arXiv subjects

Debotosh Bhattacharjee

Publications and source records attributed to Debotosh Bhattacharjee.

At least 37 records · Page 2Linked to original sources

arXiv2013

A Gabor block based Kernel Discriminative Common Vector (KDCV) approach using cosine kernels for Human Face Recognition

In this paper a nonlinear Gabor Wavelet Transform (GWT) discriminant feature extraction approach for enhanced face recognition is proposed. Firstly, the low-energized blocks from Gabor wavelet transformed images are extracted. Secondly, the nonlinear discriminating features are analyzed and extracted from the selected low-energized blocks by the generalized Kernel Discriminative Common Vector (KDCV) method. The KDCV method is extended to include cosine kernel function in the discriminating method. The KDCV with the cosine kernels is then applied on the extracted low energized discriminating feature vectors to obtain the real component of a complex quantity for face recognition. In order to derive positive kernel discriminative vectors; we apply only those kernel discriminative eigenvectors that are associated with non-zero eigenvalues. The feasibility of the low energized Gabor block based generalized KDCV method with cosine kernel function models has been successfully tested for image classification using the L1, L2 distance measures; and the cosine similarity measure on both frontal and pose-angled face recognition. Experimental results on the FRAV2D and the FERET database demonstrate the effectiveness of this new approach.

cs.CV↗

arXiv2013

Face Recognition using Hough Peaks extracted from the significant blocks of the Gradient Image

This paper proposes a new technique for automatic face recognition using integrated peaks of the Hough transformed significant blocks of the binary gradient image. In this approach firstly the gradient of an image is calculated and a threshold is set to obtain a binary gradient image, which is less sensitive to noise and illumination changes. Secondly, significant blocks are extracted from the absolute gradient image, to extract pertinent information with the idea of dimension reduction. Finally the best fitted Hough peaks are extracted from the Hough transformed significant blocks for efficient face recognition. Then these Hough peaks are concatenated together, which are used as feature in classification process. The efficiency of the proposed method is demonstrated by the experiment on 1100 images from the FRAV2D face database, 2200 images from the FERET database, where the images vary in pose, expression, illumination and scale and 400 images from the ORL face database, where the images slightly vary in pose. Our method has shown 93.3%, 88.5% and 99% recognition accuracy for the FRAV2D, FERET and the ORL database respectively.

cs.CV↗

arXiv2013

High Performance Human Face Recognition using Gabor based Pseudo Hidden Markov Model

This paper introduces a novel methodology that combines the multi-resolution feature of the Gabor wavelet transformation (GWT) with the local interactions of the facial structures expressed through the Pseudo Hidden Markov model (PHMM). Unlike the traditional zigzag scanning method for feature extraction a continuous scanning method from top-left corner to right then top-down and right to left and so on until right-bottom of the image i.e. a spiral scanning technique has been proposed for better feature selection. Unlike traditional HMMs, the proposed PHMM does not perform the state conditional independence of the visible observation sequence assumption. This is achieved via the concept of local structures introduced by the PHMM used to extract facial bands and automatically select the most informative features of a face image. Thus, the long-range dependency problem inherent to traditional HMMs has been drastically reduced. Again with the use of most informative pixels rather than the whole image makes the proposed method reasonably faster for face recognition. This method has been successfully tested on frontal face images from the ORL, FRAV2D and FERET face databases where the images vary in pose, illumination, expression, and scale. The FERET data set contains 2200 frontal face images of 200 subjects, while the FRAV2D data set consists of 1100 images of 100 subjects and the full ORL database is considered. The results reported in this application are far better than the recent and most referred systems.

cs.CV↗

arXiv2013

Human Face Recognition using Gabor based Kernel Entropy Component Analysis

In this paper, we present a novel Gabor wavelet based Kernel Entropy Component Analysis (KECA) method by integrating the Gabor wavelet transformation (GWT) of facial images with the KECA method for enhanced face recognition performance. Firstly, from the Gabor wavelet transformed images the most important discriminative desirable facial features characterized by spatial frequency, spatial locality and orientation selectivity to cope with the variations due to illumination and facial expression changes were derived. After that KECA, relating to the Renyi entropy is extended to include cosine kernel function. The KECA with the cosine kernels is then applied on the extracted most important discriminating feature vectors of facial images to obtain only those real kernel ECA eigenvectors that are associated with eigenvalues having positive entropy contribution. Finally, these real KECA features are used for image classification using the L1, L2 distance measures; the Mahalanobis distance measure and the cosine similarity measure. The feasibility of the Gabor based KECA method with the cosine kernel has been successfully tested on both frontal and pose-angled face recognition, using datasets from the ORL, FRAV2D and the FERET database.

