora. The results of the proposed ESS system are presented using support vector machine (SVM as a classifier. Experimental results show that the proposed TII-based feature extraction inspired by visual perception can provide significant classification for ESS systems. The two-dimensional (2-D TII feature can provide the discrimination between different emotions in visual expressions except for the conveyance pitch and formant tracks. In addition, the de-noising in 2-D images can be more easily completed than de-noising in 1-D speech.

Vaccine adverse event text mining system for extracting features from vaccine safety reports.

Science.gov (United States)

Botsis, Taxiarchis; Buttolph, Thomas; Nguyen, Michael D; Winiecki, Scott; Woo, Emily Jane; Ball, Robert

2012-01-01

To develop and evaluate a text mining system for extracting key clinical features from vaccine adverse event reporting system (VAERS) narratives to aid in the automated review of adverse event reports. Based upon clinical significance to VAERS reviewing physicians, we defined the primary (diagnosis and cause of death) and secondary features (eg, symptoms) for extraction. We built a novel vaccine adverse event text mining (VaeTM) system based on a semantic text mining strategy. The performance of VaeTM was evaluated using a total of 300 VAERS reports in three sequential evaluations of 100 reports each. Moreover, we evaluated the VaeTM contribution to case classification; an information retrieval-based approach was used for the identification of anaphylaxis cases in a set of reports and was compared with two other methods: a dedicated text classifier and an online tool. The performance metrics of VaeTM were text mining metrics: recall, precision and F-measure. We also conducted a qualitative difference analysis and calculated sensitivity and specificity for classification of anaphylaxis cases based on the above three approaches. VaeTM performed best in extracting diagnosis, second level diagnosis, drug, vaccine, and lot number features (lenient F-measure in the third evaluation: 0.897, 0.817, 0.858, 0.874, and 0.914, respectively). In terms of case classification, high sensitivity was achieved (83.1%); this was equal and better compared to the text classifier (83.1%) and the online tool (40.7%), respectively. Our VaeTM implementation of a semantic text mining strategy shows promise in providing accurate and efficient extraction of key features from VAERS narratives.

Feature Extraction of Weld Defectology in Digital Image of Radiographic Film Using Geometric Invariant Moment and Statistical Texture

International Nuclear Information System (INIS)

Muhtadan

2009-01-01

The purpose of this research is to perform feature extraction in weld defect of digital image of radiographic film using geometric invariant moment and statistical texture method. Feature extraction values can be use as values that used to classify and pattern recognition on interpretation of weld defect in digital image of radiographic film by computer automatically. Weld defectology type that used in this research are longitudinal crack, transversal crack, distributed porosity, clustered porosity, wormhole, and no defect. Research methodology on this research are program development to read digital image, then performing image cropping to localize weld position, and then applying geometric invariant moment and statistical texture formulas to find feature values. The result of this research are feature extraction values that have tested with RST (rotation, scale, transformation) treatment and yield moment values that more invariant there are ϕ 3 , ϕ 4 , ϕ 5 from geometric invariant moment method. Feature values from statistical texture that are average intensity, average contrast, smoothness, 3 rd moment, uniformity, and entropy, they used as feature extraction values. (author)

Evidence for unlimited capacity processing of simple features in visual cortex.

Science.gov (United States)

White, Alex L; Runeson, Erik; Palmer, John; Ernst, Zachary R; Boynton, Geoffrey M

2017-06-01

Performance in many visual tasks is impaired when observers attempt to divide spatial attention across multiple visual field locations. Correspondingly, neuronal response magnitudes in visual cortex are often reduced during divided compared with focused spatial attention. This suggests that early visual cortex is the site of capacity limits, where finite processing resources must be divided among attended stimuli. However, behavioral research demonstrates that not all visual tasks suffer such capacity limits: The costs of divided attention are minimal when the task and stimulus are simple, such as when searching for a target defined by orientation or contrast. To date, however, every neuroimaging study of divided attention has used more complex tasks and found large reductions in response magnitude. We bridged that gap by using functional magnetic resonance imaging to measure responses in the human visual cortex during simple feature detection. The first experiment used a visual search task: Observers detected a low-contrast Gabor patch within one or four potentially relevant locations. The second experiment used a dual-task design, in which observers made independent judgments of Gabor presence in patches of dynamic noise at two locations. In both experiments, blood-oxygen level-dependent (BOLD) signals in the retinotopic cortex were significantly lower for ignored than attended stimuli. However, when observers divided attention between multiple stimuli, BOLD signals were not reliably reduced and behavioral performance was unimpaired. These results suggest that processing of simple features in early visual cortex has unlimited capacity.

Effects of Feature Extraction and Classification Methods on Cyberbully Detection

Directory of Open Access Journals (Sweden)

Esra SARAÇ

2016-12-01

Full Text Available Cyberbullying is defined as an aggressive, intentional action against a defenseless person by using the Internet, or other electronic contents. Researchers have found that many of the bullying cases have tragically ended in suicides; hence automatic detection of cyberbullying has become important. In this study we show the effects of feature extraction, feature selection, and classification methods that are used, on the performance of automatic detection of cyberbullying. To perform the experiments FormSpring.me dataset is used and the effects of preprocessing methods; several classifiers like C4.5, Naïve Bayes, kNN, and SVM; and information gain and chi square feature selection methods are investigated. Experimental results indicate that the best classification results are obtained when alphabetic tokenization, no stemming, and no stopwords removal are applied. Using feature selection also improves cyberbully detection performance. When classifiers are compared, C4.5 performs the best for the used dataset.

VHDL Implementation of Feature-Extraction Algorithm for the PANDA Electromagnetic Calorimeter

NARCIS (Netherlands)

Kavatsyuk, M.; Guliyev, E.; Lemmens, P. J. J.; Löhner, H.; Tambave, G.

2010-01-01

The feature-extraction algorithm, developed for the digital front-end electronics of the electromagnetic calorimeter of the PANDA detector at the future FAIR facility, is implemented in VHDL for a commercial 16 bit 100 MHz sampling ADC. The use of modified firmware with the running on-line

VHDL implementation of feature-extraction algorithm for the PANDA electromagnetic calorimeter

NARCIS (Netherlands)

Guliyev, E.; Kavatsyuk, M.; Lemmens, P. J. J.; Tambave, G.; Löhner, H.

2012-01-01

A simple, efficient, and robust feature-extraction algorithm, developed for the digital front-end electronics of the electromagnetic calorimeter of the PANDA spectrometer at FAIR, Darmstadt, is implemented in VHDL for a commercial 16 bit 100 MHz sampling ADC. The source-code is available as an

A Low Cost VLSI Architecture for Spike Sorting Based on Feature Extraction with Peak Search

Directory of Open Access Journals (Sweden)

Yuan-Jyun Chang

2016-12-01

Full Text Available The goal of this paper is to present a novel VLSI architecture for spike sorting with high classification accuracy, low area costs and low power consumption. A novel feature extraction algorithm with low computational complexities is proposed for the design of the architecture. In the feature extraction algorithm, a spike is separated into two portions based on its peak value. The area of each portion is then used as a feature. The algorithm is simple to implement and less susceptible to noise interference. Based on the algorithm, a novel architecture capable of identifying peak values and computing spike areas concurrently is proposed. To further accelerate the computation, a spike can be divided into a number of segments for the local feature computation. The local features are subsequently merged with the global ones by a simple hardware circuit. The architecture can also be easily operated in conjunction with the circuits for commonly-used spike detection algorithms, such as the Non-linear Energy Operator (NEO. The architecture has been implemented by an Application-Specific Integrated Circuit (ASIC with 90-nm technology. Comparisons to the existing works show that the proposed architecture is well suited for real-time multi-channel spike detection and feature extraction requiring low hardware area costs, low power consumption and high classification accuracy.

Depth-based human activity recognition: A comparative perspective study on feature extraction

Directory of Open Access Journals (Sweden)

Heba Hamdy Ali

2018-06-01

Full Text Available Depth Maps-based Human Activity Recognition is the process of categorizing depth sequences with a particular activity. In this problem, some applications represent robust solutions in domains such as surveillance system, computer vision applications, and video retrieval systems. The task is challenging due to variations inside one class and distinguishes between activities of various classes and video recording settings. In this study, we introduce a detailed study of current advances in the depth maps-based image representations and feature extraction process. Moreover, we discuss the state of art datasets and subsequent classification procedure. Also, a comparative study of some of the more popular depth-map approaches has provided in greater detail. The proposed methods are evaluated on three depth-based datasets “MSR Action 3D”, “MSR Hand Gesture”, and “MSR Daily Activity 3D”. Experimental results achieved 100%, 95.83%, and 96.55% respectively. While combining depth and color features on “RGBD-HuDaAct” Dataset, achieved 89.1%. Keywords: Activity recognition, Depth, Feature extraction, Video, Human body detection, Hand gesture

Singular value decomposition based feature extraction technique for physiological signal analysis.

Science.gov (United States)

Chang, Cheng-Ding; Wang, Chien-Chih; Jiang, Bernard C

2012-06-01

Multiscale entropy (MSE) is one of the popular techniques to calculate and describe the complexity of the physiological signal. Many studies use this approach to detect changes in the physiological conditions in the human body. However, MSE results are easily affected by noise and trends, leading to incorrect estimation of MSE values. In this paper, singular value decomposition (SVD) is adopted to replace MSE to extract the features of physiological signals, and adopt the support vector machine (SVM) to classify the different physiological states. A test data set based on the PhysioNet website was used, and the classification results showed that using SVD to extract features of the physiological signal could attain a classification accuracy rate of 89.157%, which is higher than that using the MSE value (71.084%). The results show the proposed analysis procedure is effective and appropriate for distinguishing different physiological states. This promising result could be used as a reference for doctors in diagnosis of congestive heart failure (CHF) disease.

Maximum entropy methods for extracting the learned features of deep neural networks.

Science.gov (United States)

Finnegan, Alex; Song, Jun S

2017-10-01

New architectures of multilayer artificial neural networks and new methods for training them are rapidly revolutionizing the application of machine learning in diverse fields, including business, social science, physical sciences, and biology. Interpreting deep neural networks, however, currently remains elusive, and a critical challenge lies in understanding which meaningful features a network is actually learning. We present a general method for interpreting deep neural networks and extracting network-learned features from input data. We describe our algorithm in the context of biological sequence analysis. Our approach, based on ideas from statistical physics, samples from the maximum entropy distribution over possible sequences, anchored at an input sequence and subject to constraints implied by the empirical function learned by a network. Using our framework, we demonstrate that local transcription factor binding motifs can be identified from a network trained on ChIP-seq data and that nucleosome positioning signals are indeed learned by a network trained on chemical cleavage nucleosome maps. Imposing a further constraint on the maximum entropy distribution also allows us to probe whether a network is learning global sequence features, such as the high GC content in nucleosome-rich regions. This work thus provides valuable mathematical tools for interpreting and extracting learned features from feed-forward neural networks.

Classification of radiolarian images with hand-crafted and deep features

Science.gov (United States)

Keçeli, Ali Seydi; Kaya, Aydın; Keçeli, Seda Uzunçimen

2017-12-01

Radiolarians are planktonic protozoa and are important biostratigraphic and paleoenvironmental indicators for paleogeographic reconstructions. Radiolarian paleontology still remains as a low cost and the one of the most convenient way to obtain dating of deep ocean sediments. Traditional methods for identifying radiolarians are time-consuming and cannot scale to the granularity or scope necessary for large-scale studies. Automated image classification will allow making these analyses promptly. In this study, a method for automatic radiolarian image classification is proposed on Scanning Electron Microscope (SEM) images of radiolarians to ease species identification of fossilized radiolarians. The proposed method uses both hand-crafted features like invariant moments, wavelet moments, Gabor features, basic morphological features and deep features obtained from a pre-trained Convolutional Neural Network (CNN). Feature selection is applied over deep features to reduce high dimensionality. Classification outcomes are analyzed to compare hand-crafted features, deep features, and their combinations. Results show that the deep features obtained from a pre-trained CNN are more discriminative comparing to hand-crafted ones. Additionally, feature selection utilizes to the computational cost of classification algorithms and have no negative effect on classification accuracy.

[Identification of special quality eggs with NIR spectroscopy technology based on symbol entropy feature extraction method].

Science.gov (United States)

Zhao, Yong; Hong, Wen-Xue

2011-11-01

Fast, nondestructive and accurate identification of special quality eggs is an urgent problem. The present paper proposed a new feature extraction method based on symbol entropy to identify near infrared spectroscopy of special quality eggs. The authors selected normal eggs, free range eggs, selenium-enriched eggs and zinc-enriched eggs as research objects and measured the near-infrared diffuse reflectance spectra in the range of 12 000-4 000 cm(-1). Raw spectra were symbolically represented with aggregation approximation algorithm and symbolic entropy was extracted as feature vector. An error-correcting output codes multiclass support vector machine classifier was designed to identify the spectrum. Symbolic entropy feature is robust when parameter changed and the highest recognition rate reaches up to 100%. The results show that the identification method of special quality eggs using near-infrared is feasible and the symbol entropy can be used as a new feature extraction method of near-infrared spectra.

Real-time implementation of optimized maximum noise fraction transform for feature extraction of hyperspectral images

Science.gov (United States)

Wu, Yuanfeng; Gao, Lianru; Zhang, Bing; Zhao, Haina; Li, Jun

2014-01-01

We present a parallel implementation of the optimized maximum noise fraction (G-OMNF) transform algorithm for feature extraction of hyperspectral images on commodity graphics processing units (GPUs). The proposed approach explored the algorithm data-level concurrency and optimized the computing flow. We first defined a three-dimensional grid, in which each thread calculates a sub-block data to easily facilitate the spatial and spectral neighborhood data searches in noise estimation, which is one of the most important steps involved in OMNF. Then, we optimized the processing flow and computed the noise covariance matrix before computing the image covariance matrix to reduce the original hyperspectral image data transmission. These optimization strategies can greatly improve the computing efficiency and can be applied to other feature extraction algorithms. The proposed parallel feature extraction algorithm was implemented on an Nvidia Tesla GPU using the compute unified device architecture and basic linear algebra subroutines library. Through the experiments on several real hyperspectral images, our GPU parallel implementation provides a significant speedup of the algorithm compared with the CPU implementation, especially for highly data parallelizable and arithmetically intensive algorithm parts, such as noise estimation. In order to further evaluate the effectiveness of G-OMNF, we used two different applications: spectral unmixing and classification for evaluation. Considering the sensor scanning rate and the data acquisition time, the proposed parallel implementation met the on-board real-time feature extraction.

Feature Extraction

CERN Document Server

CERN. Geneva

2015-01-01

Feature selection and reduction are key to robust multivariate analyses. In this talk I will focus on pros and cons of various variable selection methods and focus on those that are most relevant in the context of HEP.

Reaction Decoder Tool (RDT): extracting features from chemical reactions.

Science.gov (United States)

Rahman, Syed Asad; Torrance, Gilliean; Baldacci, Lorenzo; Martínez Cuesta, Sergio; Fenninger, Franz; Gopal, Nimish; Choudhary, Saket; May, John W; Holliday, Gemma L; Steinbeck, Christoph; Thornton, Janet M

2016-07-01

Extracting chemical features like Atom-Atom Mapping (AAM), Bond Changes (BCs) and Reaction Centres from biochemical reactions helps us understand the chemical composition of enzymatic reactions. Reaction Decoder is a robust command line tool, which performs this task with high accuracy. It supports standard chemical input/output exchange formats i.e. RXN/SMILES, computes AAM, highlights BCs and creates images of the mapped reaction. This aids in the analysis of metabolic pathways and the ability to perform comparative studies of chemical reactions based on these features. This software is implemented in Java, supported on Windows, Linux and Mac OSX, and freely available at https://github.com/asad/ReactionDecoder : asad@ebi.ac.uk or s9asad@gmail.com. © The Author 2016. Published by Oxford University Press.

