Search

With aim of detecting breast cancer at the early stages using mammograms, this study presents the formulation of five feature types by extending the information set to encompass the concept of an intuitionist fuzzy set. The resulting pervasive information set gives not only the certainty of the pixel intensities of mammograms to a class but also the deficiency in the fuzzy modeling referred to as the hesitancy. The generalized adaptive Hanman Anirban fuzzy entropy function is shown to be equivalent to the hesitancy entropy function. The probability-based fuzzy Hanman transform and the pervasive Information with probability taking the role of hesitancy degree help derive the above five feature types termed as probability-based pervasive Information set features. The effectiveness of each feature type is demonstrated on the mini-MIAS and DDSM databases for the multi-class categorization of mammograms using the Hanman transform classifier. The statistical analysis by ANOVA test proves that the features are statistically significant and the experimental results are shown to be clinically relevant by the expert radiologists. The performance of the five feature types is either superior to or equal to that of some deep learning architectures on comparison but they outperform the state-of-the-art literature methods in the classification of breast cancer using mammograms.

In this paper, a novel method based on information set theory is proposed to detect defects in fabric texture. Information set extends the fuzzy set by finding the uncertainty associated with the a...

An efficient filtering algorithm is required to remove noise and simultaneously protect fine details and important features in the medical images. In this paper, a noise adaptive information set based switching median (NAISM) filter is proposed for the removal of impulse noise. NAISM filter is inspired from fuzzy switching median filter and works on the concept of information sets. Information sets are derived from fuzzy sets to deal with the uncertainty. It works in two phases; first phase identifies noisy pixels and second applies filtering based on an adaptive switching criterion. It is by virtue of this switching criterion and the local effective information surrounding the noisy pixel, the best calculated value replaces the noisy pixel in the selected window. The proposed information set based filter is capable of removing both low and high noise densities and can preserve image details better than the fuzzy filter. The applicability of the proposed filter is demonstrated on different datasets including Berkeley Segmentation Dataset (BSD), medical and real images. The qualitative and quantitative results demonstrate the effectiveness of the proposed approach in suppressing noise over the existing approaches.

This paper presents the information set which originates from a fuzzy set on applying the Hanman-Anirban entropy function to represent the uncertainty. Each element of the information set is called the information value which is a product of the information source value and its membership function value. The Hanman filter that modifies the information set is derived by using a filtering function. Adaptive Hanman-Anirban entropy is formulated and its properties are given. It paves the way for higher form of information sets called Hanman transforms that evaluate the information source based on the information obtained on it. Based on the information set six features, Effective Gaussian Information source value (EGI), Total Effective Gaussian Information (TEGI), Energy Feature (EF), Sigmoid Feature (SF), Hanman transform (HT) and Hanman Filter (HF) features are derived. The performance of the new features is evaluated on CASIA-IRIS-V3-Lamp database using both Inner Product Classifier (IPC) and Support Vector Machine (SVM). To tackle the problem of partially occluded eyes, majority voting method is applied on the iris strips and this enables better performance than that obtained when only a single iris strip is used.

This paper presents a robust dorsal hand vein authentication system. A new method is proposed for the region of interest extraction using fingertips and finger valley key points. Some new features and a new classifier are proposed based on information set theory. Information set stems from a fuzzy set on representing the uncertainty in its attribute/information source values using the information-theoretic entropy function. The new feature types include vein effective information, vein energy feature, vein sigmoid feature, Shannon transform feature, and composite transform feature. A classifier called the improved Hanman classifier is formulated from training and test feature vectors using Frank t-norm and the entropy function. The performance and robustness are evaluated on GPDS and BOSPHORUS palm dorsal vein database under both the constrained and unconstrained conditions.

A new filter method is proposed for feature selection and ranking that incorporates a novel mutual information with Gaussian gain for evaluating the relationships between features and the class, and in-between features. The new mutual information is derived as per the axioms of classical information theory from the recently introduced non-extensive entropy with Gaussian gain. The characteristic of this entropy is its non-linearity when representing correlated information in natural texture images represented by sparse probability distributions. In this work, we trace this property in our new mutual information in the context of correlated random variables associated with real-world datasets. The non-linearity of the Gaussian function embedded in the mutual information formula is utilized for identifying the most important features in the correct order of rank, right at the outset of the incremental feature selection algorithm. This leads to formation of smaller groups of ranked feature subsets that give the highest classification accuracies. Extensive experimentation on twenty benchmark datasets from the UCI repository along with comparison to the state-of-the-art confirms the efficacy of our approach. An automated optimum feature subset selection is also proposed based on a simple statistical test on the new measure.