cs.CV↗

arXiv2013

A Face Recognition approach based on entropy estimate of the nonlinear DCT features in the Logarithm Domain together with Kernel Entropy Component Analysis

This paper exploits the feature extraction capabilities of the discrete cosine transform (DCT) together with an illumination normalization approach in the logarithm domain that increase its robustness to variations in facial geometry and illumination. Secondly in the same domain the entropy measures are applied on the DCT coefficients so that maximum entropy preserving pixels can be extracted as the feature vector. Thus the informative features of a face can be extracted in a low dimensional space. Finally, the kernel entropy component analysis (KECA) with an extension of arc cosine kernels is applied on the extracted DCT coefficients that contribute most to the entropy estimate to obtain only those real kernel ECA eigenvectors that are associated with eigenvalues having high positive entropy contribution. The resulting system was successfully tested on real image sequences and is robust to significant partial occlusion and illumination changes, validated with the experiments on the FERET, AR, FRAV2D and ORL face databases. Experimental comparison is demonstrated to prove the superiority of the proposed approach in respect to recognition accuracy. Using specificity and sensitivity we find that the best is achieved when Renyi entropy is applied on the DCT coefficients. Extensive experimental comparison is demonstrated to prove the superiority of the proposed approach in respect to recognition accuracy. Moreover, the proposed approach is very simple, computationally fast and can be implemented in any real-time face recognition system.

cs.CV↗

arXiv2013

Medical Aid for Automatic Detection of Malaria

The analysis and counting of blood cells in a microscope image can provide useful information concerning to the health of a person. In particular, morphological analysis of red blood cells deformations can effectively detect important disease like malaria. Blood images, obtained by the microscope, which is coupled with a digital camera, are analyzed by the computer for diagnosis or can be transmitted easily to clinical centers than liquid blood samples. Automatic analysis system for the presence of Plasmodium in microscopic image of blood can greatly help pathologists and doctors that typically inspect blood films manually. Unfortunately, the analysis made by human experts is not rapid and not yet standardized due to the operators capabilities and tiredness. The paper shows how effectively and accurately it is possible to identify the Plasmodium in the blood film. In particular, the paper presents how to enhance the microscopic image and filter out the unnecessary segments followed by the threshold based segmentation and recognize the presence of Plasmodium. The proposed system can be deployed in the remote area as a supporting aid for telemedicine technology and only basic training is sufficient to operate it. This system achieved more than 98 percentage accuracy for the samples collected to test this system.

cs.CY↗

arXiv2013

Automatic White Blood Cell Measuring Aid for Medical Diagnosis

Blood related invasive pathological investigations play a major role in diagnosis of diseases. But in India and other third world countries there are no enough pathological infrastructures for medical diagnosis. Moreover, most of the remote places of those countries have neither pathologists nor physicians. Telemedicine partially solves the lack of physicians. But the pathological investigation infrastructure can not be integrated with the telemedicine technology. The objective of this work is to automate the blood related pathological investigation process. Detection of different white blood cells has been automated in this work. This system can be deployed in the remote area as a supporting aid for telemedicine technology and only high school education is sufficient to operate it. The proposed system achieved 97.33 percent accuracy for the samples collected to test this system.

cs.CY↗

arXiv2013

A novel approach for nose tip detection using smoothing by weighted median filtering applied to 3D face images in variant poses

This paper is based on an application of smoothing of 3D face images followed by feature detection i.e. detecting the nose tip. The present method uses a weighted mesh median filtering technique for smoothing. In this present smoothing technique we have built the neighborhood surrounding a particular point in 3D face and replaced that with the weighted value of the surrounding points in 3D face image. After applying the smoothing technique to the 3D face images our experimental results show that we have obtained considerable improvement as compared to the algorithm without smoothing. We have used here the maximum intensity algorithm for detecting the nose-tip and this method correctly detects the nose-tip in case of any pose i.e. along X, Y, and Z axes. The present technique gave us worked successfully on 535 out of 542 3D face images as compared to the method without smoothing which worked only on 521 3D face images out of 542 face images. Thus we have obtained a 98.70% performance rate over 96.12% performance rate of the algorithm without smoothing. All the experiments have been performed on the FRAV3D database.

cs.CV↗

arXiv2013

Detection of pose orientation across single and multiple axes in case of 3D face images

