Department of Computer Science and Information Systems
Permanent URI for this collectionhttp://localhost:4000/handle/123456789/1928
Browse
8 results
Search Results
Item Error Level Fusion of Multimodal Biometrics(JPRR, 2011) Grover, JyotsanaThis paper presents a multimodal biometric system based on error level fusion. Two error level fusion strategies, one involving the Choquet integral and another involving the t-norms are proposed. The first strategy fully exploits the non additive aspect of the integral that accounts for the dependence or the overlapping information between the error rates FAR's and FRR's of each biometric modality under consideration. A hybrid learning algorithm using combination of Particle Swarm Optimization, Bacterial Foraging and Reinforcement learning is developed to learn the fuzzy densities and the interaction factor. The second strategy employs t-norms that require no learning. The fusion of the error rates using t-norms is not only fast but results in very good performance. This sort of fusion is a kind of decision level fusion as the error rates are derived from the decisions made on individual modalities. The experimental evaluation on two hand based datasets and two publically available datasets confirms the utility of the error level fusionItem Score level fusion of multimodal biometrics using triangular norms(Elsevier, 2011-10) Grover, JyotsanaA multimodal biometric system that alleviates the limitations of the unimodal biometric systems by fusing the information from the respective biometric sources is developed. A general approach is proposed for the fusion at score level by combining the scores from multiple biometrics using triangular norms (t-norms) due to Hamacher, Yager, Frank, Schweizer and Sklar, and Einstein product. This study aims at tapping the potential of t-norms for multimodal biometrics. The proposed approach renders very good performance as it is quite computationally fast and outperforms the score level fusion using the combination approach (min, mean, and sum) and classification approaches like SVM, logistic linear regression, MLP, etc. The experimental evaluation on three databases confirms the effectiveness of score level fusion using t-norms.Item Hybrid fusion of score level and adaptive fuzzy decision level fusions for the finger-knuckle-print based authentication(Elsevier, 2015-06) Grover, JyotsanaThis 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).Item Human identification based on gait recognition for multiple view angles(Springer, 2018-06) Grover, JyotsanaGait has emerged as a new biometric verification method which helps in recognising a person by his walking style. In this paper, gait features are extracted based on information set theory, which itself is derived from fuzzy set theory. The uncertainty in the information source values is taken into account by entropy function, based on which gait information image (GII) is derived from a gait cycle. For this purpose a new GII based feature named bipolar sigmoid feature (GII-BPSF) is proposed. Moreover, to address the problem of orientation normalization for different view angles, a modified pre-processing method is adapted from the study of He et al. (The role of size normalization on the recognition rate of handwritten numerals, 2005) to verify the robustness of the proposed features, experiments were carried out on CASIA (Institute of Automation, Chinese Academy of Sciences) dataset B with a wide range of subject variation, different clothing patterns, and carrying conditions. The experimental results show that the proposed GII-BPSF is a more efficient gait representation and feature for an individual recognition and the obtained identification rates are higher concerning the previously established gait recognition approaches.Item The fusion of multispectral palmprints using the information set based features and classifier(Elsevier, 2018) Grover, JyotsanaThis 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.Item Personal identification using the rank level fusion of finger-knuckle-prints(Springer, 2017-03) Grover, JyotsanaThis 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.Item New evolutionary optimization method based on information sets(Springer, 2018-03) Grover, JyotsanaThis paper proposes a new evolutionary learning method without any algorithmic-specific parameters for solving optimization problems. The proposed method gets inspired from the information set concept that seeks to represent the uncertainty in an effort using an entropy function. This method termed as Human Effort For Achieving Goals (HEFAG) comprises two phases: Emulation and boosting phases. In the Emulation phase the outcome of the best achiever is emulated by each contender. The effort associated with the average outcome and best outcome are converted into information values based on the information set. In the Boosting phase the efforts of all contenders are boosted by adding the differential information values of any two randomly chosen contenders. The proposed method is tested on benchmark standard functions and it is found to outperform some well-known evolutionary methods based on the statistical analysis of the experimental results using the Kruskal-Wallis statistical test and Wilcoxon rank sum test.Item Novel competitive-cooperative learning models (cclms) based on higher order information sets(Springer, 2020-09) Grover, JyotsanaThis paper presents two novel competitive-cooperative learning models (CCLM) for achieving goals by human contenders. These models have two phases, viz., Competition phase and Cooperation phase. CCLM based on Hanman Transform (HT) is called HT-CCLM and that using a new concept termed Pervasive Information set is called PIS-CCLM. In the competition phase of HT-CCLM, each contender emulates the effort of best achiever by taking the difference of Hanman Transform values associated with the efforts of an individual and the best achiever whereas in the cooperation phase the differential of HT values of efforts of two random contenders is considered. In PIS-CCLM pervasive information value obtained from hesitancy values are used in the competition phase only. We have also carried out Wilcoxon test to establish the superiority of the proposed HT-CCLM and PIS-CCLM.