This paper presents the formulation of the possibilistic Renyi entropy function from the Renyi entropy function using the framework of Hanman-Anirban entropy function. The new entropy function is used to derive the information set features from keystroke dynamics for the authentication of users. A new composite fuzzy classifier is also proposed based on Mamta-Hanman entropy function and applied on the Information Set based features. A comparison of the results of the proposed approach with those of Support Vector Machine and Random Forest classifier shows that the new classifier outperforms the other two.

This paper presents three texture features, viz., topothesy-fractal dimension, Hanman transform, and structure function based transform for the multispectral palmprint based authentication. It introduces the notion of information set originating from the Hanman–Anirban entropy. Using information set, Hanman transform features are derived. The topothesy-fractal dimension features arise from the structure function on representing the intensity variation on the texture surface. The structure function based transform features are derived from both structure function and the Hanman transform. Apart from the feature extraction, the fuzzy classifier based on the information processing is also developed. A novel score level fusion is proposed using Triangular-norms and Triangular-conorms. Thus the paper’s contribution is three-fold: i) New features for multispectral palmprint, ii) novel classifier for authentication, and iii) score level fusion for improving the accuracy. The rigorous experimental results certify that the proposed approaches make a substantial improvement in the authentication accuracy and outperform the contemporary approaches.

Color textures have a unique inter-relationship among its color planes since they contribute information about the same recurring pattern. The average information or entropy is thus presumed to be redundant across the color planes. This is the basis of our paper, which focuses on dimensionality reduction of color texture features by averaging the entropies across multidimensional color planes, while at the same time maintaining the high accuracy of color texture recognition. The mean operation was used in summarizing the original eleven-dimensional difference theoretic texture features for texture classification in Susan and Hanmandlu (IET Image Process 7(8):725–732, 2013). In this work, instead of the mean, we measure the entropy of the features across multidimensional color planes. The non-extensive entropy with the Gaussian information gain is used as the entropy measure for our experiments since it is non-linear and a good indicator of regular patterns in textures. Comparisons with the state-of-the-art prove the efficiency of our approach both in terms of accuracy and the reduced feature dimension.

Display Omitted This paper presents the illumination-invariant and pose-invariant face recognition method.The Mamta-Hanman entropy function is made adaptive and its properties are provided.It makes use of the adaptive Mamta-Hanman entropy in the formulation of Hanman transform and Shannon transform.It develops several new features based on the Mamta-Hanman entropy function.It combines other techniques to make the proposed recognition invariant to poses and illumination. This paper presents a new approach for face recognition under pose and illumination variations. The concept of information set is presented and the features based on this are derived using the Mamta-Hanman entropy function. The properties of an adaptive version of this entropy are given and nonlinear Shannon transform and Hanman transform which area higher form of information set are formulated. The information set based features and the nonlinear Shannon transform features are separately combined with the Pseudo-inverse Locality Preserving Projections (PLPP) for improving their effectiveness. The performance of the combined features is compared with that of the holistic approaches on four face databases (two FERET, one head pose image, and Extended Yale face database). The features from the combination of nonlinear Shannon transform and PLPP give consistent performance on the three databases tested whereas the well known features from the literature show good performance on one or two databases only.

In the contemporary world, breast tumor is the most consistently spotted neoplasm among women, that is, instigating women’s transience at a higher rate. Radiologists prefer computer-aided mammography in order to detect breast cancer. Mammograms consist of many artifacts like labels, pectoral muscles whose removal is a daunting task. The presence of glandular tissues in digital mammograms plays a pivotal role in the early finding of breast cancer. This is necessary to find the radiation risk linked with screening and also to find the irregularity between right and left breasts. The proposed method focuses on pre-processing and breast density segmentation. In this method, both binarization and the modified region growing method are applied for removing the labels, background and pectoral muscles. For improving the contrast of the images bereft of the pectoral muscles, it uses the contrast limited adaptive histogram equalization with Rayleigh distribution. Next use is made of K-means clustering to segment the digital mammograms into different density regions. The proposed method is applied on a publicly accessible mini-MIAS database. Its results are validated by the expert radiologists and these compete with those of the state of the art methods.

Mortality rate because of breast cancer diminishes to a large extent if the categorization of breast lesions as malignant or benign is done properly. But this process is quite complicated owing to erroneous detection of noise pixels as false positives. It can be reduced by proper enhancement of the features of the mammogram giving an indication of cancer. In this paper, contrast limited adaptive histogram equalization (CLAHE) and entropy-based intuitionistic fuzzy method are anticipated for improving the contrast of digital mammogram images. To validate the efficacy of the proposed algorithm over type II fuzzy set-based techniques, subjective, quantitative and visual evaluation is done on publicly available MIAS database. Experimental results prove that the proposed technique gives better visual quality. It provides high values of subjective and quantitative metrics compared to several states of art algorithms.