In this paper, we propose a new approach that takes as input a 3D face image across X, Y and Z axes as well as both Y and X axes and gives output as its pose i.e. it tells whether the face is oriented with respect the X, Y or Z axes or is it oriented across multiple axes with angles of rotation up to 42 degree. All the experiments have been performed on the FRAV3D, GAVADB and Bosphorus database which has two figures of each individual across multiple axes. After applying the proposed algorithm to the 3D facial surface from FRAV3D on 848 3D faces, 566 3D faces were correctly recognized for pose thus giving 67% of correct identification rate. We had experimented on 420 images from the GAVADB database, and only 336 images were detected for correct pose identification rate i.e. 80% and from Bosphorus database on 560 images only 448 images were detected for correct pose identification i.e. 80%.abstract goes here.

cs.CV↗

arXiv2013

A novel approach to nose-tip and eye corners detection using H-K Curvature Analysis in case of 3D images

In this paper we present a novel method that combines a HK curvature-based approach for three-dimensional (3D) face detection in different poses (X-axis, Y-axis and Z-axis). Salient face features, such as the eyes and nose, are detected through an analysis of the curvature of the entire facial surface. All the experiments have been performed on the FRAV3D Database. After applying the proposed algorithm to the 3D facial surface we have obtained considerably good results i.e. on 752 3D face images our method detected the eye corners for 543 face images, thus giving a 72.20% of eye corners detection and 743 face images for nose-tip detection thus giving a 98.80% of good nose tip localization

cs.CV↗

arXiv2013

A Novel Approach in detecting pose orientation of a 3D face required for face

In this paper we present a novel approach that takes as input a 3D image and gives as output its pose i.e. it tells whether the face is oriented with respect the X, Y or Z axes with angles of rotation up to 40 degree. All the experiments have been performed on the FRAV3D Database. After applying the proposed algorithm to the 3D facial surface we have obtained i.e. on 848 3D face images our method detected the pose correctly for 566 face images,thus giving an approximately 67 % of correct pose detection.

cs.CV↗

arXiv2013

A method for nose-tip based 3D face registration using maximum intensity algorithm

In this paper we present a novel technique of registering 3D images across pose. In this context, we have taken into account the images which are aligned across X, Y and Z axes. We have first determined the angle across which the image is rotated with respect to X, Y and Z axes and then translation is performed on the images. After testing the proposed method on 472 images from the FRAV3D database, the method correctly registers 358 images thus giving a performance rate of 75.84%.

cs.CV↗

arXiv2013

Minutiae Based Thermal Face Recognition using Blood Perfusion Data

This paper describes an efficient approach for human face recognition based on blood perfusion data from infra-red face images. Blood perfusion data are characterized by the regional blood flow in human tissue and therefore do not depend entirely on surrounding temperature. These data bear a great potential for deriving discriminating facial thermogram for better classification and recognition of face images in comparison to optical image data. Blood perfusion data are related to distribution of blood vessels under the face skin. A distribution of blood vessels are unique for each person and as a set of extracted minutiae points from a blood perfusion data of a human face should be unique for that face. There may be several such minutiae point sets for a single face but all of these correspond to that particular face only. Entire face image is partitioned into equal blocks and the total number of minutiae points from each block is computed to construct final vector. Therefore, the size of the feature vectors is found to be same as total number of blocks considered. For classification, a five layer feed-forward backpropagation neural network has been used. A number of experiments were conducted to evaluate the performance of the proposed face recognition system with varying block sizes. Experiments have been performed on the database created at our own laboratory. The maximum success of 91.47% recognition has been achieved with block size 8X8.

cs.CV↗

arXiv2013

Automated Thermal Face recognition based on Minutiae Extraction

In this paper an efficient approach for human face recognition based on the use of minutiae points in thermal face image is proposed. The thermogram of human face is captured by thermal infra-red camera. Image processing methods are used to pre-process the captured thermogram, from which different physiological features based on blood perfusion data are extracted. Blood perfusion data are related to distribution of blood vessels under the face skin. In the present work, three different methods have been used to get the blood perfusion image, namely bit-plane slicing and medial axis transform, morphological erosion and medial axis transform, sobel edge operators. Distribution of blood vessels is unique for each person and a set of extracted minutiae points from a blood perfusion data of a human face should be unique for that face. Two different methods are discussed for extracting minutiae points from blood perfusion data. For extraction of features entire face image is partitioned into equal size blocks and the total number of minutiae points from each block is computed to construct final feature vector. Therefore, the size of the feature vectors is found to be same as total number of blocks considered. A five layer feed-forward back propagation neural network is used as the classification tool. A number of experiments were conducted to evaluate the performance of the proposed face recognition methodologies with varying block size on the database created at our own laboratory. It has been found that the first method supercedes the other two producing an accuracy of 97.62% with block size 16X16 for bit-plane 4.