On Feature Extraction from Large Scale Linear LiDAR Data

Science.gov (United States)

Acharjee, Partha Pratim

Airborne light detection and ranging (LiDAR) can generate co-registered elevation and intensity map over large terrain. The co-registered 3D map and intensity information can be used efficiently for different feature extraction application. In this dissertation, we developed two algorithms for feature extraction, and usages of features for practical applications. One of the developed algorithms can map still and flowing waterbody features, and another one can extract building feature and estimate solar potential on rooftops and facades. Remote sensing capabilities, distinguishing characteristics of laser returns from water surface and specific data collection procedures provide LiDAR data an edge in this application domain. Furthermore, water surface mapping solutions must work on extremely large datasets, from a thousand square miles, to hundreds of thousands of square miles. National and state-wide map generation/upgradation and hydro-flattening of LiDAR data for many other applications are two leading needs of water surface mapping. These call for as much automation as possible. Researchers have developed many semi-automated algorithms using multiple semi-automated tools and human interventions. This reported work describes a consolidated algorithm and toolbox developed for large scale, automated water surface mapping. Geometric features such as flatness of water surface, higher elevation change in water-land interface and, optical properties such as dropouts caused by specular reflection, bimodal intensity distributions were some of the linear LiDAR features exploited for water surface mapping. Large-scale data handling capabilities are incorporated by automated and intelligent windowing, by resolving boundary issues and integrating all results to a single output. This whole algorithm is developed as an ArcGIS toolbox using Python libraries. Testing and validation are performed on a large datasets to determine the effectiveness of the toolbox and results are

Feature Extraction and Analysis of Breast Cancer Specimen

Science.gov (United States)

Bhattacharyya, Debnath; Robles, Rosslin John; Kim, Tai-Hoon; Bandyopadhyay, Samir Kumar

In this paper, we propose a method to identify abnormal growth of cells in breast tissue and suggest further pathological test, if necessary. We compare normal breast tissue with malignant invasive breast tissue by a series of image processing steps. Normal ductal epithelial cells and ductal / lobular invasive carcinogenic cells also consider for comparison here in this paper. In fact, features of cancerous breast tissue (invasive) are extracted and analyses with normal breast tissue. We also suggest the breast cancer recognition technique through image processing and prevention by controlling p53 gene mutation to some greater extent.

Extracting intrinsic functional networks with feature-based group independent component analysis.

Science.gov (United States)

Calhoun, Vince D; Allen, Elena

2013-04-01

There is increasing use of functional imaging data to understand the macro-connectome of the human brain. Of particular interest is the structure and function of intrinsic networks (regions exhibiting temporally coherent activity both at rest and while a task is being performed), which account for a significant portion of the variance in functional MRI data. While networks are typically estimated based on the temporal similarity between regions (based on temporal correlation, clustering methods, or independent component analysis [ICA]), some recent work has suggested that these intrinsic networks can be extracted from the inter-subject covariation among highly distilled features, such as amplitude maps reflecting regions modulated by a task or even coordinates extracted from large meta analytic studies. In this paper our goal was to explicitly compare the networks obtained from a first-level ICA (ICA on the spatio-temporal functional magnetic resonance imaging (fMRI) data) to those from a second-level ICA (i.e., ICA on computed features rather than on the first-level fMRI data). Convergent results from simulations, task-fMRI data, and rest-fMRI data show that the second-level analysis is slightly noisier than the first-level analysis but yields strikingly similar patterns of intrinsic networks (spatial correlations as high as 0.85 for task data and 0.65 for rest data, well above the empirical null) and also preserves the relationship of these networks with other variables such as age (for example, default mode network regions tended to show decreased low frequency power for first-level analyses and decreased loading parameters for second-level analyses). In addition, the best-estimated second-level results are those which are the most strongly reflected in the input feature. In summary, the use of feature-based ICA appears to be a valid tool for extracting intrinsic networks. We believe it will become a useful and important approach in the study of the macro

Four-Channel Biosignal Analysis and Feature Extraction for Automatic Emotion Recognition

Science.gov (United States)

Kim, Jonghwa; André, Elisabeth

This paper investigates the potential of physiological signals as a reliable channel for automatic recognition of user's emotial state. For the emotion recognition, little attention has been paid so far to physiological signals compared to audio-visual emotion channels such as facial expression or speech. All essential stages of automatic recognition system using biosignals are discussed, from recording physiological dataset up to feature-based multiclass classification. Four-channel biosensors are used to measure electromyogram, electrocardiogram, skin conductivity and respiration changes. A wide range of physiological features from various analysis domains, including time/frequency, entropy, geometric analysis, subband spectra, multiscale entropy, etc., is proposed in order to search the best emotion-relevant features and to correlate them with emotional states. The best features extracted are specified in detail and their effectiveness is proven by emotion recognition results.

Feature Extraction and Classification on Esophageal X-Ray Images of Xinjiang Kazak Nationality

Directory of Open Access Journals (Sweden)

Fang Yang

2017-01-01

Full Text Available Esophageal cancer is one of the fastest rising types of cancers in China. The Kazak nationality is the highest-risk group in Xinjiang. In this work, an effective computer-aided diagnostic system is developed to assist physicians in interpreting digital X-ray image features and improving the quality of diagnosis. The modules of the proposed system include image preprocessing, feature extraction, feature selection, image classification, and performance evaluation. 300 original esophageal X-ray images were resized to a region of interest and then enhanced by the median filter and histogram equalization method. 37 features from textural, frequency, and complexity domains were extracted. Both sequential forward selection and principal component analysis methods were employed to select the discriminative features for classification. Then, support vector machine and K-nearest neighbors were applied to classify the esophageal cancer images with respect to their specific types. The classification performance was evaluated in terms of the area under the receiver operating characteristic curve, accuracy, precision, and recall, respectively. Experimental results show that the classification performance of the proposed system outperforms the conventional visual inspection approaches in terms of diagnostic quality and processing time. Therefore, the proposed computer-aided diagnostic system is promising for the diagnostics of esophageal cancer.

Wearable Sensor-Based Human Activity Recognition Method with Multi-Features Extracted from Hilbert-Huang Transform.

Science.gov (United States)

Xu, Huile; Liu, Jinyi; Hu, Haibo; Zhang, Yi

2016-12-02

Wearable sensors-based human activity recognition introduces many useful applications and services in health care, rehabilitation training, elderly monitoring and many other areas of human interaction. Existing works in this field mainly focus on recognizing activities by using traditional features extracted from Fourier transform (FT) or wavelet transform (WT). However, these signal processing approaches are suitable for a linear signal but not for a nonlinear signal. In this paper, we investigate the characteristics of the Hilbert-Huang transform (HHT) for dealing with activity data with properties such as nonlinearity and non-stationarity. A multi-features extraction method based on HHT is then proposed to improve the effect of activity recognition. The extracted multi-features include instantaneous amplitude (IA) and instantaneous frequency (IF) by means of empirical mode decomposition (EMD), as well as instantaneous energy density (IE) and marginal spectrum (MS) derived from Hilbert spectral analysis. Experimental studies are performed to verify the proposed approach by using the PAMAP2 dataset from the University of California, Irvine for wearable sensors-based activity recognition. Moreover, the effect of combining multi-features vs. a single-feature are investigated and discussed in the scenario of a dependent subject. The experimental results show that multi-features combination can further improve the performance measures. Finally, we test the effect of multi-features combination in the scenario of an independent subject. Our experimental results show that we achieve four performance indexes: recall, precision, F-measure, and accuracy to 0.9337, 0.9417, 0.9353, and 0.9377 respectively, which are all better than the achievements of related works.

ANTHOCYANINS ALIPHATIC ALCOHOLS EXTRACTION FEATURES

Directory of Open Access Journals (Sweden)

P. N. Savvin

2015-01-01

Full Text Available Anthocyanins red pigments that give color a wide range of fruits, berries and flowers. In the food industry it is widely known as a dye a food additive E163. To extract from natural vegetable raw materials traditionally used ethanol or acidified water, but in same technologies it’s unacceptable. In order to expand the use of anthocyanins as colorants and antioxidants were explored extracting pigments alcohols with different structures of the carbon skeleton, and the position and number of hydroxyl groups. For the isolation anthocyanins raw materials were extracted sequentially twice with t = 60 C for 1.5 hours. The evaluation was performed using extracts of classical spectrophotometric methods and modern express chromaticity. Color black currant extracts depends on the length of the carbon skeleton and position of the hydroxyl group, with the alcohols of normal structure have higher alcohols compared to the isomeric structure of the optical density and index of the red color component. This is due to the different ability to form hydrogen bonds when allocating anthocyanins and other intermolecular interactions. During storage blackcurrant extracts are significant structural changes recoverable pigments, which leads to a significant change in color. In this variation, the stronger the higher the length of the carbon skeleton and branched molecules extractant. Extraction polyols (ethyleneglycol, glycerol are less effective than the corresponding monohydric alcohols. However these extracts saved significantly higher because of their reducing ability at interacting with polyphenolic compounds.

Deep SOMs for automated feature extraction and classification from big data streaming

Science.gov (United States)

Sakkari, Mohamed; Ejbali, Ridha; Zaied, Mourad

2017-03-01

In this paper, we proposed a deep self-organizing map model (Deep-SOMs) for automated features extracting and learning from big data streaming which we benefit from the framework Spark for real time streams and highly parallel data processing. The SOMs deep architecture is based on the notion of abstraction (patterns automatically extract from the raw data, from the less to more abstract). The proposed model consists of three hidden self-organizing layers, an input and an output layer. Each layer is made up of a multitude of SOMs, each map only focusing at local headmistress sub-region from the input image. Then, each layer trains the local information to generate more overall information in the higher layer. The proposed Deep-SOMs model is unique in terms of the layers architecture, the SOMs sampling method and learning. During the learning stage we use a set of unsupervised SOMs for feature extraction. We validate the effectiveness of our approach on large data sets such as Leukemia dataset and SRBCT. Results of comparison have shown that the Deep-SOMs model performs better than many existing algorithms for images classification.

A method of evolving novel feature extraction algorithms for detecting buried objects in FLIR imagery using genetic programming

Science.gov (United States)

Paino, A.; Keller, J.; Popescu, M.; Stone, K.

2014-06-01

In this paper we present an approach that uses Genetic Programming (GP) to evolve novel feature extraction algorithms for greyscale images. Our motivation is to create an automated method of building new feature extraction algorithms for images that are competitive with commonly used human-engineered features, such as Local Binary Pattern (LBP) and Histogram of Oriented Gradients (HOG). The evolved feature extraction algorithms are functions defined over the image space, and each produces a real-valued feature vector of variable length. Each evolved feature extractor breaks up the given image into a set of cells centered on every pixel, performs evolved operations on each cell, and then combines the results of those operations for every cell using an evolved operator. Using this method, the algorithm is flexible enough to reproduce both LBP and HOG features. The dataset we use to train and test our approach consists of a large number of pre-segmented image "chips" taken from a Forward Looking Infrared Imagery (FLIR) camera mounted on the hood of a moving vehicle. The goal is to classify each image chip as either containing or not containing a buried object. To this end, we define the fitness of a candidate solution as the cross-fold validation accuracy of the features generated by said candidate solution when used in conjunction with a Support Vector Machine (SVM) classifier. In order to validate our approach, we compare the classification accuracy of an SVM trained using our evolved features with the accuracy of an SVM trained using mainstream feature extraction algorithms, including LBP and HOG.

An improved feature extraction algorithm based on KAZE for multi-spectral image

Science.gov (United States)

Yang, Jianping; Li, Jun

2018-02-01

Multi-spectral image contains abundant spectral information, which is widely used in all fields like resource exploration, meteorological observation and modern military. Image preprocessing, such as image feature extraction and matching, is indispensable while dealing with multi-spectral remote sensing image. Although the feature matching algorithm based on linear scale such as SIFT and SURF performs strong on robustness, the local accuracy cannot be guaranteed. Therefore, this paper proposes an improved KAZE algorithm, which is based on nonlinear scale, to raise the number of feature and to enhance the matching rate by using the adjusted-cosine vector. The experiment result shows that the number of feature and the matching rate of the improved KAZE are remarkably than the original KAZE algorithm.

Multi-scale Analysis of High Resolution Topography: Feature Extraction and Identification of Landscape Characteristic Scales

Science.gov (United States)

Passalacqua, P.; Sangireddy, H.; Stark, C. P.

2015-12-01

With the advent of digital terrain data, detailed information on terrain characteristics and on scale and location of geomorphic features is available over extended areas. Our ability to observe landscapes and quantify topographic patterns has greatly improved, including the estimation of fluxes of mass and energy across landscapes. Challenges still remain in the analysis of high resolution topography data; the presence of features such as roads, for example, challenges classic methods for feature extraction and large data volumes require computationally efficient extraction and analysis methods. Moreover, opportunities exist to define new robust metrics of landscape characterization for landscape comparison and model validation. In this presentation we cover recent research in multi-scale and objective analysis of high resolution topography data. We show how the analysis of the probability density function of topographic attributes such as slope, curvature, and topographic index contains useful information for feature localization and extraction. The analysis of how the distributions change across scales, quantified by the behavior of modal values and interquartile range, allows the identification of landscape characteristic scales, such as terrain roughness. The methods are introduced on synthetic signals in one and two dimensions and then applied to a variety of landscapes of different characteristics. Validation of the methods includes the analysis of modeled landscapes where the noise distribution is known and features of interest easily measured.

Multiple-Fault Diagnosis Method Based on Multiscale Feature Extraction and MSVM_PPA

Directory of Open Access Journals (Sweden)

Min Zhang

2018-01-01

Full Text Available Identification of rolling bearing fault patterns, especially for the compound faults, has attracted notable attention and is still a challenge in fault diagnosis. In this paper, a novel method called multiscale feature extraction (MFE and multiclass support vector machine (MSVM with particle parameter adaptive (PPA is proposed. MFE is used to preprocess the process signals, which decomposes the data into intrinsic mode function by empirical mode decomposition method, and instantaneous frequency of decomposed components was obtained by Hilbert transformation. Then, statistical features and principal component analysis are utilized to extract significant information from the features, to get effective data from multiple faults. MSVM method with PPA parameters optimization will classify the fault patterns. The results of a case study of the rolling bearings faults data from Case Western Reserve University show that (1 the proposed intelligent method (MFE_PPA_MSVM improves the classification recognition rate; (2 the accuracy will decline when the number of fault patterns increases; (3 prediction accuracy can be the best when the training set size is increased to 70% of the total sample set. It verifies the method is feasible and efficient for fault diagnosis.

Advancing Affect Modeling via Preference Learning and Unsupervised Feature Extraction

DEFF Research Database (Denmark)

Martínez, Héctor Pérez

strategies (error functions and training algorithms) for artificial neural networks are examined across synthetic and psycho-physiological datasets, and compared against support vector machines and Cohen’s method. Results reveal the best training strategies for neural networks and suggest their superiority...... difficulties, ordinal reports such as rankings and ratings can yield more reliable affect annotations than alternative tools. This thesis explores preference learning methods to automatically learn computational models from ordinal annotations of affect. In particular, an extensive collection of training...... over the other examined methods. The second challenge addressed in this thesis refers to the extraction of relevant information from physiological modalities. Deep learning is proposed as an automatic approach to extract input features for models of affect from physiological signals. Experiments...

GA Based Optimal Feature Extraction Method for Functional Data Classification

OpenAIRE

Jun Wan; Zehua Chen; Yingwu Chen; Zhidong Bai

2010-01-01

Classification is an interesting problem in functional data analysis (FDA), because many science and application problems end up with classification problems, such as recognition, prediction, control, decision making, management, etc. As the high dimension and high correlation in functional data (FD), it is a key problem to extract features from FD whereas keeping its global characters, which relates to the classification efficiency and precision to heavens. In this paper...

Historical Feature Pattern Extraction Based Network Attack Situation Sensing Algorithm

OpenAIRE

Zeng, Yong; Liu, Dacheng; Lei, Zhou

2014-01-01

The situation sequence contains a series of complicated and multivariate random trends, which are very sudden, uncertain, and difficult to recognize and describe its principle by traditional algorithms. To solve the above questions, estimating parameters of super long situation sequence is essential, but very difficult, so this paper proposes a situation prediction method based on historical feature pattern extraction (HFPE). First, HFPE algorithm seeks similar indications from the history si...

Improving features used for hyper-temporal land cover change detection by reducing the uncertainty in the feature extraction method

CSIR Research Space (South Africa)

Salmon, BP

2017-07-01

Full Text Available the effect which the length of a temporal sliding window has on the success of detecting land cover change. It is shown using a short Fourier transform as a feature extraction method provides meaningful robust input to a machine learning method. In theory...