This paper presents the properties of information sets that help derive local features from a face when partitioned into windows and devises the information rules from the generalized fuzzy rules for information processing that helps match the unknown test face with the known for authenticating a user. information set is constituted from the information values that result from representing the uncertainty in a type-1 fuzzy set by Hanman–Anirban entropy function. The information values are shown to be the products of information sources (gray levels) in a window and their membership function values. The Hanman filter (HF) is devised to modify the information values using a cosine function whereas the Hanman transform (HT) is devised to evaluate the information source values based on the information obtained on them. Three classifiers, namely the inner product classifier, normed error classifier, and Hanman classifier are formulated. The two feature types based on HF and HT are tested on the AT&T (ORL) database, which contains pose variations in the face images and two other face databases: Indian face Database (IIT Kanpur) and UMIST (Sheffield) using new as well as known classifiers like Euclidean distance- based, Bayesian, and support vector machine classifiers.

This paper presents keystroke dynamics based authentication system using the information set concept. Two types of membership functions (MFs) are computed: one based on the timing features of all the samples and another based on the timing features of a single sample. These MFs lead to two types of information components (spatial and temporal) which are concatenated and modified to produce different feature types. Two Component Information Set (TCIS) is proposed for keystroke dynamics based user authentication. The keystroke features are converted into TCIS features which are then classified by SVM, Random Forest and proposed Convex Entropy Based Hanman Classifier. The TCIS features are capable of representing the spatial and temporal uncertainties. The performance of the proposed features is tested on CMU benchmark dataset in terms of error rates (FAR, FRR, EER) and accuracy of the features. In addition, the proposed features are also tested on Android Touch screen based Mobile Keystroke Dataset. The TCIS features improve the performance and give lower error rates and better accuracy than that of the existing features in literature.

This paper presents the finger-knuckle-print (FKP) recognition system which comprises three functional phases namely: (1) novel technique for the feature extraction based on the structure function, (2) new classifier based on Triangular norms (T-norms), (3) novel techniques for the rank level fusion. The features derived from the structure function capture the variation in the texture of FKP. We have also proposed a classifier based on Frank T-norm which addresses the uncertainty in the intensity levels of image. We have also adapted the Choquet integral for the rank level fusion to improve further the identification accuracy of the individual FKP. The Choquet integral has never been used for the rank level fusion in the literature. The fuzzy densities will be learned using the reinforced hybrid bacterial foraging-particle swarm optimization (BF-PSO). The integral takes care of the overlapping information between the different instances of FKPs. We have also proposed the use of entropy based function for the rank level fusion. The rigorous experimental results of the rank level fusion show the significant improvement in the identification accuracy.

The Local Principal Independent Components (LPIC) developed as an extension to the Principal Component Analysis (PCA) based on the information set are utilized for the iris based authentication. LPIC allows the extraction of not only the local texture information present in the Iris image but also reduces the dimension far less than that can be achieved with PCA. Four types of information set features such as Effective information (EI), Energy feature (EF), Sigmoid feature (SF), Hanman transform (HT) are formulated and the corresponding LPIC features much less in number are derived and then the test set is classified with the Hanman classifier. The experiments carried out on CASIA-Iris-Lamp database show that LPIC outperforms PCA using the Hanman Classifier mostly. The proposed approach gives 99.2% whereas PCA gives 27.7% with only 30% of features.

Human attention tends to get focused on the most prominent components of a scene which are in sharp contrast with the background. These are termed as salient regions. The human brain perceives an object to be salient based on various features like the relative intensity, spread of the region, color contrast with the background, size and position within an image. Since these features vary widely, no crisp thresholds can be specified for an automatic salient region detector. In this paper we present a rule based system which uses a set of fuzzy features to mark out the salient region in an image. A genetic algorithm based evolutionary system is used to learn the rules from the training images. Extensive comparisons with the state-of-the-art methods in terms of precision, recall and F-measure are made on two different publicly available datasets to prove the effectiveness of this approach. The application of the proposed salient object detection approach is shown in non-photorealistic rendering, perception based image compression and context aware retargeting applications with promising results.

This paper presents the development of a multimodal biometric system comprising a behavioral biometric called gait and a physiological biometric called hand vein pattern. Toward the unified feature extraction, we use the information set approach to represent the frame of a gait sequence by the feature called the effective gait information and the vein pattern image by the feature called the effective vein information using the Hanman---Anirban entropy function. Using these two features for the two modalities, we go in for the score level fusion which gives a limited accuracy. In order to improve the performance refined scores approach is proposed where in the original scores are refined by using the cohort (neighborhood) scores. The performance of the proposed approach is demonstrated on two databases.