cs.CV↗

arXiv2013

A Comparative Study of Human thermal face recognition based on Haar wavelet transform (HWT) and Local Binary Pattern (LBP)

Thermal infra-red (IR) images focus on changes of temperature distribution on facial muscles and blood vessels. These temperature changes can be regarded as texture features of images. A comparative study of face recognition methods working in thermal spectrum is carried out in this paper. In these study two local-matching methods based on Haar wavelet transform and Local Binary Pattern (LBP) are analyzed. Wavelet transform is a good tool to analyze multi-scale, multi-direction changes of texture. Local binary patterns (LBP) are a type of feature used for classification in computer vision. Firstly, human thermal IR face image is preprocessed and cropped the face region only from the entire image. Secondly, two different approaches are used to extract the features from the cropped face region. In the first approach, the training images and the test images are processed with Haar wavelet transform and the LL band and the average of LH/HL/HH bands sub-images are created for each face image. Then a total confidence matrix is formed for each face image by taking a weighted sum of the corresponding pixel values of the LL band and average band. For LBP feature extraction, each of the face images in training and test datasets is divided into 161 numbers of sub images, each of size 8X8 pixels. For each such sub images, LBP features are extracted which are concatenated in row wise manner. PCA is performed separately on the individual feature set for dimensionality reeducation. Finally two different classifiers are used to classify face images. One such classifier multi-layer feed forward neural network and another classifier is minimum distance classifier. The Experiments have been performed on the database created at our own laboratory and Terravic Facial IR Database.

cs.CV↗

arXiv2013

Minutiae Based Thermal Human Face Recognition using Label Connected Component Algorithm

In this paper, a thermal infra red face recognition system for human identification and verification using blood perfusion data and back propagation feed forward neural network is proposed. The system consists of three steps. At the very first step face region is cropped from the colour 24-bit input images. Secondly face features are extracted from the croped region, which will be taken as the input of the back propagation feed forward neural network in the third step and classification and recognition is carried out. The proposed approaches are tested on a number of human thermal infra red face images created at our own laboratory. Experimental results reveal the higher degree performance

cs.CV↗

arXiv2013

Thermal Human face recognition based on Haar wavelet transform and series matching technique

Thermal infrared (IR) images represent the heat patterns emitted from hot object and they do not consider the energies reflected from an object. Objects living or non-living emit different amounts of IR energy according to their body temperature and characteristics. Humans are homoeothermic and hence capable of maintaining constant temperature under different surrounding temperature. Face recognition from thermal (IR) images should focus on changes of temperature on facial blood vessels. These temperature changes can be regarded as texture features of images and wavelet transform is a very good tool to analyze multi-scale and multi-directional texture. Wavelet transform is also used for image dimensionality reduction, by removing redundancies and preserving original features of the image. The sizes of the facial images are normally large. So, the wavelet transform is used before image similarity is measured. Therefore this paper describes an efficient approach of human face recognition based on wavelet transform from thermal IR images. The system consists of three steps. At the very first step, human thermal IR face image is preprocessed and the face region is only cropped from the entire image. Secondly, Haar wavelet is used to extract low frequency band from the cropped face region. Lastly, the image classification between the training images and the test images is done, which is based on low-frequency components. The proposed approach is tested on a number of human thermal infrared face images created at our own laboratory and Terravic Facial IR Database. Experimental results indicated that the thermal infra red face images can be recognized by the proposed system effectively. The maximum success of 95% recognition has been achieved.

cs.CV↗

arXiv2011

Next Level of Data Fusion for Human Face Recognition

This paper demonstrates two different fusion techniques at two different levels of a human face recognition process. The first one is called data fusion at lower level and the second one is the decision fusion towards the end of the recognition process. At first a data fusion is applied on visual and corresponding thermal images to generate fused image. Data fusion is implemented in the wavelet domain after decomposing the images through Daubechies wavelet coefficients (db2). During the data fusion maximum of approximate and other three details coefficients are merged together. After that Principle Component Analysis (PCA) is applied over the fused coefficients and finally two different artificial neural networks namely Multilayer Perceptron(MLP) and Radial Basis Function(RBF) networks have been used separately to classify the images. After that, for decision fusion based decisions from both the classifiers are combined together using Bayesian formulation. For experiments, IRIS thermal/visible Face Database has been used. Experimental results show that the performance of multiple classifier system along with decision fusion works well over the single classifier system.

cs.CV↗