Wearable Sensor-Based Human Activity Recognition Method with Multi-Features Extracted from Hilbert-Huang Transform

Directory of Open Access Journals (Sweden)

Huile Xu

2016-12-01

Full Text Available Wearable sensors-based human activity recognition introduces many useful applications and services in health care, rehabilitation training, elderly monitoring and many other areas of human interaction. Existing works in this field mainly focus on recognizing activities by using traditional features extracted from Fourier transform (FT or wavelet transform (WT. However, these signal processing approaches are suitable for a linear signal but not for a nonlinear signal. In this paper, we investigate the characteristics of the Hilbert-Huang transform (HHT for dealing with activity data with properties such as nonlinearity and non-stationarity. A multi-features extraction method based on HHT is then proposed to improve the effect of activity recognition. The extracted multi-features include instantaneous amplitude (IA and instantaneous frequency (IF by means of empirical mode decomposition (EMD, as well as instantaneous energy density (IE and marginal spectrum (MS derived from Hilbert spectral analysis. Experimental studies are performed to verify the proposed approach by using the PAMAP2 dataset from the University of California, Irvine for wearable sensors-based activity recognition. Moreover, the effect of combining multi-features vs. a single-feature are investigated and discussed in the scenario of a dependent subject. The experimental results show that multi-features combination can further improve the performance measures. Finally, we test the effect of multi-features combination in the scenario of an independent subject. Our experimental results show that we achieve four performance indexes: recall, precision, F-measure, and accuracy to 0.9337, 0.9417, 0.9353, and 0.9377 respectively, which are all better than the achievements of related works.

Constructing New Biorthogonal Wavelet Type which Matched for Extracting the Iris Image Features

International Nuclear Information System (INIS)

Isnanto, R Rizal; Suhardjo; Susanto, Adhi

2013-01-01

Some former research have been made for obtaining a new type of wavelet. In case of iris recognition using orthogonal or biorthogonal wavelets, it had been obtained that Haar filter is most suitable to recognize the iris image. However, designing the new wavelet should be done to find a most matched wavelet to extract the iris image features, for which we can easily apply it for identification, recognition, or authentication purposes. In this research, a new biorthogonal wavelet was designed based on Haar filter properties and Haar's orthogonality conditions. As result, it can be obtained a new biorthogonal 5/7 filter type wavelet which has a better than other types of wavelets, including Haar, to extract the iris image features based on its mean-squared error (MSE) and Euclidean distance parameters.

ROAD AND ROADSIDE FEATURE EXTRACTION USING IMAGERY AND LIDAR DATA FOR TRANSPORTATION OPERATION

Directory of Open Access Journals (Sweden)

S. Ural

2015-03-01

Full Text Available Transportation agencies require up-to-date, reliable, and feasibly acquired information on road geometry and features within proximity to the roads as input for evaluating and prioritizing new or improvement road projects. The information needed for a robust evaluation of road projects includes road centerline, width, and extent together with the average grade, cross-sections, and obstructions near the travelled way. Remote sensing is equipped with a large collection of data and well-established tools for acquiring the information and extracting aforementioned various road features at various levels and scopes. Even with many remote sensing data and methods available for road extraction, transportation operation requires more than the centerlines. Acquiring information that is spatially coherent at the operational level for the entire road system is challenging and needs multiple data sources to be integrated. In the presented study, we established a framework that used data from multiple sources, including one-foot resolution color infrared orthophotos, airborne LiDAR point clouds, and existing spatially non-accurate ancillary road networks. We were able to extract 90.25% of a total of 23.6 miles of road networks together with estimated road width, average grade along the road, and cross sections at specified intervals. Also, we have extracted buildings and vegetation within a predetermined proximity to the extracted road extent. 90.6% of 107 existing buildings were correctly identified with 31% false detection rate.

Time Domain Feature Extraction Technique for earth's electric field signal prior to the Earthquake

International Nuclear Information System (INIS)

Astuti, W; Sediono, W; Akmeliawati, R; Salami, M J E

2013-01-01

Earthquake is one of the most destructive of natural disasters that killed many people and destroyed a lot of properties. By considering these catastrophic effects, it is highly important of knowing ahead of earthquakes in order to reduce the number of victims and material losses. Earth's electric field is one of the features that can be used to predict earthquakes (EQs), since it has significant changes in the amplitude of the signal prior to the earthquake. This paper presents a detailed analysis of the earth's electric field due to earthquakes which occurred in Greece, between January 1, 2008 and June 30, 2008. In that period of time, 13 earthquakes had occurred. 6 of them were recorded with magnitudes greater than Ms=5R (5R), while 7 of them were recorded with magnitudes greater than Ms=6R (6R). Time domain feature extraction technique is applied to analyze the 1st significant changes in the earth's electric field prior to the earthquake. Two different time domain feature extraction techniques are applied in this work, namely Simple Square Integral (SSI) and Root Mean Square (RMS). The 1st significant change of the earth's electric field signal in each of monitoring sites is extracted using those two techniques. The feature extraction result can be used as input parameter for an earthquake prediction system

Delineation and geometric modeling of road networks

Science.gov (United States)

Poullis, Charalambos; You, Suya

In this work we present a novel vision-based system for automatic detection and extraction of complex road networks from various sensor resources such as aerial photographs, satellite images, and LiDAR. Uniquely, the proposed system is an integrated solution that merges the power of perceptual grouping theory (Gabor filtering, tensor voting) and optimized segmentation techniques (global optimization using graph-cuts) into a unified framework to address the challenging problems of geospatial feature detection and classification. Firstly, the local precision of the Gabor filters is combined with the global context of the tensor voting to produce accurate classification of the geospatial features. In addition, the tensorial representation used for the encoding of the data eliminates the need for any thresholds, therefore removing any data dependencies. Secondly, a novel orientation-based segmentation is presented which incorporates the classification of the perceptual grouping, and results in segmentations with better defined boundaries and continuous linear segments. Finally, a set of gaussian-based filters are applied to automatically extract centerline information (magnitude, width and orientation). This information is then used for creating road segments and transforming them to their polygonal representations.

Reliable Fault Classification of Induction Motors Using Texture Feature Extraction and a Multiclass Support Vector Machine

Directory of Open Access Journals (Sweden)

Jia Uddin

2014-01-01

Full Text Available This paper proposes a method for the reliable fault detection and classification of induction motors using two-dimensional (2D texture features and a multiclass support vector machine (MCSVM. The proposed model first converts time-domain vibration signals to 2D gray images, resulting in texture patterns (or repetitive patterns, and extracts these texture features by generating the dominant neighborhood structure (DNS map. The principal component analysis (PCA is then used for the purpose of dimensionality reduction of the high-dimensional feature vector including the extracted texture features due to the fact that the high-dimensional feature vector can degrade classification performance, and this paper configures an effective feature vector including discriminative fault features for diagnosis. Finally, the proposed approach utilizes the one-against-all (OAA multiclass support vector machines (MCSVMs to identify induction motor failures. In this study, the Gaussian radial basis function kernel cooperates with OAA MCSVMs to deal with nonlinear fault features. Experimental results demonstrate that the proposed approach outperforms three state-of-the-art fault diagnosis algorithms in terms of fault classification accuracy, yielding an average classification accuracy of 100% even in noisy environments.

Feature extraction algorithm for space targets based on fractal theory

Science.gov (United States)

Tian, Balin; Yuan, Jianping; Yue, Xiaokui; Ning, Xin

2007-11-01

In order to offer a potential for extending the life of satellites and reducing the launch and operating costs, satellite servicing including conducting repairs, upgrading and refueling spacecraft on-orbit become much more frequently. Future space operations can be more economically and reliably executed using machine vision systems, which can meet real time and tracking reliability requirements for image tracking of space surveillance system. Machine vision was applied to the research of relative pose for spacecrafts, the feature extraction algorithm was the basis of relative pose. In this paper fractal geometry based edge extraction algorithm which can be used in determining and tracking the relative pose of an observed satellite during proximity operations in machine vision system was presented. The method gets the gray-level image distributed by fractal dimension used the Differential Box-Counting (DBC) approach of the fractal theory to restrain the noise. After this, we detect the consecutive edge using Mathematical Morphology. The validity of the proposed method is examined by processing and analyzing images of space targets. The edge extraction method not only extracts the outline of the target, but also keeps the inner details. Meanwhile, edge extraction is only processed in moving area to reduce computation greatly. Simulation results compared edge detection using the method which presented by us with other detection methods. The results indicate that the presented algorithm is a valid method to solve the problems of relative pose for spacecrafts.

Features extraction from image based on processes of human vision; Ningen no shikaku shori tejun ni naratta gazo no tokucho chushutsu hoho

Energy Technology Data Exchange (ETDEWEB)

Nakajima, C.; Ishino, R. [Central Research Institute of Electric Power Industry, Tokyo (Japan)

1997-03-01

Described herein is a feature extraction processing method necessary for measurement of an object on a stationary image. It imitates the structures and functions of the visual area in the human brain to automatically extract features, such as edges, lines and apexes, from a stationary image or drawing. Information transmitted from the retina to the primary visual cortex area 1 (V1 area) is processed to extract feature candidates from brightness changes on the shading-treated image. The V1 area has the cells which react with long lines and the structure which controls the other cells. This structure is used to remove noise, where a portion which is not controlled is extracted from feature candidates, and is regarded as a line feature. This procedure, involving shading, is not suited for process of images containing an out-of-focus portion, but stably extracts features from clear images or drawings. 9 refs., 28 figs.

Feature extraction and classification of clouds in high resolution panchromatic satellite imagery

Science.gov (United States)

Sharghi, Elan

The development of sophisticated remote sensing sensors is rapidly increasing, and the vast amount of satellite imagery collected is too much to be analyzed manually by a human image analyst. It has become necessary for a tool to be developed to automate the job of an image analyst. This tool would need to intelligently detect and classify objects of interest through computer vision algorithms. Existing software called the Rapid Image Exploitation Resource (RAPIER®) was designed by engineers at Space and Naval Warfare Systems Center Pacific (SSC PAC) to perform exactly this function. This software automatically searches for anomalies in the ocean and reports the detections as a possible ship object. However, if the image contains a high percentage of cloud coverage, a high number of false positives are triggered by the clouds. The focus of this thesis is to explore various feature extraction and classification methods to accurately distinguish clouds from ship objects. An examination of a texture analysis method, line detection using the Hough transform, and edge detection using wavelets are explored as possible feature extraction methods. The features are then supplied to a K-Nearest Neighbors (KNN) or Support Vector Machine (SVM) classifier. Parameter options for these classifiers are explored and the optimal parameters are determined.

Automatic building extraction from LiDAR data fusion of point and grid-based features

Science.gov (United States)

Du, Shouji; Zhang, Yunsheng; Zou, Zhengrong; Xu, Shenghua; He, Xue; Chen, Siyang

2017-08-01

This paper proposes a method for extracting buildings from LiDAR point cloud data by combining point-based and grid-based features. To accurately discriminate buildings from vegetation, a point feature based on the variance of normal vectors is proposed. For a robust building extraction, a graph cuts algorithm is employed to combine the used features and consider the neighbor contexture information. As grid feature computing and a graph cuts algorithm are performed on a grid structure, a feature-retained DSM interpolation method is proposed in this paper. The proposed method is validated by the benchmark ISPRS Test Project on Urban Classification and 3D Building Reconstruction and compared to the state-art-of-the methods. The evaluation shows that the proposed method can obtain a promising result both at area-level and at object-level. The method is further applied to the entire ISPRS dataset and to a real dataset of the Wuhan City. The results show a completeness of 94.9% and a correctness of 92.2% at the per-area level for the former dataset and a completeness of 94.4% and a correctness of 95.8% for the latter one. The proposed method has a good potential for large-size LiDAR data.

Water Extraction in High Resolution Remote Sensing Image Based on Hierarchical Spectrum and Shape Features

International Nuclear Information System (INIS)

Li, Bangyu; Zhang, Hui; Xu, Fanjiang

2014-01-01

This paper addresses the problem of water extraction from high resolution remote sensing images (including R, G, B, and NIR channels), which draws considerable attention in recent years. Previous work on water extraction mainly faced two difficulties. 1) It is difficult to obtain accurate position of water boundary because of using low resolution images. 2) Like all other image based object classification problems, the phenomena of ''different objects same image'' or ''different images same object'' affects the water extraction. Shadow of elevated objects (e.g. buildings, bridges, towers and trees) scattered in the remote sensing image is a typical noise objects for water extraction. In many cases, it is difficult to discriminate between water and shadow in a remote sensing image, especially in the urban region. We propose a water extraction method with two hierarchies: the statistical feature of spectral characteristic based on image segmentation and the shape feature based on shadow removing. In the first hierarchy, the Statistical Region Merging (SRM) algorithm is adopted for image segmentation. The SRM includes two key steps: one is sorting adjacent regions according to a pre-ascertained sort function, and the other one is merging adjacent regions based on a pre-ascertained merging predicate. The sort step is done one time during the whole processing without considering changes caused by merging which may cause imprecise results. Therefore, we modify the SRM with dynamic sort processing, which conducts sorting step repetitively when there is large adjacent region changes after doing merging. To achieve robust segmentation, we apply the merging region with six features (four remote sensing image bands, Normalized Difference Water Index (NDWI), and Normalized Saturation-value Difference Index (NSVDI)). All these features contribute to segment image into region of object. NDWI and NSVDI are discriminate between water and

Automated human skull landmarking with 2D Gabor wavelets

Science.gov (United States)

de Jong, Markus A.; Gül, Atilla; de Gijt, Jan Pieter; Koudstaal, Maarten J.; Kayser, Manfred; Wolvius, Eppo B.; Böhringer, Stefan

2018-05-01

Landmarking of CT scans is an important step in the alignment of skulls that is key in surgery planning, pre-/post-surgery comparisons, and morphometric studies. We present a novel method for automatically locating anatomical landmarks on the surface of cone beam CT-based image models of human skulls using 2D Gabor wavelets and ensemble learning. The algorithm is validated via human inter- and intra-rater comparisons on a set of 39 scans and a skull superimposition experiment with an established surgery planning software (Maxilim). Automatic landmarking results in an accuracy of 1–2 mm for a subset of landmarks around the nose area as compared to a gold standard derived from human raters. These landmarks are located in eye sockets and lower jaw, which is competitive with or surpasses inter-rater variability. The well-performing landmark subsets allow for the automation of skull superimposition in clinical applications. Our approach delivers accurate results, has modest training requirements (training set size of 30–40 items) and is generic, so that landmark sets can be easily expanded or modified to accommodate shifting landmark interests, which are important requirements for the landmarking of larger cohorts.

Chinese License Plates Recognition Method Based on A Robust and Efficient Feature Extraction and BPNN Algorithm

Science.gov (United States)

Zhang, Ming; Xie, Fei; Zhao, Jing; Sun, Rui; Zhang, Lei; Zhang, Yue

2018-04-01

The prosperity of license plate recognition technology has made great contribution to the development of Intelligent Transport System (ITS). In this paper, a robust and efficient license plate recognition method is proposed which is based on a combined feature extraction model and BPNN (Back Propagation Neural Network) algorithm. Firstly, the candidate region of the license plate detection and segmentation method is developed. Secondly, a new feature extraction model is designed considering three sets of features combination. Thirdly, the license plates classification and recognition method using the combined feature model and BPNN algorithm is presented. Finally, the experimental results indicate that the license plate segmentation and recognition both can be achieved effectively by the proposed algorithm. Compared with three traditional methods, the recognition accuracy of the proposed method has increased to 95.7% and the consuming time has decreased to 51.4ms.

LOCAL LINE BINARY PATTERN FOR FEATURE EXTRACTION ON PALM VEIN RECOGNITION

Directory of Open Access Journals (Sweden)

Jayanti Yusmah Sari

2015-08-01

Full Text Available In recent years, palm vein recognition has been studied to overcome problems in conventional systems in biometrics technology (finger print, face, and iris. Those problems in biometrics includes convenience and performance. However, due to the clarity of the palm vein image, the veins could not be segmented properly. To overcome this problem, we propose a palm vein recognition system using Local Line Binary Pattern (LLBP method that can extract robust features from the palm vein images that has unclear veins. LLBP is an advanced method of Local Binary Pattern (LBP, a texture descriptor based on the gray level comparison of a neighborhood of pixels. There are four major steps in this paper, Region of Interest (ROI detection, image preprocessing, features extraction using LLBP method, and matching using Fuzzy k-NN classifier. The proposed method was applied on the CASIA Multi-Spectral Image Database. Experimental results showed that the proposed method using LLBP has a good performance with recognition accuracy of 97.3%. In the future, experiments will be conducted to observe which parameter that could affect processing time and recognition accuracy of LLBP is needed

Enhancement and feature extraction of RS images from seismic area and seismic disaster recognition technologies

Science.gov (United States)

Zhang, Jingfa; Qin, Qiming

2003-09-01

Many types of feature extracting of RS image are analyzed, and the work procedure of pattern recognizing in RS images of seismic disaster is proposed. The aerial RS image of Tangshan Great Earthquake is processed, and the digital features of various typical seismic disaster on the RS image is calculated.