In order to visualize the breast cancer radiologists prefer to use mammogram and breast ultrasound imaging modalities. To detect cancer, a region of interest (ROI) symbolizing tumor is extracted from the image. The segmentation process becomes tedious in presence of noise, low contrast, and blurriness. Pre-processing is done before segmentation to enhance the contrast and to remove the unwanted information from the image. Segmentation also influences the classification of the image into benign and malignant classes. Various segmentation techniques have been proposed in the literature to extract microcalcification region of interest, masses, and breast lesions and to remove the pectoral muscles. This paper provides the detailed review of these techniques, particularly for mammogram images.

This paper presents the convolutional neural network for feature extraction and Support vector machine for the verification of offline signatures. The cropped signatures are used to train CNN forr extracting features. The Extracted features are classified into two classes genuine or forgery using SVM. The the new signature is tested on GPDS signature data base using the trained SVM. The dabase contains signatures of 960 users and for each user there are 24 genuine signatures and 30 forgeries. The CNN network is trained with 300 users and signatures of 400 users are used for feature learning. These 400x20x25 signatures are used 90%to train and 10% to test SVM classifier.

This paper presents a novel method for keystroke dynamics based authentication by utilising Generalised Fuzzy Model (GFM), which is a combination of Mamdani-Larsen and Takagi-Sugeno fuzzy models. We make use of Gaussian Mixture Model (GMM) and GFM for modelling using the individual keystroke measurement types and combinations of measurement types of the keystroke dynamics. To validate GFM on keystroke dynamics in the real-world situation, it is tested on CMU dataset and the performance of this model is superior to that of GMM.

Owing to the ever increasing demand of privacy protection and security concerns, hand geometry based biometric system aimed at addressing these concerns is developed. In this study we have developed an authentication system which is based on finger shapes. The shapes of fingers are considered as patterns for extracting features using Eigen vector method and discrete wavelet transform. There are four feature types that include (i) Frequency and power content using Eigen vector method, (ii) Pisaranko’s method (iii) Wavelet entropy of individual fingers, and (iv) Specific area of finger.

The information set that widens the fuzzy set theory.A spatiotemporal statistical gait representation, which expresses the statistics of motion patterns.The superiority of our features demonstrated by testing them on changed co-variant conditions (i.e. clothing, carrying) and change in speed.The performance of the new features is quantified through measures like cumulative match characteristics (CMC). Human gait, a soft biometric helps to recognize people by the manner, they walk. This paper presents gait image features based on the information set theory, henceforth these are called gait information image features. The information set stems from a fuzzy set with a view to represent the uncertainty in the information source values using the entropy function. The proposed gait information image (GII) is derived by applying the concept of information set on the frames in one gait cycle and two features named gait information image with energy feature (GII-EF) and gait information image with sigmoid feature (GII-SF) are extracted. Nearest neighbor (NN) classifier is applied to identify the gait. The proposed features are tested on Casia-B dataset, SOTON small database with variations in clothing and carrying conditions and on OU-ISIR Treadmill B database with large variation in clothing conditions. Moreover, experiments are carried out on OU-ISIR Treadmill A database with slight variation in the walking speeds to demonstrate the robustness of the proposed features.

The detection of singular points (core and delta) accurately and reliably is very important for classification and matching of fingerprints. This paper presents a new approach for core point detection based on scale invariant feature transform (SIFT). Firstly, SIFT points are extracted ,then reliability and ridge frequency criteria are applied to reduce the candidate points required to make a decision on the core point. Finally a suitable mask is applied to detect an accurate core point. Experiments on FVC2002 and FVC2004 databases show that our approach locates a unique reference point with high accuracy. Results of our approach are compared with those of the existing methods in terms of accuracy of core point detection. Defence Science Journal, 2013, 63(4), pp.402 -407 , DOI:http://dx.doi.org/10.14429/dsj.63.2708

This paper presents the hybrid of the adaptive fuzzy decision level fusion and the score level fusion for finger-knuckle-print (FKP) based authentication to improve over the individual fusion methods. The scores obtained from the fusion of the left index (LI) and the left middle (LM) and those obtained from the fusion of the right index (RI) and the right middle (RM) FKP are fused at the fuzzy decision level. The uncertainty in the local decisions made by the individual score level fusion methods is addressed by treating the error rates as fuzzy sets. The operating points (thresholds) are adapted to accommodate the varying the cost of false acceptance rate using the hybrid PSO algorithm that ensures the desired level of security. The error rates associated with the operating points are converted into the fuzzy domain by triangular membership functions and the alpha-cuts are applied on the membership functions for the better representation of uncertainty. The global fuzzy error rates are defuzzified using total distance criterion (TDC). The rigorous experimental results indicate that the hybrid fusion is superior to the component level fusion methods (score level and decision level fusion).

A new entropy that can modify the probabilities in the function is formulated.Two information set based features: EGI and EEI are derived from the above function.A unique multimodal biometric system comprising IR face, iris and ear is developed.A classifier based on Refined Scores that use cohort scores in refining is devised.The combined scores from individual modalities are fused at the score level fusion and then improved by RS method. This paper presents a unique face based multimodal biometric system comprising IR face, ear and iris to cater to the surveillance application by proposing new entropy function. Two new features based on this entropy are devised to cater the highly uncertain database found at the surveillance site. To handle the erroneous scores we have proposed Refined Score (RS) method and applied it on individual IR face, ear and iris modalities under both constrained and the unconstrained conditions for the authentication of users and also used for the score level fusion of these modalities using the proposed entropy based features. The entropy features show good performance under the constrained and unconstrained databases whereas the conventional entropies do not fare well on the unconstrained databases. RS based classifier always outperforms the EC (Euclidean classifier) and RS based score level fusion has an edge over the conventional score level fusion.

This paper presents three feature types based on the concept of information set for face recognition. The first set of features includes sigmoid and energy features. The second set of features includes two features, viz. effective information set features-I and features-II and their combinations using t-norms, s-norms of Hamacher and Yager. The third set of features includes two hybrid features called Gabor-information set features and wavelet-information set features. These are extracted by applying the information set concept on the responses of Gabor filter bank and on the approximation components of the wavelet decompositions of the original face images. In addition to these two hybrid features, Hanman filter is developed by combining the information set and cosine function. The performance of all three types involving a total of seven features, two from the first type, two from the second type and three from the third type is evaluated on AT&T database using the proposed Hanman classifier formulated from the conditional entropy function and SVM. The effectiveness of these features is also demonstrated on another database called Indian Face database of IIT Kanpur having wide pose variations. The Hanman filter is shown to have consistent performance on these two databases.

Biometric systems are enabling technologies for a wide set of applications in Ambient Intelligence (AmI) environments. In this context, speaker recognition techniques are of paramount importance due to their high user acceptance and low required cooperation. Typical applications of biometric recognition in AmI environments are identification techniques designed to recognize individuals in small datasets. Biometric recognition methods are frequently deployed on embedded hardware and therefore need to be optimized in terms of computational time as well as used memory. This paper presents a text-independent speaker recognition method particularly suitable for identification in AmI environments. The proposed method first computes the Mel Frequency Cepstral Coefficients (MFCC) and then creates Information Set Features (ISF) by applying a fuzzy logic approach. Finally, it estimates the user's identity by using a hierarchical classification technique based on computational intelligence. We evaluated the performance of the speaker recognition method using signals belonging to the NIST-2003 switchboard speaker database. The achieved results showed that the proposed method reduced the size of the template with respect to traditional approaches based on Gaussian Mixture Models (GMM) and achieved better identification accuracy.

Several studies have been made in the literature for the early detection of breast cancer using mammograms. These studies mainly deal with methods that do not capture local information. To fill up this gap this paper presents an approach that extracts the local features called information set features representing the uncertainties in the distributions of grey levels in windows/sub-images of a mammogram using the Mamta-Hanman entropy function. The extracted features are used for classification into two-class (abnormal, normal) and three-class (normal, benign, malignant) modes. Two classifiers are used, the first is the Hanman transform classifier that represents the uncertainties in the error vectors between training feature vectors of a patient and the test feature vector of an unknown patient, and the second is hesitancy based Hanman transform classifier that not only represents the uncertainties in the error vectors but also the deficiencies in the modeling of membership and non-membership functions. Both classifiers outperform the methods considered for comparison on the same mini-MIAS database.

An attempt is made to devise a new entropy function that goes beyond the existing entropy functions with its ability to change the information source values (gray levels in an IR image) and its information gain by selecting its parameters. Our objective is to improve the existing results on the Infra-Red thermal face recognition by using this entropy function that possesses peculiar characteristics such as splitting and inverting which impart a discriminating power. To cash on its discriminating power, two types of features Effective Gaussian Information (EGI) source and Effective Exponential Information (EEI) source functions are developed. To classify the features, we have modified our earlier classifier (Mamta and Hanmandlu, 2014) using the new entropy function. The performance of the new features and new classifier is tested on IR face databases under the constrained and the unconstrained conditions with regard to occlusion, noise and low resolution. A comparison of performance shows that the new entropy function outperforms the existing entropy functions such as Shannon, Renyi, Tsallis and Pal and Pal, Collision, Min entropy and Susan-Hanman. A new non-extensive entropy is proposed in this paper.Features based on this entropy is used for experiments.A classifier is developed based on new entropy function.The results of experiments carried out on different databases are promising.The proposed authentication system shows invariance to resolution, occlusion and noise.