Chemical name extraction based on automatic training data generation and rich feature set.

Science.gov (United States)

Yan, Su; Spangler, W Scott; Chen, Ying

2013-01-01

The automation of extracting chemical names from text has significant value to biomedical and life science research. A major barrier in this task is the difficulty of getting a sizable and good quality data to train a reliable entity extraction model. Another difficulty is the selection of informative features of chemical names, since comprehensive domain knowledge on chemistry nomenclature is required. Leveraging random text generation techniques, we explore the idea of automatically creating training sets for the task of chemical name extraction. Assuming the availability of an incomplete list of chemical names, called a dictionary, we are able to generate well-controlled, random, yet realistic chemical-like training documents. We statistically analyze the construction of chemical names based on the incomplete dictionary, and propose a series of new features, without relying on any domain knowledge. Compared to state-of-the-art models learned from manually labeled data and domain knowledge, our solution shows better or comparable results in annotating real-world data with less human effort. Moreover, we report an interesting observation about the language for chemical names. That is, both the structural and semantic components of chemical names follow a Zipfian distribution, which resembles many natural languages.

On a possible mechanism of the brain for responding to dynamical features extracted from input signals

International Nuclear Information System (INIS)

Liu Zengrong; Chen Guanrong

2003-01-01

Based on the general theory of nonlinear dynamical systems, a possible mechanism for responding to some dynamical features extracted from input signals in brain activities is described and discussed. This mechanism is first converted to a nonlinear dynamical configuration--a generalized synchronization of complex dynamical systems. Then, some general conditions for achieving such synchronizations are derived. It is shown that dynamical systems have potentials of producing different responses for different features extracted from various input signals, which may be used to describe brain activities. For illustration, some numerical examples are given with simulation figures

Detailed Hydrographic Feature Extraction from High-Resolution LiDAR Data

Energy Technology Data Exchange (ETDEWEB)

Danny L. Anderson

2012-05-01

Detailed hydrographic feature extraction from high-resolution light detection and ranging (LiDAR) data is investigated. Methods for quantitatively evaluating and comparing such extractions are presented, including the use of sinuosity and longitudinal root-mean-square-error (LRMSE). These metrics are then used to quantitatively compare stream networks in two studies. The first study examines the effect of raster cell size on watershed boundaries and stream networks delineated from LiDAR-derived digital elevation models (DEMs). The study confirmed that, with the greatly increased resolution of LiDAR data, smaller cell sizes generally yielded better stream network delineations, based on sinuosity and LRMSE. The second study demonstrates a new method of delineating a stream directly from LiDAR point clouds, without the intermediate step of deriving a DEM. Direct use of LiDAR point clouds could improve efficiency and accuracy of hydrographic feature extractions. The direct delineation method developed herein and termed “mDn”, is an extension of the D8 method that has been used for several decades with gridded raster data. The method divides the region around a starting point into sectors, using the LiDAR data points within each sector to determine an average slope, and selecting the sector with the greatest downward slope to determine the direction of flow. An mDn delineation was compared with a traditional grid-based delineation, using TauDEM, and other readily available, common stream data sets. Although, the TauDEM delineation yielded a sinuosity that more closely matches the reference, the mDn delineation yielded a sinuosity that was higher than either the TauDEM method or the existing published stream delineations. Furthermore, stream delineation using the mDn method yielded the smallest LRMSE.

Feature extraction and classification in automatic weld seam radioscopy

International Nuclear Information System (INIS)

Heindoerfer, F.; Pohle, R.

1994-01-01

The investigations conducted have shown that automatic feature extraction and classification procedures permit the identification of weld seam flaws. Within this context the favored learning fuzzy classificator represents a very good alternative to conventional classificators. The results have also made clear that improvements mainly in the field of image registration are still possible by increasing the resolution of the radioscopy system. Since, only if the flaw is segmented correctly, i.e. in its full size, and due to improved detail recognizability and sufficient contrast difference will an almost error-free classification be conceivable. (orig./MM) [de

Linear feature extraction from radar imagery: SBIR (Small Business Innovative Research), phase 2, option 2

Science.gov (United States)

Milgram, David L.; Kahn, Philip; Conner, Gary D.; Lawton, Daryl T.

1988-12-01

The goal of this effort is to develop and demonstrate prototype processing capabilities for a knowledge-based system to automatically extract and analyze features from Synthetic Aperture Radar (SAR) imagery. This effort constitutes Phase 2 funding through the Defense Small Business Innovative Research (SBIR) Program. Previous work examined the feasibility of and technology issues involved in the development of an automated linear feature extraction system. This final report documents this examination and the technologies involved in automating this image understanding task. In particular, it reports on a major software delivery containing an image processing algorithmic base, a perceptual structures manipulation package, a preliminary hypothesis management framework and an enhanced user interface.

Wire Finishing Mill Rolling Bearing Fault Diagnosis Based on Feature Extraction and BP Neural Network

Directory of Open Access Journals (Sweden)

Hong-Yu LIU

2014-10-01

Full Text Available Rolling bearing is main part of rotary machine. It is frail section of rotary machine. Its running status affects entire mechanical equipment system performance directly. Vibration acceleration signals of the third finishing mill of Anshan Steel and Iron Group wire plant were collected in this paper. Fourier analysis, power spectrum analysis and wavelet transform were made on collected signals. Frequency domain feature extraction and wavelet transform feature extraction were made on collected signals. BP neural network fault diagnosis model was adopted. Frequency domain feature values and wavelet transform feature values were treated as neural network input values. Various typical fault models were treated as neural network output values. Corresponding relations between feature vector and fault omen were utilized. BP neural network model of typical wire plant finishing mill rolling bearing fault was constructed by training many groups sample data. After inputting sample needed to be diagnosed, wire plant finishing mill rolling bearing fault can be diagnosed. This research has important practical significance on enhancing rolling bearing fault diagnosis precision, repairing rolling bearing duly, decreasing stop time, enhancing equipment running efficiency and enhancing economic benefits.

Automated Diatom Classification (Part A: Handcrafted Feature Approaches

Directory of Open Access Journals (Sweden)

Gloria Bueno

2017-07-01

Full Text Available This paper deals with automatic taxa identification based on machine learning methods. The aim is therefore to automatically classify diatoms, in terms of pattern recognition terminology. Diatoms are a kind of algae microorganism with high biodiversity at the species level, which are useful for water quality assessment. The most relevant features for diatom description and classification have been selected using an extensive dataset of 80 taxa with a minimum of 100 samples/taxon augmented to 300 samples/taxon. In addition to published morphological, statistical and textural descriptors, a new textural descriptor, Local Binary Patterns (LBP, to characterize the diatom’s valves, and a log Gabor implementation not tested before for this purpose are introduced in this paper. Results show an overall accuracy of 98.11% using bagging decision trees and combinations of descriptors. Finally, some phycological features of diatoms that are still difficult to integrate in computer systems are discussed for future work.

Consistent Feature Extraction From Vector Fields: Combinatorial Representations and Analysis Under Local Reference Frames

Energy Technology Data Exchange (ETDEWEB)

Bhatia, Harsh [Univ. of Utah, Salt Lake City, UT (United States)

2015-05-01

This dissertation presents research on addressing some of the contemporary challenges in the analysis of vector fields—an important type of scientific data useful for representing a multitude of physical phenomena, such as wind flow and ocean currents. In particular, new theories and computational frameworks to enable consistent feature extraction from vector fields are presented. One of the most fundamental challenges in the analysis of vector fields is that their features are defined with respect to reference frames. Unfortunately, there is no single “correct” reference frame for analysis, and an unsuitable frame may cause features of interest to remain undetected, thus creating serious physical consequences. This work develops new reference frames that enable extraction of localized features that other techniques and frames fail to detect. As a result, these reference frames objectify the notion of “correctness” of features for certain goals by revealing the phenomena of importance from the underlying data. An important consequence of using these local frames is that the analysis of unsteady (time-varying) vector fields can be reduced to the analysis of sequences of steady (timeindependent) vector fields, which can be performed using simpler and scalable techniques that allow better data management by accessing the data on a per-time-step basis. Nevertheless, the state-of-the-art analysis of steady vector fields is not robust, as most techniques are numerical in nature. The residing numerical errors can violate consistency with the underlying theory by breaching important fundamental laws, which may lead to serious physical consequences. This dissertation considers consistency as the most fundamental characteristic of computational analysis that must always be preserved, and presents a new discrete theory that uses combinatorial representations and algorithms to provide consistency guarantees during vector field analysis along with the uncertainty

A New Method for Weak Fault Feature Extraction Based on Improved MED

Directory of Open Access Journals (Sweden)

Junlin Li

2018-01-01

Full Text Available Because of the characteristics of weak signal and strong noise, the low-speed vibration signal fault feature extraction has been a hot spot and difficult problem in the field of equipment fault diagnosis. Moreover, the traditional minimum entropy deconvolution (MED method has been proved to be used to detect such fault signals. The MED uses objective function method to design the filter coefficient, and the appropriate threshold value should be set in the calculation process to achieve the optimal iteration effect. It should be pointed out that the improper setting of the threshold will cause the target function to be recalculated, and the resulting error will eventually affect the distortion of the target function in the background of strong noise. This paper presents an improved MED based method of fault feature extraction from rolling bearing vibration signals that originate in high noise environments. The method uses the shuffled frog leaping algorithm (SFLA, finds the set of optimal filter coefficients, and eventually avoids the artificial error influence of selecting threshold parameter. Therefore, the fault bearing under the two rotating speeds of 60 rpm and 70 rpm is selected for verification with typical low-speed fault bearing as the research object; the results show that SFLA-MED extracts more obvious bearings and has a higher signal-to-noise ratio than the prior MED method.

Sliding Window Based Feature Extraction and Traffic Clustering for Green Mobile Cyberphysical Systems

Directory of Open Access Journals (Sweden)

Jiao Zhang

2017-01-01

Full Text Available Both the densification of small base stations and the diversity of user activities bring huge challenges for today’s heterogeneous networks, either heavy burdens on base stations or serious energy waste. In order to ensure coverage of the network while reducing the total energy consumption, we adopt a green mobile cyberphysical system (MCPS to handle this problem. In this paper, we propose a feature extraction method using sliding window to extract the distribution feature of mobile user equipment (UE, and a case study is presented to demonstrate that the method is efficacious in reserving the clustering distribution feature. Furthermore, we present traffic clustering analysis to categorize collected traffic distribution samples into a limited set of traffic patterns, where the patterns and corresponding optimized control strategies are used to similar traffic distributions for the rapid control of base station state. Experimental results show that the sliding window is more superior in enabling higher UE coverage over the grid method. Besides, the optimized control strategy obtained from the traffic pattern is capable of achieving a high coverage that can well serve over 98% of all mobile UE for similar traffic distributions.

Bilinear modeling of EMG signals to extract user-independent features for multiuser myoelectric interface.

Science.gov (United States)

Matsubara, Takamitsu; Morimoto, Jun

2013-08-01

In this study, we propose a multiuser myoelectric interface that can easily adapt to novel users. When a user performs different motions (e.g., grasping and pinching), different electromyography (EMG) signals are measured. When different users perform the same motion (e.g., grasping), different EMG signals are also measured. Therefore, designing a myoelectric interface that can be used by multiple users to perform multiple motions is difficult. To cope with this problem, we propose for EMG signals a bilinear model that is composed of two linear factors: 1) user dependent and 2) motion dependent. By decomposing the EMG signals into these two factors, the extracted motion-dependent factors can be used as user-independent features. We can construct a motion classifier on the extracted feature space to develop the multiuser interface. For novel users, the proposed adaptation method estimates the user-dependent factor through only a few interactions. The bilinear EMG model with the estimated user-dependent factor can extract the user-independent features from the novel user data. We applied our proposed method to a recognition task of five hand gestures for robotic hand control using four-channel EMG signals measured from subject forearms. Our method resulted in 73% accuracy, which was statistically significantly different from the accuracy of standard nonmultiuser interfaces, as the result of a two-sample t -test at a significance level of 1%.

An alternative to scale-space representation for extracting local features in image recognition

DEFF Research Database (Denmark)

Andersen, Hans Jørgen; Nguyen, Phuong Giang

2012-01-01

In image recognition, the common approach for extracting local features using a scale-space representation has usually three main steps; first interest points are extracted at different scales, next from a patch around each interest point the rotation is calculated with corresponding orientation...... and compensation, and finally a descriptor is computed for the derived patch (i.e. feature of the patch). To avoid the memory and computational intensive process of constructing the scale-space, we use a method where no scale-space is required This is done by dividing the given image into a number of triangles...... with sizes dependent on the content of the image, at the location of each triangle. In this paper, we will demonstrate that by rotation of the interest regions at the triangles it is possible in grey scale images to achieve a recognition precision comparable with that of MOPS. The test of the proposed method...

AN EFFICIENT METHOD FOR AUTOMATIC ROAD EXTRACTION BASED ON MULTIPLE FEATURES FROM LiDAR DATA

Directory of Open Access Journals (Sweden)

Y. Li

2016-06-01

Full Text Available The road extraction in urban areas is difficult task due to the complicated patterns and many contextual objects. LiDAR data directly provides three dimensional (3D points with less occlusions and smaller shadows. The elevation information and surface roughness are distinguishing features to separate roads. However, LiDAR data has some disadvantages are not beneficial to object extraction, such as the irregular distribution of point clouds and lack of clear edges of roads. For these problems, this paper proposes an automatic road centerlines extraction method which has three major steps: (1 road center point detection based on multiple feature spatial clustering for separating road points from ground points, (2 local principal component analysis with least squares fitting for extracting the primitives of road centerlines, and (3 hierarchical grouping for connecting primitives into complete roads network. Compared with MTH (consist of Mean shift algorithm, Tensor voting, and Hough transform proposed in our previous article, this method greatly reduced the computational cost. To evaluate the proposed method, the Vaihingen data set, a benchmark testing data provided by ISPRS for “Urban Classification and 3D Building Reconstruction” project, was selected. The experimental results show that our method achieve the same performance by less time in road extraction using LiDAR data.

An Efficient Method for Automatic Road Extraction Based on Multiple Features from LiDAR Data

Science.gov (United States)

Li, Y.; Hu, X.; Guan, H.; Liu, P.

2016-06-01

The road extraction in urban areas is difficult task due to the complicated patterns and many contextual objects. LiDAR data directly provides three dimensional (3D) points with less occlusions and smaller shadows. The elevation information and surface roughness are distinguishing features to separate roads. However, LiDAR data has some disadvantages are not beneficial to object extraction, such as the irregular distribution of point clouds and lack of clear edges of roads. For these problems, this paper proposes an automatic road centerlines extraction method which has three major steps: (1) road center point detection based on multiple feature spatial clustering for separating road points from ground points, (2) local principal component analysis with least squares fitting for extracting the primitives of road centerlines, and (3) hierarchical grouping for connecting primitives into complete roads network. Compared with MTH (consist of Mean shift algorithm, Tensor voting, and Hough transform) proposed in our previous article, this method greatly reduced the computational cost. To evaluate the proposed method, the Vaihingen data set, a benchmark testing data provided by ISPRS for "Urban Classification and 3D Building Reconstruction" project, was selected. The experimental results show that our method achieve the same performance by less time in road extraction using LiDAR data.

Gender Recognition from Human-Body Images Using Visible-Light and Thermal Camera Videos Based on a Convolutional Neural Network for Image Feature Extraction.

Science.gov (United States)

Nguyen, Dat Tien; Kim, Ki Wan; Hong, Hyung Gil; Koo, Ja Hyung; Kim, Min Cheol; Park, Kang Ryoung

2017-03-20

Extracting powerful image features plays an important role in computer vision systems. Many methods have previously been proposed to extract image features for various computer vision applications, such as the scale-invariant feature transform (SIFT), speed-up robust feature (SURF), local binary patterns (LBP), histogram of oriented gradients (HOG), and weighted HOG. Recently, the convolutional neural network (CNN) method for image feature extraction and classification in computer vision has been used in various applications. In this research, we propose a new gender recognition method for recognizing males and females in observation scenes of surveillance systems based on feature extraction from visible-light and thermal camera videos through CNN. Experimental results confirm the superiority of our proposed method over state-of-the-art recognition methods for the gender recognition problem using human body images.