Face recognition under the unconstrained conditions that exist in surveillance is the need of the present times. Thus for high end security the research on IR based face recognition assumes importance because of its insensitivity to illumination, disguise and surgery. This paper presents IR face based biometric authentication using the information-set based four types of interactive features and two classifiers. The information sets originate from a fuzzy set on representing the uncertainty associated with the information source instead of a membership function which gives only the degree of association to the fuzzy set. The four feature types include the effective exponential information source ( EEI ), the effective Gaussian information source ( EGI ), the effective multi quadratic information source ( EMQDI ) and inverse of this feature ( EIMQDI ). The interactive features are obtained by taking the s-norms on the features from the successive windows. Two classifiers called the Hanman Classifier and the weighted Hanman Classifier are formulated using t-norms. The features and classifiers are tested on the created databases incorporating the unconstrained conditions such as occlusion, less resolution and noise.

This study presents a new online signature verification system based on fuzzy modelling of shape and dynamic features extracted from online signature data. Instead of extracting these features from a signature, it is segmented at the points of geometric extrema followed by the feature extraction and fuzzy modelling of each segment thus obtained. A minimum distance alignment between the two samples is made using dynamic time warping technique that provides a segment to segment correspondence. Fuzzy modelling of the extracted features is carried out in the next step. A user-dependent threshold is used to classify a test sample as either genuine or forged. The accuracy of the proposed system is evaluated using both skilled and random forgeries. For this, several experiments are carried out on two publicly available benchmark databases, SVC2004 and SUSIG. The experimental results obtained on these databases demonstrate the effectiveness of this system.

Texture identification and classification under varying scale, rotation and illumination conditions is a challenging task in pattern recognition and grey level difference statistics have been extensively used for this purpose. This study presents a new set of features for scale-, rotation- and illumination-invariant texture classification derived from the correlated distributions of local and global grey level differences of intensities in the texture image. The authors analyse the terms in the correlation formula for determining the difference-based feature set that is invariant and unique for a texture class. A comprehensive evaluation is performed on a huge database of digitally created texture samples of varying scale, orientation and brightness. The one-nearest neighbour classifier is used in the authors' experiments and the results indicate high classification accuracy for the proposed feature vector under varying scale, rotation and brightness conditions. The proposed method is compared with the highly efficient rotation- and illumination-invariant local binary pattern (LBP) and LBP variance techniques and the scale- and rotation-invariant MRS4 technique and is found superior in performance with an additional advantage of reduced feature dimension.

This paper presents the ear based authentication using Local Principal Independent Components (LPIC) an extension of PCA. As PCA is a global approach dealing with all pixel intensities, it is difficult to get finer details from the ear image. The concept of information sets is introduced in this paper so as to have leverage over the local information. These sets are based on the granularization of the ear image in the form of windows. The features based on these sets allow us to change the local information which goes into LPIC as the input. Thus LPIC not only uses this local information but also helps to reduce the dimensions of the deduced features far less than that can be achieved with PCA. For the extraction of sparse information from ear, features such as Effective information (EI), Energy feature (EF), Sigmoid feature (SF), Multi Quadratic feature (MQD) are derived and then LPIC is applied to get the reduced number of features. Inner product classifier (IPC) is developed for the classification of these features. The experiments carried out on constrained and unconstrained databases show that LPIC is effective not only under the ideal conditions but also under the unconstrained environment.

This paper proposes a new probabilistic non-extensive entropy feature for texture characterization, based on a Gaussian information measure. The highlights of the new entropy are that it is bounded by finite limits and that it is non-additive in nature. The non-additive property of the proposed entropy makes it useful for the representation of information content in the non-extensive systems containing some degree of regularity or correlation. The effectiveness of the proposed entropy in representing the correlated random variables is demonstrated by applying it for the texture classification problem since textures found in nature are random and at the same time contain some degree of correlation or regularity at some scale. The gray level co-occurrence probabilities (GLCP) are used for computing the entropy function. The experimental results indicate high degree of the classification accuracy. The performance of the new entropy function is found superior to other forms of entropy such as Shannon, Renyi, Tsallis and Pal and Pal entropies on comparison. Using the feature based polar interaction maps (FBIM) the proposed entropy is shown to be the best measure among the entropies compared for representing the correlated textures.

This paper presents three novel methods for speaker identification of which two methods utilize both the continuous density hidden Markov model (HMM) and the generalized fuzzy model (GFM), which has the advantages of both Mamdani and Takagi-Sugeno models. In the first method, the HMM is utilized for the extraction of shape-based batch feature vector that is fitted with the GFM to identify the speaker. On the other hand, the second method makes use of the Gaussian mixture model (GMM) and the GFM for the identification of speakers. Finally, the third method has been inspired by the way humans cash in on the mutual acquaintances while identifying a speaker. To see the validity of the proposed models [HMM-GFM, GMM-GFM, and HMM-GFM (fusion)] in a real-life scenario, they are tested on VoxForge speech corpus and on the subset of the 2003 National Institute of Standards and Technology evaluation data set. These models are also evaluated on the corrupted VoxForge speech corpus by mixing with different types of noisy signals at different values of signal-to-noise ratios, and their performance is found superior to that of the well-known models.

Motion estimation and motion analysis have an important role to play for detecting abnormal motion in surveillance videos. In this paper, we propose to use the non-extensive entropy to detect any unnaturalness in the motion over correlated video frames since it has already been proved to represent the correlated textures successfully. To achieve this end, we utilize the temporal correlation property of motion vectors over three consecutive frames to detect any motion disturbance using a weighted average of the non-extensive entropies. It is proved by the experimental results on the state-of-the-art database that the non-extensive entropy is most apt for detecting any disturbance in the continuance of motion vectors in between frames. The advantage of our approach is that no training period or normalcy reference is required since a relative disturbance in the magnitudes of motion vectors over a three-frame window gives an alarm.

paper presents a novel algorithm for fingerprint matching using statistical descriptors. This fingerprint-matching algorithm overcomes the problems faced during matching of low quality fingerprint images. The steps of the algorithm include extraction of core point using Poincare index method, extraction of Region of Interest (ROI) around core point, and similarity evaluation of statistical descriptors using k-NN classifier. Statistical descriptors are computed from 16 Gray Level Co-occurrence Matrices (GLCM) from Extracted ROI. The proposed algorithm is evaluated on the FVC2002 DB2 database. The experimental results show the effectiveness of proposed algorithm. Computational efficiency is improved by considering the ROI of size 101  101 around the core point.

This paper presents an approach for the personal authentication using rank-level fusion of multispectral palmprints, instead of using multiple biometric modalities and multiple matchers. The rank level fusion involving the non linear combination of hyperbolic tangent functions gives the best recognition rate for the Rank 1 obtained from two types of features, viz., sigmoid and fuzzy. The results of using rank level fusion on the publicly available multispectral palmprint database show the significant improvement in the recognition rate as compared to the individual spectral bands. Recognition rate of 99.4% from sigmoid features and that of 99.2% from fuzzy features based on Rank 1 is the outcome of the hyperbolic tangent nonlinearity.

This paper presents a fast and reliable algorithm for fingerprint verification. Our proposed fingerprint verification algorithm is based on image-based fingerprint matching. The improved orientation feature vector of two fingerprints has been compared to compute the similarities at a given threshold. Fingerprint image has been aligned by rotating through an angle before feature vector is computed and matched. Row and Column variance feature vector of orientation image will be employed. The algorithm has been tested on the FVC2002 Databases. The performance of algorithm is measured in terms of GAR and FAR. At a threshold level of 1.1 % and at 5.7% FAR the GAR observed is 97.83%. The improved Feature vector will lower imposter acceptance rate at reasonable GAR and hence yields better GAR at lower FAR. The proposed algorithm is computationally very efficient and can be implemented on Real-Time Systems.

Bio-inspired edge detection using fuzzy logic has achieved great attention in the recent years. The bacterial foraging (BF) algorithm, introduced in Passino (IEEE Control Syst Mag 22(3):52---67, 2002) is one of the powerful bio-inspired optimization algorithms. It attempts to imitate a single bacterium or groups of E. Coli bacteria. In BF algorithm, a set of bacteria forages towards a nutrient rich medium to get more nutrients. A new edge detection technique is proposed to deal with the noisy image using fuzzy derivative and bacterial foraging algorithm. The bacteria detect edge pixels as well as noisy pixels in its path during the foraging. The new fuzzy inference rules are devised and the direction of movement of each bacterium is found using these rules. During the foraging if a bacterium encounters a noisy pixel, it first removes the noisy pixel using an adaptive fuzzy switching median filter in Toh and Isa (IEEE Signal Process Lett 17(3):281---284, 2010). If the bacterium does not encounter any noisy pixel then it searches only the edge pixel in the image and draws the edge map. This approach can detect the edges in an image in the presence of impulse noise up to 30%.