Gender Recognition from Human-Body Images Using Visible-Light and Thermal Camera Videos Based on a Convolutional Neural Network for Image Feature Extraction

Science.gov (United States)

Nguyen, Dat Tien; Kim, Ki Wan; Hong, Hyung Gil; Koo, Ja Hyung; Kim, Min Cheol; Park, Kang Ryoung

2017-01-01

Extracting powerful image features plays an important role in computer vision systems. Many methods have previously been proposed to extract image features for various computer vision applications, such as the scale-invariant feature transform (SIFT), speed-up robust feature (SURF), local binary patterns (LBP), histogram of oriented gradients (HOG), and weighted HOG. Recently, the convolutional neural network (CNN) method for image feature extraction and classification in computer vision has been used in various applications. In this research, we propose a new gender recognition method for recognizing males and females in observation scenes of surveillance systems based on feature extraction from visible-light and thermal camera videos through CNN. Experimental results confirm the superiority of our proposed method over state-of-the-art recognition methods for the gender recognition problem using human body images. PMID:28335510

Cue combination in a combined feature contrast detection and figure identification task.

Science.gov (United States)

Meinhardt, Günter; Persike, Malte; Mesenholl, Björn; Hagemann, Cordula

2006-11-01

Target figures defined by feature contrast in spatial frequency, orientation or both cues had to be detected in Gabor random fields and their shape had to be identified in a dual task paradigm. Performance improved with increasing feature contrast and was strongly correlated among both tasks. Subjects performed significantly better with combined cues than with single cues. The improvement due to cue summation was stronger than predicted by the assumption of independent feature specific mechanisms, and increased with the performance level achieved with single cues until it was limited by ceiling effects. Further, cue summation was also strongly correlated among tasks: when there was benefit due to the additional cue in feature contrast detection, there was also benefit in figure identification. For the same performance level achieved with single cues, cue summation was generally larger in figure identification than in feature contrast detection, indicating more benefit when processes of shape and surface formation are involved. Our results suggest that cue combination improves spatial form completion and figure-ground segregation in noisy environments, and therefore leads to more stable object vision.

Feature extraction based on extended multi-attribute profiles and sparse autoencoder for remote sensing image classification

Science.gov (United States)

Teffahi, Hanane; Yao, Hongxun; Belabid, Nasreddine; Chaib, Souleyman

2018-02-01

The satellite images with very high spatial resolution have been recently widely used in image classification topic as it has become challenging task in remote sensing field. Due to a number of limitations such as the redundancy of features and the high dimensionality of the data, different classification methods have been proposed for remote sensing images classification particularly the methods using feature extraction techniques. This paper propose a simple efficient method exploiting the capability of extended multi-attribute profiles (EMAP) with sparse autoencoder (SAE) for remote sensing image classification. The proposed method is used to classify various remote sensing datasets including hyperspectral and multispectral images by extracting spatial and spectral features based on the combination of EMAP and SAE by linking them to kernel support vector machine (SVM) for classification. Experiments on new hyperspectral image "Huston data" and multispectral image "Washington DC data" shows that this new scheme can achieve better performance of feature learning than the primitive features, traditional classifiers and ordinary autoencoder and has huge potential to achieve higher accuracy for classification in short running time.

Point features extraction: towards slam for an autonomous underwater vehicle

CSIR Research Space (South Africa)

Matsebe, O

2010-07-01

Full Text Available and Control. Available: http://www.robots.ox.ac.uk/~pnewman/papers/Robotica.pdf, date accessed: [2009, 05/20] [7] Williams, S.B., Newman, P., Rosenblatt, J., Dissanayake, G. & Whyte, H.D., Autonomous Underwater Simultaneous and Localisation and Map Building.... Available: http://www.robots.ox.ac.uk/~pnewman/papers/Robotica.pdf., date accessed: [2009, 05/20] [8]http://www.tritech.co.uk/products/products-micron_sonar.htm, date accessed: [10/01/10] [9] Tena, I., Petillot, Y., Lane, D.M.,Salson. Feature Extraction...

Extraction of features from sleep EEG for Bayesian assessment of brain development.

Directory of Open Access Journals (Sweden)

Vitaly Schetinin

Full Text Available Brain development can be evaluated by experts analysing age-related patterns in sleep electroencephalograms (EEG. Natural variations in the patterns, noise, and artefacts affect the evaluation accuracy as well as experts' agreement. The knowledge of predictive posterior distribution allows experts to estimate confidence intervals within which decisions are distributed. Bayesian approach to probabilistic inference has provided accurate estimates of intervals of interest. In this paper we propose a new feature extraction technique for Bayesian assessment and estimation of predictive distribution in a case of newborn brain development assessment. The new EEG features are verified within the Bayesian framework on a large EEG data set including 1,100 recordings made from newborns in 10 age groups. The proposed features are highly correlated with brain maturation and their use increases the assessment accuracy.

Preattentive extraction of abstract feature conjunctions from auditory stimulation as reflected by the mismatch negativity (MMN).

Science.gov (United States)

Paavilainen, P; Simola, J; Jaramillo, M; Näätänen, R; Winkler, I

2001-03-01

Brain mechanisms extracting invariant information from varying auditory inputs were studied using the mismatch-negativity (MMN) brain response. We wished to determine whether the preattentive sound-analysis mechanisms, reflected by MMN, are capable of extracting invariant relationships based on abstract conjunctions between two sound features. The standard stimuli varied over a large range in frequency and intensity dimensions following the rule that the higher the frequency, the louder the intensity. The occasional deviant stimuli violated this frequency-intensity relationship and elicited an MMN. The results demonstrate that preattentive processing of auditory stimuli extends to unexpectedly complex relationships between the stimulus features.

Linear feature extraction from radar imagery: SBIR (Small Business Innovative Research) phase 2, option 1

Science.gov (United States)

Conner, Gary D.; Milgram, David L.; Lawton, Daryl T.; McConnell, Christopher C.

1988-04-01

The goal of this effort is to develop and demonstrate prototype processing capabilities for a knowledge-based system to automatically extract and analyze linear features from synthetic aperture radar (SAR) imagery. This effort constitutes Phase 2 funding through the Defense Small Business Innovative Research (SBIR) Program. Previous work examined the feasibility of the technology issues involved in the development of an automatedlinear feature extraction system. This Option 1 Final Report documents this examination and the technologies involved in automating this image understanding task. In particular, it reports on a major software delivery containing an image processing algorithmic base, a perceptual structures manipulation package, a preliminary hypothesis management framework and an enhanced user interface.

An expert botanical feature extraction technique based on phenetic features for identifying plant species.

Directory of Open Access Journals (Sweden)

Hoshang Kolivand

Full Text Available In this paper, we present a new method to recognise the leaf type and identify plant species using phenetic parts of the leaf; lobes, apex and base detection. Most of the research in this area focuses on the popular features such as the shape, colour, vein, and texture, which consumes large amounts of computational processing and are not efficient, especially in the Acer database with a high complexity structure of the leaves. This paper is focused on phenetic parts of the leaf which increases accuracy. Detecting the local maxima and local minima are done based on Centroid Contour Distance for Every Boundary Point, using north and south region to recognise the apex and base. Digital morphology is used to measure the leaf shape and the leaf margin. Centroid Contour Gradient is presented to extract the curvature of leaf apex and base. We analyse 32 leaf images of tropical plants and evaluated with two different datasets, Flavia, and Acer. The best accuracy obtained is 94.76% and 82.6% respectively. Experimental results show the effectiveness of the proposed technique without considering the commonly used features with high computational cost.

An expert botanical feature extraction technique based on phenetic features for identifying plant species

Science.gov (United States)

Fern, Bong Mei; Rahim, Mohd Shafry Mohd; Sulong, Ghazali; Baker, Thar; Tully, David

2018-01-01

In this paper, we present a new method to recognise the leaf type and identify plant species using phenetic parts of the leaf; lobes, apex and base detection. Most of the research in this area focuses on the popular features such as the shape, colour, vein, and texture, which consumes large amounts of computational processing and are not efficient, especially in the Acer database with a high complexity structure of the leaves. This paper is focused on phenetic parts of the leaf which increases accuracy. Detecting the local maxima and local minima are done based on Centroid Contour Distance for Every Boundary Point, using north and south region to recognise the apex and base. Digital morphology is used to measure the leaf shape and the leaf margin. Centroid Contour Gradient is presented to extract the curvature of leaf apex and base. We analyse 32 leaf images of tropical plants and evaluated with two different datasets, Flavia, and Acer. The best accuracy obtained is 94.76% and 82.6% respectively. Experimental results show the effectiveness of the proposed technique without considering the commonly used features with high computational cost. PMID:29420568

Automatic Target Recognition in Synthetic Aperture Sonar Images Based on Geometrical Feature Extraction

Directory of Open Access Journals (Sweden)

J. Del Rio Vera

2009-01-01

Full Text Available This paper presents a new supervised classification approach for automated target recognition (ATR in SAS images. The recognition procedure starts with a novel segmentation stage based on the Hilbert transform. A number of geometrical features are then extracted and used to classify observed objects against a previously compiled database of target and non-target features. The proposed approach has been tested on a set of 1528 simulated images created by the NURC SIGMAS sonar model, achieving up to 95% classification accuracy.

Achieving Accurate Automatic Sleep Staging on Manually Pre-processed EEG Data Through Synchronization Feature Extraction and Graph Metrics.

Science.gov (United States)

Chriskos, Panteleimon; Frantzidis, Christos A; Gkivogkli, Polyxeni T; Bamidis, Panagiotis D; Kourtidou-Papadeli, Chrysoula

2018-01-01

Sleep staging, the process of assigning labels to epochs of sleep, depending on the stage of sleep they belong, is an arduous, time consuming and error prone process as the initial recordings are quite often polluted by noise from different sources. To properly analyze such data and extract clinical knowledge, noise components must be removed or alleviated. In this paper a pre-processing and subsequent sleep staging pipeline for the sleep analysis of electroencephalographic signals is described. Two novel methods of functional connectivity estimation (Synchronization Likelihood/SL and Relative Wavelet Entropy/RWE) are comparatively investigated for automatic sleep staging through manually pre-processed electroencephalographic recordings. A multi-step process that renders signals suitable for further analysis is initially described. Then, two methods that rely on extracting synchronization features from electroencephalographic recordings to achieve computerized sleep staging are proposed, based on bivariate features which provide a functional overview of the brain network, contrary to most proposed methods that rely on extracting univariate time and frequency features. Annotation of sleep epochs is achieved through the presented feature extraction methods by training classifiers, which are in turn able to accurately classify new epochs. Analysis of data from sleep experiments on a randomized, controlled bed-rest study, which was organized by the European Space Agency and was conducted in the "ENVIHAB" facility of the Institute of Aerospace Medicine at the German Aerospace Center (DLR) in Cologne, Germany attains high accuracy rates, over 90% based on ground truth that resulted from manual sleep staging by two experienced sleep experts. Therefore, it can be concluded that the above feature extraction methods are suitable for semi-automatic sleep staging.

Digital tool for detecting diabetic retinopathy in retinography image using gabor transform

Science.gov (United States)

Morales, Y.; Nuñez, R.; Suarez, J.; Torres, C.

2017-01-01

Diabetic retinopathy is a chronic disease and is the leading cause of blindness in the population. The fundamental problem is that diabetic retinopathy is usually asymptomatic in its early stage and, in advanced stages, it becomes incurable, hence the importance of early detection. To detect diabetic retinopathy, the ophthalmologist examines the fundus by ophthalmoscopy, after sends the patient to get a Retinography. Sometimes, these retinography are not of good quality. This paper show the implementation of a digital tool that facilitates to ophthalmologist provide better patient diagnosis suffering from diabetic retinopathy, informing them that type of retinopathy has and to what degree of severity is find . This tool develops an algorithm in Matlab based on Gabor transform and in the application of digital filters to provide better and higher quality of retinography. The performance of algorithm has been compared with conventional methods obtaining resulting filtered images with better contrast and higher.

Feature extraction for face recognition via Active Shape Model (ASM) and Active Appearance Model (AAM)

Science.gov (United States)

Iqtait, M.; Mohamad, F. S.; Mamat, M.

2018-03-01

Biometric is a pattern recognition system which is used for automatic recognition of persons based on characteristics and features of an individual. Face recognition with high recognition rate is still a challenging task and usually accomplished in three phases consisting of face detection, feature extraction, and expression classification. Precise and strong location of trait point is a complicated and difficult issue in face recognition. Cootes proposed a Multi Resolution Active Shape Models (ASM) algorithm, which could extract specified shape accurately and efficiently. Furthermore, as the improvement of ASM, Active Appearance Models algorithm (AAM) is proposed to extracts both shape and texture of specified object simultaneously. In this paper we give more details about the two algorithms and give the results of experiments, testing their performance on one dataset of faces. We found that the ASM is faster and gains more accurate trait point location than the AAM, but the AAM gains a better match to the texture.

Gender Recognition from Human-Body Images Using Visible-Light and Thermal Camera Videos Based on a Convolutional Neural Network for Image Feature Extraction

Directory of Open Access Journals (Sweden)

Dat Tien Nguyen

2017-03-01

Full Text Available Extracting powerful image features plays an important role in computer vision systems. Many methods have previously been proposed to extract image features for various computer vision applications, such as the scale-invariant feature transform (SIFT, speed-up robust feature (SURF, local binary patterns (LBP, histogram of oriented gradients (HOG, and weighted HOG. Recently, the convolutional neural network (CNN method for image feature extraction and classification in computer vision has been used in various applications. In this research, we propose a new gender recognition method for recognizing males and females in observation scenes of surveillance systems based on feature extraction from visible-light and thermal camera videos through CNN. Experimental results confirm the superiority of our proposed method over state-of-the-art recognition methods for the gender recognition problem using human body images.

Dynamic biometric identification from multiple views using the GLBP-TOP method.

Science.gov (United States)

Wang, Yu; Shen, Xuanjing; Chen, Haipeng; Zhai, Yujie

2014-01-01

To realize effective and rapid dynamic biometric identification with low computational complexity, a video-based facial texture program that extracts local binary patterns from three orthogonal planes in the frequency domain of the Gabor transform (GLBP-TOP) was proposed. Firstly, each normalized face was transformed by Gabor wavelet to get the enhanced Gabor magnitude map, and then the LBP-TOP operator was applied to the maps to extract video texture. Finally, weighted Chi square statistics based on the Fisher Criterion were used to realize the identification. The proposed algorithm was proved effective through the biometric experiments using the Honda/UCSD database, and was robust against changes of illumination and expressions.

A study on the extraction of feature variables for the pattern recognition for welding flaws

International Nuclear Information System (INIS)

Kim, J. Y.; Kim, C. H.; Kim, B. H.

1996-01-01

In this study, the researches classifying the artificial and natural flaws in welding parts are performed using the pattern recognition technology. For this purpose the signal pattern recognition package including the user defined function was developed and the total procedure including the digital signal processing, feature extraction, feature selection and classifier selection is treated by bulk. Specially it is composed with and discussed using the statistical classifier such as the linear discriminant function classifier, the empirical Bayesian classifier. Also, the pattern recognition technology is applied to classification problem of natural flaw(i.e multiple classification problem-crack, lack of penetration, lack of fusion, porosity, and slag inclusion, the planar and volumetric flaw classification problem). According to this results, if appropriately teamed the neural network classifier is better than stastical classifier in the classification problem of natural flaw. And it is possible to acquire the recognition rate of 80% above through it is different a little according to domain extracting the feature and the classifier.

Statistical Feature Extraction for Fault Locations in Nonintrusive Fault Detection of Low Voltage Distribution Systems

Directory of Open Access Journals (Sweden)

Hsueh-Hsien Chang

2017-04-01

Full Text Available This paper proposes statistical feature extraction methods combined with artificial intelligence (AI approaches for fault locations in non-intrusive single-line-to-ground fault (SLGF detection of low voltage distribution systems. The input features of the AI algorithms are extracted using statistical moment transformation for reducing the dimensions of the power signature inputs measured by using non-intrusive fault monitoring (NIFM techniques. The data required to develop the network are generated by simulating SLGF using the Electromagnetic Transient Program (EMTP in a test system. To enhance the identification accuracy, these features after normalization are given to AI algorithms for presenting and evaluating in this paper. Different AI techniques are then utilized to compare which identification algorithms are suitable to diagnose the SLGF for various power signatures in a NIFM system. The simulation results show that the proposed method is effective and can identify the fault locations by using non-intrusive monitoring techniques for low voltage distribution systems.

Iris Recognition Using Feature Extraction of Box Counting Fractal Dimension

Science.gov (United States)

Khotimah, C.; Juniati, D.

2018-01-01

Biometrics is a science that is now growing rapidly. Iris recognition is a biometric modality which captures a photo of the eye pattern. The markings of the iris are distinctive that it has been proposed to use as a means of identification, instead of fingerprints. Iris recognition was chosen for identification in this research because every human has a special feature that each individual is different and the iris is protected by the cornea so that it will have a fixed shape. This iris recognition consists of three step: pre-processing of data, feature extraction, and feature matching. Hough transformation is used in the process of pre-processing to locate the iris area and Daugman’s rubber sheet model to normalize the iris data set into rectangular blocks. To find the characteristics of the iris, it was used box counting method to get the fractal dimension value of the iris. Tests carried out by used k-fold cross method with k = 5. In each test used 10 different grade K of K-Nearest Neighbor (KNN). The result of iris recognition was obtained with the best accuracy was 92,63 % for K = 3 value on K-Nearest Neighbor (KNN) method.

Feature Extraction for Track Section Status Classification Based on UGW Signals

Directory of Open Access Journals (Sweden)

Lei Yuan

2018-04-01

Full Text Available Track status classification is essential for the stability and safety of railway operations nowadays, when railway networks are becoming more and more complex and broad. In this situation, monitoring systems are already a key element in applications dedicated to evaluating the status of a certain track section, often determining whether it is free or occupied by a train. Different technologies have already been involved in the design of monitoring systems, including ultrasonic guided waves (UGW. This work proposes the use of the UGW signals captured by a track monitoring system to extract the features that are relevant for determining the corresponding track section status. For that purpose, three features of UGW signals have been considered: the root mean square value, the energy, and the main frequency components. Experimental results successfully validated how these features can be used to classify the track section status into free, occupied and broken. Furthermore, spatial and temporal dependencies among these features were analysed in order to show how they can improve the final classification performance. Finally, a preliminary high-level classification system based on deep learning networks has been envisaged for future works.

Credible Set Estimation, Analysis, and Applications in Synthetic Aperture Radar Canonical Feature Extraction

Science.gov (United States)

2015-03-26

83 5.1 Marginal PMFs for the cylinder scene at coarse zoom. . . . . . . . . . . . . . . 85 5.2 SAR image of a Nissan Sentra with canonical...of a Nissan Sentra with canonical features extracted by the SPLIT algorithm. 5.2.4 Experiment Summary. A notional algorithm is presented in Figure 5.3

Feature Extraction in the North Sinai Desert Using Spaceborne Synthetic Aperture Radar: Potential Archaeological Applications

Directory of Open Access Journals (Sweden)

Christopher Stewart

2016-10-01

Full Text Available Techniques were implemented to extract anthropogenic features in the desert region of North Sinai using data from the first- and second-generation Phased Array type L-band Synthetic Aperture Radar (PALSAR-1 and 2. To obtain a synoptic view over the study area, a mosaic of average, multitemporal (De Grandi filtered PALSAR-1 σ° backscatter of North Sinai was produced. Two subset regions were selected for further analysis. The first included an area of abundant linear features of high relative backscatter in a strategic, but sparsely developed area between the Wadi Tumilat and Gebel Maghara. The second included an area of low backscatter anomaly features in a coastal sabkha around the archaeological sites of Tell el-Farama, Tell el-Mahzan, and Tell el-Kanais. Over the subset region between the Wadi Tumilat and Gebel Maghara, algorithms were developed to extract linear features and convert them to vector format to facilitate interpretation. The algorithms were based on mathematical morphology, but to distinguish apparent man-made features from sand dune ridges, several techniques were applied. The first technique took as input the average σ° backscatter and used a Digital Elevation Model (DEM derived Local Incidence Angle (LAI mask to exclude sand dune ridges. The second technique, which proved more effective, used the average interferometric coherence as input. Extracted features were compared with other available information layers and in some cases revealed partially buried roads. Over the coastal subset region a time series of PALSAR-2 spotlight data were processed. The coefficient of variation (CoV of De Grandi filtered imagery clearly revealed anomaly features of low CoV. These were compared with the results of an archaeological field walking survey carried out previously. The features generally correspond with isolated areas identified in the field survey as having a higher density of archaeological finds, and interpreted as possible

Raft cultivation area extraction from high resolution remote sensing imagery by fusing multi-scale region-line primitive association features

Science.gov (United States)

Wang, Min; Cui, Qi; Wang, Jie; Ming, Dongping; Lv, Guonian

2017-01-01

In this paper, we first propose several novel concepts for object-based image analysis, which include line-based shape regularity, line density, and scale-based best feature value (SBV), based on the region-line primitive association framework (RLPAF). We then propose a raft cultivation area (RCA) extraction method for high spatial resolution (HSR) remote sensing imagery based on multi-scale feature fusion and spatial rule induction. The proposed method includes the following steps: (1) Multi-scale region primitives (segments) are obtained by image segmentation method HBC-SEG, and line primitives (straight lines) are obtained by phase-based line detection method. (2) Association relationships between regions and lines are built based on RLPAF, and then multi-scale RLPAF features are extracted and SBVs are selected. (3) Several spatial rules are designed to extract RCAs within sea waters after land and water separation. Experiments show that the proposed method can successfully extract different-shaped RCAs from HR images with good performance.

Data-Wave-Based Features Extraction and Its Application in Symbol Identifier Recognition and Positioning Suitable for Multi-Robot Systems

Directory of Open Access Journals (Sweden)

Xilong Liu

2012-12-01

Full Text Available In this paper, feature extraction based on data-wave is proposed. The concept of data-wave is introduced to describe the rising and falling trends of the data over the long-term which are detected based on ripple and wave filters. Supported by data-wave, a novel symbol identifier with significant structure features is designed and these features are extracted by constructing pixel chains. On this basis, the corresponding recognition and positioning approach is presented. The effectiveness of the proposed approach is verified by experiments.

The Fault Feature Extraction of Rolling Bearing Based on EMD and Difference Spectrum of Singular Value

Directory of Open Access Journals (Sweden)

Te Han

2016-01-01

Full Text Available Nowadays, the fault diagnosis of rolling bearing in aeroengines is based on the vibration signal measured on casing, instead of bearing block. However, the vibration signal of the bearing is often covered by a series of complex components caused by other structures (rotor, gears. Therefore, when bearings cause failure, it is still not certain that the fault feature can be extracted from the vibration signal on casing. In order to solve this problem, a novel fault feature extraction method for rolling bearing based on empirical mode decomposition (EMD and the difference spectrum of singular value is proposed in this paper. Firstly, the vibration signal is decomposed by EMD. Next, the difference spectrum of singular value method is applied. The study finds that each peak on the difference spectrum corresponds to each component in the original signal. According to the peaks on the difference spectrum, the component signal of the bearing fault can be reconstructed. To validate the proposed method, the bearing fault data collected on the casing are analyzed. The results indicate that the proposed rolling bearing diagnosis method can accurately extract the fault feature that is submerged in other component signals and noise.

Detection of architectural distortion in prior screening mammograms using Gabor filters, phase portraits, fractal dimension, and texture analysis

International Nuclear Information System (INIS)

Rangayyan, Rangaraj M.; Prajna, Shormistha; Ayres, Fabio J.; Desautels, J.E.L.

2008-01-01

Mammography is a widely used screening tool for the early detection of breast cancer. One of the commonly missed signs of breast cancer is architectural distortion. The purpose of this study is to explore the application of fractal analysis and texture measures for the detection of architectural distortion in screening mammograms taken prior to the detection of breast cancer. A method based on Gabor filters and phase portrait analysis was used to detect initial candidates for sites of architectural distortion. A total of 386 regions of interest (ROIs) were automatically obtained from 14 ''prior mammograms'', including 21 ROIs related to architectural distortion. From the corresponding set of 14 ''detection mammograms'', 398 ROIs were obtained, including 18 related to breast cancer. For each ROI, the fractal dimension and Haralick's texture features were computed. The fractal dimension of the ROIs was calculated using the circular average power spectrum technique. The average fractal dimension of the normal (false-positive) ROIs was significantly higher than that of the ROIs with architectural distortion (p = 0.006). For the ''prior mammograms'', the best receiver operating characteristics (ROC) performance achieved, in terms of the area under the ROC curve, was 0.80 with a Bayesian classifier using four features including fractal dimension, entropy, sum entropy, and inverse difference moment. Analysis of the performance of the methods with free-response receiver operating characteristics indicated a sensitivity of 0.79 at 8.4 false positives per image in the detection of sites of architectural distortion in the ''prior mammograms''. Fractal dimension offers a promising way to detect the presence of architectural distortion in prior mammograms. (orig.)

Distant supervision for neural relation extraction integrated with word attention and property features.

Science.gov (United States)

Qu, Jianfeng; Ouyang, Dantong; Hua, Wen; Ye, Yuxin; Li, Ximing

2018-04-01

Distant supervision for neural relation extraction is an efficient approach to extracting massive relations with reference to plain texts. However, the existing neural methods fail to capture the critical words in sentence encoding and meanwhile lack useful sentence information for some positive training instances. To address the above issues, we propose a novel neural relation extraction model. First, we develop a word-level attention mechanism to distinguish the importance of each individual word in a sentence, increasing the attention weights for those critical words. Second, we investigate the semantic information from word embeddings of target entities, which can be developed as a supplementary feature for the extractor. Experimental results show that our model outperforms previous state-of-the-art baselines. Copyright © 2018 Elsevier Ltd. All rights reserved.

An Accurate CT Saturation Classification Using a Deep Learning Approach Based on Unsupervised Feature Extraction and Supervised Fine-Tuning Strategy

Directory of Open Access Journals (Sweden)

Muhammad Ali

2017-11-01

Full Text Available Current transformer (CT saturation is one of the significant problems for protection engineers. If CT saturation is not tackled properly, it can cause a disastrous effect on the stability of the power system, and may even create a complete blackout. To cope with CT saturation properly, an accurate detection or classification should be preceded. Recently, deep learning (DL methods have brought a subversive revolution in the field of artificial intelligence (AI. This paper presents a new DL classification method based on unsupervised feature extraction and supervised fine-tuning strategy to classify the saturated and unsaturated regions in case of CT saturation. In other words, if protection system is subjected to a CT saturation, proposed method will correctly classify the different levels of saturation with a high accuracy. Traditional AI methods are mostly based on supervised learning and rely heavily on human crafted features. This paper contributes to an unsupervised feature extraction, using autoencoders and deep neural networks (DNNs to extract features automatically without prior knowledge of optimal features. To validate the effectiveness of proposed method, a variety of simulation tests are conducted, and classification results are analyzed using standard classification metrics. Simulation results confirm that proposed method classifies the different levels of CT saturation with a remarkable accuracy and has unique feature extraction capabilities. Lastly, we provided a potential future research direction to conclude this paper.

Discriminative kernel feature extraction and learning for object recognition and detection

DEFF Research Database (Denmark)

Pan, Hong; Olsen, Søren Ingvor; Zhu, Yaping

2015-01-01

Feature extraction and learning is critical for object recognition and detection. By embedding context cue of image attributes into the kernel descriptors, we propose a set of novel kernel descriptors called context kernel descriptors (CKD). The motivation of CKD is to use the spatial consistency...... even in high-dimensional space. In addition, the latent connection between Rényi quadratic entropy and the mapping data in kernel feature space further facilitates us to capture the geometric structure as well as the information about the underlying labels of the CKD using CSQMI. Thus the resulting...... codebook and reduced CKD are discriminative. We report superior performance of our algorithm for object recognition on benchmark datasets like Caltech-101 and CIFAR-10, as well as for detection on a challenging chicken feet dataset....

Multi-source feature extraction and target recognition in wireless sensor networks based on adaptive distributed wavelet compression algorithms

Science.gov (United States)

Hortos, William S.

2008-04-01

Proposed distributed wavelet-based algorithms are a means to compress sensor data received at the nodes forming a wireless sensor network (WSN) by exchanging information between neighboring sensor nodes. Local collaboration among nodes compacts the measurements, yielding a reduced fused set with equivalent information at far fewer nodes. Nodes may be equipped with multiple sensor types, each capable of sensing distinct phenomena: thermal, humidity, chemical, voltage, or image signals with low or no frequency content as well as audio, seismic or video signals within defined frequency ranges. Compression of the multi-source data through wavelet-based methods, distributed at active nodes, reduces downstream processing and storage requirements along the paths to sink nodes; it also enables noise suppression and more energy-efficient query routing within the WSN. Targets are first detected by the multiple sensors; then wavelet compression and data fusion are applied to the target returns, followed by feature extraction from the reduced data; feature data are input to target recognition/classification routines; targets are tracked during their sojourns through the area monitored by the WSN. Algorithms to perform these tasks are implemented in a distributed manner, based on a partition of the WSN into clusters of nodes. In this work, a scheme of collaborative processing is applied for hierarchical data aggregation and decorrelation, based on the sensor data itself and any redundant information, enabled by a distributed, in-cluster wavelet transform with lifting that allows multiple levels of resolution. The wavelet-based compression algorithm significantly decreases RF bandwidth and other resource use in target processing tasks. Following wavelet compression, features are extracted. The objective of feature extraction is to maximize the probabilities of correct target classification based on multi-source sensor measurements, while minimizing the resource expenditures at

The quantum state vector in phase space and Gabor's windowed Fourier transform

International Nuclear Information System (INIS)

Bracken, A J; Watson, P

2010-01-01

Representations of quantum state vectors by complex phase space amplitudes, complementing the description of the density operator by the Wigner function, have been defined by applying the Weyl-Wigner transform to dyadic operators, linear in the state vector and anti-linear in a fixed 'window state vector'. Here aspects of this construction are explored, and a connection is established with Gabor's 'windowed Fourier transform'. The amplitudes that arise for simple quantum states from various choices of windows are presented as illustrations. Generalized Bargmann representations of the state vector appear as special cases, associated with Gaussian windows. For every choice of window, amplitudes lie in a corresponding linear subspace of square-integrable functions on phase space. A generalized Born interpretation of amplitudes is described, with both the Wigner function and a generalized Husimi function appearing as quantities linear in an amplitude and anti-linear in its complex conjugate. Schroedinger's time-dependent and time-independent equations are represented on phase space amplitudes, and their solutions described in simple cases.

A comparative study of image low level feature extraction algorithms

Directory of Open Access Journals (Sweden)

M.M. El-gayar

2013-07-01

Full Text Available Feature extraction and matching is at the base of many computer vision problems, such as object recognition or structure from motion. Current methods for assessing the performance of popular image matching algorithms are presented and rely on costly descriptors for detection and matching. Specifically, the method assesses the type of images under which each of the algorithms reviewed herein perform to its maximum or highest efficiency. The efficiency is measured in terms of the number of matches founds by the algorithm and the number of type I and type II errors encountered when the algorithm is tested against a specific pair of images. Current comparative studies asses the performance of the algorithms based on the results obtained in different criteria such as speed, sensitivity, occlusion, and others. This study addresses the limitations of the existing comparative tools and delivers a generalized criterion to determine beforehand the level of efficiency expected from a matching algorithm given the type of images evaluated. The algorithms and the respective images used within this work are divided into two groups: feature-based and texture-based. And from this broad classification only three of the most widely used algorithms are assessed: color histogram, FAST (Features from Accelerated Segment Test, SIFT (Scale Invariant Feature Transform, PCA-SIFT (Principal Component Analysis-SIFT, F-SIFT (fast-SIFT and SURF (speeded up robust features. The performance of the Fast-SIFT (F-SIFT feature detection methods are compared for scale changes, rotation, blur, illumination changes and affine transformations. All the experiments use repeatability measurement and the number of correct matches for the evaluation measurements. SIFT presents its stability in most situations although its slow. F-SIFT is the fastest one with good performance as the same as SURF, SIFT, PCA-SIFT show its advantages in rotation and illumination changes.

Deep PDF parsing to extract features for detecting embedded malware.