In character recognition, zoning based feature extraction is one of the most popular methods. The character image is divided into predefined number of zones and a feature is computed from each of these zones. Usually, this feature is based on the pattern (black) pixels contained in that zone. Some of such features are average pixel density, sum squared distance, histogram. But in such features, say the average pixel density, different combination location of pixels can all give rise to same average pixel density. This often leads to errors in classification. In this paper, a new technique is presented where the pattern pixel location is also taken into account to contribute as much unique feature as possible. The experimental tests, carried out in the field of Devanagari handwritten numeral and character recognition show that the proposed technique leads to improvement over the traditional zoning methods.. General Terms Character recognition.

We present a novel approach for the development of fuzzy hidden Markov models (FHMMs) by exploiting both additive and nonadditive properties of input fuzzy sets in the fuzzy rules of generalized fuzzy model (GFM). This development utilizes 1) Gaussian mixture model (GMM) to manipulate the mixture parameters for the input fuzzy sets and 2) GFM rules for the inclusion of states in the consequent part to be able to use HMM. Taking the components of Gaussian mixture density conditioned on the past system states and making use of equivalence of GMM with GFM, parameters of the additive and nonadditive FHMMs are estimated using the forward-backward procedure of the Baum-Welch algorithm. The additive and nonadditive FHMMs are validated on three benchmark applications involving time-series prediction, and the results are compared and found to be better than or equal to those of the existing recent fuzzy models.

This paper makes an attempt to segment the handwritten Hindi words. The problem of segmentation is compounded by the possible presence of modifiers known as matras on all sides of the basic characters and due to the uncertainty introduced in the character shapes by way of different writing styles. We have devised a structural approach to capture the similarities and differences between structure classes. The segmentation is performed in hierarchical order: 1) Separating the upper modifiers and header line from the character, 2) Detecting and then segmenting lower modifiers from the characters, 3) Identifying whether a character is conjunct or not, 4) Categorization of top modifiers based on Check_point, Mid_point and Touching_points. The segmentation accuracy has been found to be around 78%. Some general conditions are applied for separating modifiers from the characters. But certain words cannot be segmented because they violate the general conditions. However, specifics are not dealt with in this paper because such an attempt requires an exhaustive study on a large database that is not available presently.

This paper proposes a new improved mountain clustering technique, which is compared with some of the existing techniques such as K-Means, FCM, EM and Modified Mountain Clustering. The performance of all these clustering techniques towards color image segmentation is compared in terms of cluster entropy as a measure of information and observed via computational complexity. The cluster entropy is heuristically determined, but is found to be effective in forming correct clusters as verified by visual assessment.

Human attention tends to get focused on the most prominent components of a scene which are in sharp contrast with the background. These are termed as salient regions. Saliency is defined in terms of local and global feature contrasts. The human brain perceives an object of salient type based on its difference with the surroundings in terms of color and texture. There have been many color based approaches in the past for salient object detection. In this paper, we define the uncertainty of a window being salient or background in terms of information extracted from different color components. The uncertainty associated with the elements of a fuzzy set is described by a membership function, which gives the degree of association of each element to the set. The overall uncertainty is sought to be quantified by an entropy function. To locate the salient parts of the image, we make use of the entropy to compute a new set of features from color and luminance components of the image. Extensive comparisons with the state-of-the-art methods in terms of precision, recall and F-Measure are made on a publicly available dataset to prove the effectiveness of this approach.

This paper presents a single sample face recognition technique which takes care of illumination variations by applying normalization based on Weber's law. Local Directional Pattern (LDP) features are extracted from the normalized face by examining the prominent edge directions at each pixel. The LDP image is divided into non-overlapping windows and each window is treated as a fuzzy set. Treating LDP values as the information source values, entropy features called the information set- based features are extracted from each window. Further, 2DPCA is used to reduce the number of features. These features are augmented with entropy features of the fiducial regions and contour based features for face recognition. A nearest neighbor classifier based on these features is used on Extended Yale B and Face94 datasets and it is shown that compared with other results based on single and multiple training images, the proposed approach results in better recognition accuracy for wide illumination variations in test images. Further the efficiency of the scheme is shown by comparing the number of features needed for recognition.

This paper proposes a new online signature verification system. We have developed features based on Hanman-Anirban entropy function. We have used the Inner Product Classifier (IPC) for the verification of the signatures. The performance of signature verification has been found to be promising.