Energy Technology Data Exchange (ETDEWEB)

Munson, Miles Arthur; Cross, Jesse S. (Missouri University of Science and Technology, Rolla, MO)

2011-09-01

The number of PDF files with embedded malicious code has risen significantly in the past few years. This is due to the portability of the file format, the ways Adobe Reader recovers from corrupt PDF files, the addition of many multimedia and scripting extensions to the file format, and many format properties the malware author may use to disguise the presence of malware. Current research focuses on executable, MS Office, and HTML formats. In this paper, several features and properties of PDF Files are identified. Features are extracted using an instrumented open source PDF viewer. The feature descriptions of benign and malicious PDFs can be used to construct a machine learning model for detecting possible malware in future PDF files. The detection rate of PDF malware by current antivirus software is very low. A PDF file is easy to edit and manipulate because it is a text format, providing a low barrier to malware authors. Analyzing PDF files for malware is nonetheless difficult because of (a) the complexity of the formatting language, (b) the parsing idiosyncrasies in Adobe Reader, and (c) undocumented correction techniques employed in Adobe Reader. In May 2011, Esparza demonstrated that PDF malware could be hidden from 42 of 43 antivirus packages by combining multiple obfuscation techniques [4]. One reason current antivirus software fails is the ease of varying byte sequences in PDF malware, thereby rendering conventional signature-based virus detection useless. The compression and encryption functions produce sequences of bytes that are each functions of multiple input bytes. As a result, padding the malware payload with some whitespace before compression/encryption can change many of the bytes in the final payload. In this study we analyzed a corpus of 2591 benign and 87 malicious PDF files. While this corpus is admittedly small, it allowed us to test a system for collecting indicators of embedded PDF malware. We will call these indicators features throughout

Visual feature extraction and establishment of visual tags in the intelligent visual internet of things

Science.gov (United States)

Zhao, Yiqun; Wang, Zhihui

2015-12-01

The Internet of things (IOT) is a kind of intelligent networks which can be used to locate, track, identify and supervise people and objects. One of important core technologies of intelligent visual internet of things ( IVIOT) is the intelligent visual tag system. In this paper, a research is done into visual feature extraction and establishment of visual tags of the human face based on ORL face database. Firstly, we use the principal component analysis (PCA) algorithm for face feature extraction, then adopt the support vector machine (SVM) for classifying and face recognition, finally establish a visual tag for face which is already classified. We conducted a experiment focused on a group of people face images, the result show that the proposed algorithm have good performance, and can show the visual tag of objects conveniently.

Descending necrotizing mediastinitis following dental extraction. Radiological features and surgical treatment considerations.

Science.gov (United States)

González-García, Raúl; Risco-Rojas, Roberto; Román-Romero, Leticia; Moreno-García, Carlos; López García, Cipriano

2011-07-01

Descending necrotizing mediastinitis (DNM) following dental extraction is an extremely serious infection with a high mortality rate. Oral infection may rapidly descend into the mediastinum across the retropharyngeal and retrovisceral spaces. Once established, mediastinitis is rapidly followed by sepsis and death. If DNM is suspected cervical and thoracic CT must be carried out urgently. After this, prompt control of the upper airway with tracheostomy, aggressive surgical debridement of the deep cervical spaces and mediastinum, and intravenous broad spectrum antibiotic therapy are mandatory. The present paper reports two new cases of DNM following dental extraction, and focuses on radiological features of abscess progression through the cervical spaces down into the mediastinum. 2010 European Association for Cranio-Maxillo-Facial Surgery. Published by Elsevier Ltd. All rights reserved.

Development of feature extraction analysis for a multi-functional optical profiling device applied to field engineering applications

Science.gov (United States)

Han, Xu; Xie, Guangping; Laflen, Brandon; Jia, Ming; Song, Guiju; Harding, Kevin G.

2015-05-01

In the real application environment of field engineering, a large variety of metrology tools are required by the technician to inspect part profile features. However, some of these tools are burdensome and only address a sole application or measurement. In other cases, standard tools lack the capability of accessing irregular profile features. Customers of field engineering want the next generation metrology devices to have the ability to replace the many current tools with one single device. This paper will describe a method based on the ring optical gage concept to the measurement of numerous kinds of profile features useful for the field technician. The ring optical system is composed of a collimated laser, a conical mirror and a CCD camera. To be useful for a wide range of applications, the ring optical system requires profile feature extraction algorithms and data manipulation directed toward real world applications in field operation. The paper will discuss such practical applications as measuring the non-ideal round hole with both off-centered and oblique axes. The algorithms needed to analyze other features such as measuring the width of gaps, radius of transition fillets, fall of step surfaces, and surface parallelism will also be discussed in this paper. With the assistance of image processing and geometric algorithms, these features can be extracted with a reasonable performance. Tailoring the feature extraction analysis to this specific gage offers the potential for a wider application base beyond simple inner diameter measurements. The paper will present experimental results that are compared with standard gages to prove the performance and feasibility of the analysis in real world field engineering. Potential accuracy improvement methods, a new dual ring design and future work will be discussed at the end of this paper.

Assessment of global and local region-based bilateral mammographic feature asymmetry to predict short-term breast cancer risk

Science.gov (United States)

Li, Yane; Fan, Ming; Cheng, Hu; Zhang, Peng; Zheng, Bin; Li, Lihua

2018-01-01

This study aims to develop and test a new imaging marker-based short-term breast cancer risk prediction model. An age-matched dataset of 566 screening mammography cases was used. All ‘prior’ images acquired in the two screening series were negative, while in the ‘current’ screening images, 283 cases were positive for cancer and 283 cases remained negative. For each case, two bilateral cranio-caudal view mammograms acquired from the ‘prior’ negative screenings were selected and processed by a computer-aided image processing scheme, which segmented the entire breast area into nine strip-based local regions, extracted the element regions using difference of Gaussian filters, and computed both global- and local-based bilateral asymmetrical image features. An initial feature pool included 190 features related to the spatial distribution and structural similarity of grayscale values, as well as of the magnitude and phase responses of multidirectional Gabor filters. Next, a short-term breast cancer risk prediction model based on a generalized linear model was built using an embedded stepwise regression analysis method to select features and a leave-one-case-out cross-validation method to predict the likelihood of each woman having image-detectable cancer in the next sequential mammography screening. The area under the receiver operating characteristic curve (AUC) values significantly increased from 0.5863  ±  0.0237 to 0.6870  ±  0.0220 when the model trained by the image features extracted from the global regions and by the features extracted from both the global and the matched local regions (p  =  0.0001). The odds ratio values monotonically increased from 1.00-8.11 with a significantly increasing trend in slope (p  =  0.0028) as the model-generated risk score increased. In addition, the AUC values were 0.6555  ±  0.0437, 0.6958  ±  0.0290, and 0.7054  ±  0.0529 for the three age groups of 37

Efficient ConvNet Feature Extraction with Multiple RoI Pooling for Landmark-Based Visual Localization of Autonomous Vehicles

Directory of Open Access Journals (Sweden)

Yi Hou

2017-01-01

Full Text Available Efficient and robust visual localization is important for autonomous vehicles. By achieving impressive localization accuracy under conditions of significant changes, ConvNet landmark-based approach has attracted the attention of people in several research communities including autonomous vehicles. Such an approach relies heavily on the outstanding discrimination power of ConvNet features to match detected landmarks between images. However, a major challenge of this approach is how to extract discriminative ConvNet features efficiently. To address this challenging, inspired by the high efficiency of the region of interest (RoI pooling layer, we propose a Multiple RoI (MRoI pooling technique, an enhancement of RoI, and a simple yet efficient ConvNet feature extraction method. Our idea is to leverage MRoI pooling to exploit multilevel and multiresolution information from multiple convolutional layers and then fuse them to improve the discrimination capacity of the final ConvNet features. The main advantages of our method are (a high computational efficiency for real-time applications; (b GPU memory efficiency for mobile applications; and (c use of pretrained model without fine-tuning or retraining for easy implementation. Experimental results on four datasets have demonstrated not only the above advantages but also the high discriminating power of the extracted ConvNet features with state-of-the-art localization accuracy.

Urban Area Extent Extraction in Spaceborne HR and VHR Data Using Multi-Resolution Features

Directory of Open Access Journals (Sweden)

Gianni Cristian Iannelli

2014-09-01

Full Text Available Detection of urban area extents by means of remotely sensed data is a difficult task, especially because of the multiple, diverse definitions of what an “urban area” is. The models of urban areas listed in technical literature are based on the combination of spectral information with spatial patterns, possibly at different spatial resolutions. Starting from the same data set, “urban area” extraction may thus lead to multiple outputs. If this is done in a well-structured framework, however, this may be considered as an advantage rather than an issue. This paper proposes a novel framework for urban area extent extraction from multispectral Earth Observation (EO data. The key is to compute and combine spectral and multi-scale spatial features. By selecting the most adequate features, and combining them with proper logical rules, the approach allows matching multiple urban area models. Experimental results for different locations in Brazil and Kenya using High-Resolution (HR data prove the usefulness and flexibility of the framework.

Autonomous celestial navigation based on Earth ultraviolet radiance and fast gradient statistic feature extraction

Science.gov (United States)

Lu, Shan; Zhang, Hanmo

2016-01-01

To meet the requirement of autonomous orbit determination, this paper proposes a fast curve fitting method based on earth ultraviolet features to obtain accurate earth vector direction, in order to achieve the high precision autonomous navigation. Firstly, combining the stable characters of earth ultraviolet radiance and the use of transmission model software of atmospheric radiation, the paper simulates earth ultraviolet radiation model on different time and chooses the proper observation band. Then the fast improved edge extracting method combined Sobel operator and local binary pattern (LBP) is utilized, which can both eliminate noises efficiently and extract earth ultraviolet limb features accurately. And earth's centroid locations on simulated images are estimated via the least square fitting method using part of the limb edges. Taken advantage of the estimated earth vector direction and earth distance, Extended Kalman Filter (EKF) is applied to realize the autonomous navigation finally. Experiment results indicate the proposed method can achieve a sub-pixel earth centroid location estimation and extremely enhance autonomous celestial navigation precision.

Multivariate matching pursuit in optimal Gabor dictionaries: theory and software with interface for EEG/MEG via Svarog

Science.gov (United States)

2013-01-01

Background Matching pursuit algorithm (MP), especially with recent multivariate extensions, offers unique advantages in analysis of EEG and MEG. Methods We propose a novel construction of an optimal Gabor dictionary, based upon the metrics introduced in this paper. We implement this construction in a freely available software for MP decomposition of multivariate time series, with a user friendly interface via the Svarog package (Signal Viewer, Analyzer and Recorder On GPL, http://braintech.pl/svarog), and provide a hands-on introduction to its application to EEG. Finally, we describe numerical and mathematical optimizations used in this implementation. Results Optimal Gabor dictionaries, based on the metric introduced in this paper, for the first time allowed for a priori assessment of maximum one-step error of the MP algorithm. Variants of multivariate MP, implemented in the accompanying software, are organized according to the mathematical properties of the algorithms, relevant in the light of EEG/MEG analysis. Some of these variants have been successfully applied to both multichannel and multitrial EEG and MEG in previous studies, improving preprocessing for EEG/MEG inverse solutions and parameterization of evoked potentials in single trials; we mention also ongoing work and possible novel applications. Conclusions Mathematical results presented in this paper improve our understanding of the basics of the MP algorithm. Simple introduction of its properties and advantages, together with the accompanying stable and user-friendly Open Source software package, pave the way for a widespread and reproducible analysis of multivariate EEG and MEG time series and novel applications, while retaining a high degree of compatibility with the traditional, visual analysis of EEG. PMID:24059247

A Biologically Inspired Approach to Frequency Domain Feature Extraction for EEG Classification

Directory of Open Access Journals (Sweden)

Nurhan Gursel Ozmen

2018-01-01

Full Text Available Classification of electroencephalogram (EEG signal is important in mental decoding for brain-computer interfaces (BCI. We introduced a feature extraction approach based on frequency domain analysis to improve the classification performance on different mental tasks using single-channel EEG. This biologically inspired method extracts the most discriminative spectral features from power spectral densities (PSDs of the EEG signals. We applied our method on a dataset of six subjects who performed five different imagination tasks: (i resting state, (ii mental arithmetic, (iii imagination of left hand movement, (iv imagination of right hand movement, and (v imagination of letter “A.” Pairwise and multiclass classifications were performed in single EEG channel using Linear Discriminant Analysis and Support Vector Machines. Our method produced results (mean classification accuracy of 83.06% for binary classification and 91.85% for multiclassification that are on par with the state-of-the-art methods, using single-channel EEG with low computational cost. Among all task pairs, mental arithmetic versus letter imagination yielded the best result (mean classification accuracy of 90.29%, indicating that this task pair could be the most suitable pair for a binary class BCI. This study contributes to the development of single-channel BCI, as well as finding the best task pair for user defined applications.

High Resolution SAR Imaging Employing Geometric Features for Extracting Seismic Damage of Buildings

Science.gov (United States)

Cui, L. P.; Wang, X. P.; Dou, A. X.; Ding, X.

2018-04-01

Synthetic Aperture Radar (SAR) image is relatively easy to acquire but difficult for interpretation. This paper probes how to identify seismic damage of building using geometric features of SAR. The SAR imaging geometric features of buildings, such as the high intensity layover, bright line induced by double bounce backscattering and dark shadow is analysed, and show obvious differences texture features of homogeneity, similarity and entropy in combinatorial imaging geometric regions between the un-collapsed and collapsed buildings in airborne SAR images acquired in Yushu city damaged by 2010 Ms7.1 Yushu, Qinghai, China earthquake, which implicates a potential capability to discriminate collapsed and un-collapsed buildings from SAR image. Study also shows that the proportion of highlight (layover & bright line) area (HA) is related to the seismic damage degree, thus a SAR image damage index (SARDI), which related to the ratio of HA to the building occupation are of building in a street block (SA), is proposed. While HA is identified through feature extraction with high-pass and low-pass filtering of SAR image in frequency domain. A partial region with 58 natural street blocks in the Yushu City are selected as study area. Then according to the above method, HA is extracted, SARDI is then calculated and further classified into 3 classes. The results show effective through validation check with seismic damage classes interpreted artificially from post-earthquake airborne high resolution optical image, which shows total classification accuracy 89.3 %, Kappa coefficient 0.79 and identical to the practical seismic damage distribution. The results are also compared and discussed with the building damage identified from SAR image available by other authors.

Automated Solar Flare Detection and Feature Extraction in High-Resolution and Full-Disk Hα Images

Science.gov (United States)

Yang, Meng; Tian, Yu; Liu, Yangyi; Rao, Changhui

2018-05-01

In this article, an automated solar flare detection method applied to both full-disk and local high-resolution Hα images is proposed. An adaptive gray threshold and an area threshold are used to segment the flare region. Features of each detected flare event are extracted, e.g. the start, peak, and end time, the importance class, and the brightness class. Experimental results have verified that the proposed method can obtain more stable and accurate segmentation results than previous works on full-disk images from Big Bear Solar Observatory (BBSO) and Kanzelhöhe Observatory for Solar and Environmental Research (KSO), and satisfying segmentation results on high-resolution images from the Goode Solar Telescope (GST). Moreover, the extracted flare features correlate well with the data given by KSO. The method may be able to implement a more complicated statistical analysis of Hα solar flares.

Integrating angle-frequency domain synchronous averaging technique with feature extraction for gear fault diagnosis

Science.gov (United States)

Zhang, Shengli; Tang, J.

2018-01-01

Gear fault diagnosis relies heavily on the scrutiny of vibration responses measured. In reality, gear vibration signals are noisy and dominated by meshing frequencies as well as their harmonics, which oftentimes overlay the fault related components. Moreover, many gear transmission systems, e.g., those in wind turbines, constantly operate under non-stationary conditions. To reduce the influences of non-synchronous components and noise, a fault signature enhancement method that is built upon angle-frequency domain synchronous averaging is developed in this paper. Instead of being averaged in the time domain, the signals are processed in the angle-frequency domain to solve the issue of phase shifts between signal segments due to uncertainties caused by clearances, input disturbances, and sampling errors, etc. The enhanced results are then analyzed through feature extraction algorithms to identify the most distinct features for fault classification and identification. Specifically, Kernel Principal Component Analysis (KPCA) targeting at nonlinearity, Multilinear Principal Component Analysis (MPCA) targeting at high dimensionality, and Locally Linear Embedding (LLE) targeting at local similarity among the enhanced data are employed and compared to yield insights. Numerical and experimental investigations are performed, and the results reveal the effectiveness of angle-frequency domain synchronous averaging in enabling feature extraction and classification.

Coding Local and Global Binary Visual Features Extracted From Video Sequences

Science.gov (United States)

Baroffio, Luca; Canclini, Antonio; Cesana, Matteo; Redondi, Alessandro; Tagliasacchi, Marco; Tubaro, Stefano

2015-11-01

Binary local features represent an effective alternative to real-valued descriptors, leading to comparable results for many visual analysis tasks, while being characterized by significantly lower computational complexity and memory requirements. When dealing with large collections, a more compact representation based on global features is often preferred, which can be obtained from local features by means of, e.g., the Bag-of-Visual-Word (BoVW) model. Several applications, including for example visual sensor networks and mobile augmented reality, require visual features to be transmitted over a bandwidth-limited network, thus calling for coding techniques that aim at reducing the required bit budget, while attaining a target level of efficiency. In this paper we investigate a coding scheme tailored to both local and global binary features, which aims at exploiting both spatial and temporal redundancy by means of intra- and inter-frame coding. In this respect, the proposed coding scheme can be conveniently adopted to support the Analyze-Then-Compress (ATC) paradigm. That is, visual features are extracted from the acquired content, encoded at remote nodes, and finally transmitted to a central controller that performs visual analysis. This is in contrast with the traditional approach, in which visual content is acquired at a node, compressed and then sent to a central unit for further processing, according to the Compress-Then-Analyze (CTA) paradigm. In this paper we experimentally compare ATC and CTA by means of rate-efficiency curves in the context of two different visual analysis tasks: homography estimation and content-based retrieval. Our results show that the novel ATC paradigm based on the proposed coding primitives can be competitive with CTA, especially in bandwidth limited scenarios.

Regularized generalized eigen-decomposition with applications to sparse supervised feature extraction and sparse discriminant analysis

DEFF Research Database (Denmark)

Han, Xixuan; Clemmensen, Line Katrine Harder

2015-01-01

We propose a general technique for obtaining sparse solutions to generalized eigenvalue problems, and call it Regularized Generalized Eigen-Decomposition (RGED). For decades, Fisher's discriminant criterion has been applied in supervised feature extraction and discriminant analysis, and it is for...

LiDAR DTMs and anthropogenic feature extraction: testing the feasibility of geomorphometric parameters in floodplains

Science.gov (United States)

Sofia, G.; Tarolli, P.; Dalla Fontana, G.

2012-04-01

resolution topography have been proven to be reliable for feasible applications. The use of statistical operators as thresholds for these geomorphic parameters, furthermore, showed a high reliability for feature extraction in mountainous environments. The goal of this research is to test if these morphological indicators and objective thresholds can be feasible also in floodplains, where features assume different characteristics and other artificial disturbances might be present. In the work, three different geomorphic parameters are tested and applied at different scales on a LiDAR DTM of typical alluvial plain's area in the North East of Italy. The box-plot is applied to identify the threshold for feature extraction, and a filtering procedure is proposed, to improve the quality of the final results. The effectiveness of the different geomorphic parameters is analyzed, comparing automatically derived features with the surveyed ones. The results highlight the capability of high resolution topography, geomorphic indicators and statistical thresholds for anthropogenic features extraction and characterization in a floodplains context.

Fatigue Feature Extraction Analysis based on a K-Means Clustering Approach

Directory of Open Access Journals (Sweden)

M.F.M. Yunoh

2015-06-01

Full Text Available This paper focuses on clustering analysis using a K-means approach for fatigue feature dataset extraction. The aim of this study is to group the dataset as closely as possible (homogeneity for the scattered dataset. Kurtosis, the wavelet-based energy coefficient and fatigue damage are calculated for all segments after the extraction process using wavelet transform. Kurtosis, the wavelet-based energy coefficient and fatigue damage are used as input data for the K-means clustering approach. K-means clustering calculates the average distance of each group from the centroid and gives the objective function values. Based on the results, maximum values of the objective function can be seen in the two centroid clusters, with a value of 11.58. The minimum objective function value is found at 8.06 for five centroid clusters. It can be seen that the objective function with the lowest value for the number of clusters is equal to five; which is therefore the best cluster for the dataset.

An Improved AAM Method for Extracting Human Facial Features

Directory of Open Access Journals (Sweden)

Tao Zhou

2012-01-01

Full Text Available Active appearance model is a statistically parametrical model, which is widely used to extract human facial features and recognition. However, intensity values used in original AAM cannot provide enough information for image texture, which will lead to a larger error or a failure fitting of AAM. In order to overcome these defects and improve the fitting performance of AAM model, an improved texture representation is proposed in this paper. Firstly, translation invariant wavelet transform is performed on face images and then image structure is represented using the measure which is obtained by fusing the low-frequency coefficients with edge intensity. Experimental results show that the improved algorithm can increase the accuracy of the AAM fitting and express more information for structures of edge and texture.

PCA Fault Feature Extraction in Complex Electric Power Systems

Directory of Open Access Journals (Sweden)

ZHANG, J.

2010-08-01

Full Text Available Electric power system is one of the most complex artificial systems in the world. The complexity is determined by its characteristics about constitution, configuration, operation, organization, etc. The fault in electric power system cannot be completely avoided. When electric power system operates from normal state to failure or abnormal, its electric quantities (current, voltage and angles, etc. may change significantly. Our researches indicate that the variable with the biggest coefficient in principal component usually corresponds to the fault. Therefore, utilizing real-time measurements of phasor measurement unit, based on principal components analysis technology, we have extracted successfully the distinct features of fault component. Of course, because of the complexity of different types of faults in electric power system, there still exists enormous problems need a close and intensive study.

THE MORPHOLOGICAL PYRAMID AND ITS APPLICATIONS TO REMOTE SENSING: MULTIRESOLUTION DATA ANALYSIS AND FEATURES EXTRACTION

Directory of Open Access Journals (Sweden)

Laporterie Florence

2011-05-01

Full Text Available In remote sensing, sensors are more and more numerous, and their spatial resolution is higher and higher. Thus, the availability of a quick and accurate characterisation of the increasing amount of data is now a quite important issue. This paper deals with an approach combining a pyramidal algorithm and mathematical morphology to study the physiographic characteristics of terrestrial ecosystems. Our pyramidal strategy involves first morphological filters, then extraction at each level of resolution of well-known landscapes features. The approach is applied to a digitised aerial photograph representing an heterogeneous landscape of orchards and forests along the Garonne river (France. This example, simulating very high spatial resolution imagery, highlights the influence of the parameters of the pyramid according to the spatial properties of the studied patterns. It is shown that, the morphological pyramid approach is a promising attempt for multi-level features extraction by modelling geometrical relevant parameters.

Solid waste bin detection and classification using Dynamic Time Warping and MLP classifier

Energy Technology Data Exchange (ETDEWEB)

Islam, Md. Shafiqul, E-mail: shafique@eng.ukm.my [Dept. of Electrical, Electronic and Systems Engineering, Universiti Kebangsaan Malaysia, Bangi 43600, Selangore (Malaysia); Hannan, M.A., E-mail: hannan@eng.ukm.my [Dept. of Electrical, Electronic and Systems Engineering, Universiti Kebangsaan Malaysia, Bangi 43600, Selangore (Malaysia); Basri, Hassan [Dept. of Civil and Structural Engineering, Universiti Kebangsaan Malaysia, Bangi 43600, Selangore (Malaysia); Hussain, Aini; Arebey, Maher [Dept. of Electrical, Electronic and Systems Engineering, Universiti Kebangsaan Malaysia, Bangi 43600, Selangore (Malaysia)

2014-02-15

Highlights: • Solid waste bin level detection using Dynamic Time Warping (DTW). • Gabor wavelet filter is used to extract the solid waste image features. • Multi-Layer Perceptron classifier network is used for bin image classification. • The classification performance evaluated by ROC curve analysis. - Abstract: The increasing requirement for Solid Waste Management (SWM) has become a significant challenge for municipal authorities. A number of integrated systems and methods have introduced to overcome this challenge. Many researchers have aimed to develop an ideal SWM system, including approaches involving software-based routing, Geographic Information Systems (GIS), Radio-frequency Identification (RFID), or sensor intelligent bins. Image processing solutions for the Solid Waste (SW) collection have also been developed; however, during capturing the bin image, it is challenging to position the camera for getting a bin area centralized image. As yet, there is no ideal system which can correctly estimate the amount of SW. This paper briefly discusses an efficient image processing solution to overcome these problems. Dynamic Time Warping (DTW) was used for detecting and cropping the bin area and Gabor wavelet (GW) was introduced for feature extraction of the waste bin image. Image features were used to train the classifier. A Multi-Layer Perceptron (MLP) classifier was used to classify the waste bin level and estimate the amount of waste inside the bin. The area under the Receiver Operating Characteristic (ROC) curves was used to statistically evaluate classifier performance. The results of this developed system are comparable to previous image processing based system. The system demonstration using DTW with GW for feature extraction and an MLP classifier led to promising results with respect to the accuracy of waste level estimation (98.50%). The application can be used to optimize the routing of waste collection based on the estimated bin level.

A New Feature Extraction Method Based on EEMD and Multi-Scale Fuzzy Entropy for Motor Bearing

Directory of Open Access Journals (Sweden)

Huimin Zhao

2016-12-01

Full Text Available Feature extraction is one of the most important, pivotal, and difficult problems in mechanical fault diagnosis, which directly relates to the accuracy of fault diagnosis and the reliability of early fault prediction. Therefore, a new fault feature extraction method, called the EDOMFE method based on integrating ensemble empirical mode decomposition (EEMD, mode selection, and multi-scale fuzzy entropy is proposed to accurately diagnose fault in this paper. The EEMD method is used to decompose the vibration signal into a series of intrinsic mode functions (IMFs with a different physical significance. The correlation coefficient analysis method is used to calculate and determine three improved IMFs, which are close to the original signal. The multi-scale fuzzy entropy with the ability of effective distinguishing the complexity of different signals is used to calculate the entropy values of the selected three IMFs in order to form a feature vector with the complexity measure, which is regarded as the inputs of the support vector machine (SVM model for training and constructing a SVM classifier (EOMSMFD based on EDOMFE and SVM for fulfilling fault pattern recognition. Finally, the effectiveness of the proposed method is validated by real bearing vibration signals of the motor with different loads and fault severities. The experiment results show that the proposed EDOMFE method can effectively extract fault features from the vibration signal and that the proposed EOMSMFD method can accurately diagnose the fault types and fault severities for the inner race fault, the outer race fault, and rolling element fault of the motor bearing. Therefore, the proposed method provides a new fault diagnosis technology for rotating machinery.

Fault feature extraction of planet gear in wind turbine gearbox based on spectral kurtosis and time wavelet energy spectrum

Science.gov (United States)

Kong, Yun; Wang, Tianyang; Li, Zheng; Chu, Fulei

2017-09-01

Planetary transmission plays a vital role in wind turbine drivetrains, and its fault diagnosis has been an important and challenging issue. Owing to the complicated and coupled vibration source, time-variant vibration transfer path, and heavy background noise masking effect, the vibration signal of planet gear in wind turbine gearboxes exhibits several unique characteristics: Complex frequency components, low signal-to-noise ratio, and weak fault feature. In this sense, the periodic impulsive components induced by a localized defect are hard to extract, and the fault detection of planet gear in wind turbines remains to be a challenging research work. Aiming to extract the fault feature of planet gear effectively, we propose a novel feature extraction method based on spectral kurtosis and time wavelet energy spectrum (SK-TWES) in the paper. Firstly, the spectral kurtosis (SK) and kurtogram of raw vibration signals are computed and exploited to select the optimal filtering parameter for the subsequent band-pass filtering. Then, the band-pass filtering is applied to extrude periodic transient impulses using the optimal frequency band in which the corresponding SK value is maximal. Finally, the time wavelet energy spectrum analysis is performed on the filtered signal, selecting Morlet wavelet as the mother wavelet which possesses a high similarity to the impulsive components. The experimental signals collected from the wind turbine gearbox test rig demonstrate that the proposed method is effective at the feature extraction and fault diagnosis for the planet gear with a localized defect.

Coding Local and Global Binary Visual Features Extracted From Video Sequences.

Science.gov (United States)

Baroffio, Luca; Canclini, Antonio; Cesana, Matteo; Redondi, Alessandro; Tagliasacchi, Marco; Tubaro, Stefano

2015-11-01

Binary local features represent an effective alternative to real-valued descriptors, leading to comparable results for many visual analysis tasks while being characterized by significantly lower computational complexity and memory requirements. When dealing with large collections, a more compact representation based on global features is often preferred, which can be obtained from local features by means of, e.g., the bag-of-visual word model. Several applications, including, for example, visual sensor networks and mobile augmented reality, require visual features to be transmitted over a bandwidth-limited network, thus calling for coding techniques that aim at reducing the required bit budget while attaining a target level of efficiency. In this paper, we investigate a coding scheme tailored to both local and global binary features, which aims at exploiting both spatial and temporal redundancy by means of intra- and inter-frame coding. In this respect, the proposed coding scheme can conveniently be adopted to support the analyze-then-compress (ATC) paradigm. That is, visual features are extracted from the acquired content, encoded at remote nodes, and finally transmitted to a central controller that performs the visual analysis. This is in contrast with the traditional approach, in which visual content is acquired at a node, compressed and then sent to a central unit for further processing, according to the compress-then-analyze (CTA) paradigm. In this paper, we experimentally compare the ATC and the CTA by means of rate-efficiency curves in the context of two different visual analysis tasks: 1) homography estimation and 2) content-based retrieval. Our results show that the novel ATC paradigm based on the proposed coding primitives can be competitive with the CTA, especially in bandwidth limited scenarios.

Reconocimiento de valvulopatías cardíacas en señales de fonocardiografía empleando la transformada Gabor

OpenAIRE

Echeverry Correa, Julián David; López, Andrés Felipe; López, Juan Fernando

2007-01-01

Se presenta en este trabajo una metodología de caracterización basada en la representación tiempo frecuencia de las señales fonocardiográficas con el fin de hacer reconocimiento de valvulopatías cardíacas. La naturaleza de estas patologías las hace susceptibles a ser caracterizadas por medio de representaciones en el espacio conjunto tiempo-frecuencia. Se emplea la transformada de Gabor para llevar los registros a este tipo bidimensional de representación. Los porcentajes de clasificación, me...

Pigmented skin lesion detection using random forest and wavelet-based texture

Science.gov (United States)

Hu, Ping; Yang, Tie-jun

2016-10-01

The incidence of cutaneous malignant melanoma, a disease of worldwide distribution and is the deadliest form of skin cancer, has been rapidly increasing over the last few decades. Because advanced cutaneous melanoma is still incurable, early detection is an important step toward a reduction in mortality. Dermoscopy photographs are commonly used in melanoma diagnosis and can capture detailed features of a lesion. A great variability exists in the visual appearance of pigmented skin lesions. Therefore, in order to minimize the diagnostic errors that result from the difficulty and subjectivity of visual interpretation, an automatic detection approach is required. The objectives of this paper were to propose a hybrid method using random forest and Gabor wavelet transformation to accurately differentiate which part belong to lesion area and the other is not in a dermoscopy photographs and analyze segmentation accuracy. A random forest classifier consisting of a set of decision trees was used for classification. Gabor wavelets transformation are the mathematical model of visual cortical cells of mammalian brain and an image can be decomposed into multiple scales and multiple orientations by using it. The Gabor function has been recognized as a very useful tool in texture analysis, due to its optimal localization properties in both spatial and frequency domain. Texture features based on Gabor wavelets transformation are found by the Gabor filtered image. Experiment results indicate the following: (1) the proposed algorithm based on random forest outperformed the-state-of-the-art in pigmented skin lesions detection (2) and the inclusion of Gabor wavelet transformation based texture features improved segmentation accuracy significantly.

Learning object location predictors with boosting and grammar-guided feature extraction

Energy Technology Data Exchange (ETDEWEB)

Eads, Damian Ryan [Los Alamos National Laboratory; Rosten, Edward [UNIV OF CAMBRIDGE; Helmbold, David [UC/SANTA CRUZ

2009-01-01

The authors present BEAMER: a new spatially exploitative approach to learning object detectors which shows excellent results when applied to the task of detecting objects in greyscale aerial imagery in the presence of ambiguous and noisy data. There are four main contributions used to produce these results. First, they introduce a grammar-guided feature extraction system, enabling the exploration of a richer feature space while constraining the features to a useful subset. This is specified with a rule-based generative grammer crafted by a human expert. Second, they learn a classifier on this data using a newly proposed variant of AdaBoost which takes into account the spatially correlated nature of the data. Third, they perform another round of training to optimize the method of converting the pixel classifications generated by boosting into a high quality set of (x,y) locations. lastly, they carefully define three common problems in object detection and define two evaluation criteria that are tightly matched to these problems. Major strengths of this approach are: (1) a way of randomly searching a broad feature space, (2) its performance when evaluated on well-matched evaluation criteria, and (3) its use of the location prediction domain to learn object detectors as well as to generate detections that perform well on several tasks: object counting, tracking, and target detection. They demonstrate the efficacy of BEAMER with a comprehensive experimental evaluation on a challenging data set.