A Multi-Level Integrator with Programming Based Boosting for Person Authentication Using Different Biometrics
1
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
A multiple classification system based on a new boosting technique has been approached utilizing differentbiometric traits, that is, color face, iris and eye along with fingerprints of right and left hands, handwriting,palm-print, gait (silhouettes) and wrist-vein for person authentication. The images of different biometrictraits were taken from different standard databases such as FEI, UTIRIS, CASIA, IAM and CIE. This system iscomprised of three different super-classifiers to individually perform person identification. The individualclassifiers corresponding to each super-classifier in their turn identify different biometric features and theirconclusions are integrated together in their respective super-classifiers. The decisions from individual superclassifiersare integrated together through a mega-super-classifier to perform the final conclusion usingprogramming based boosting. The mega-super-classifier system using different super-classifiers in a compactform is more reliable than single classifier or even single super-classifier system. The system has beenevaluated with accuracy, precision, recall and F-score metrics through holdout method and confusion matrixfor each of the single classifiers, super-classifiers and finally the mega-super-classifier. The differentperformance evaluations are appreciable. Also the learning and the recognition time is fairly reasonable. Thereby making the system is efficient and effective.
Abstract
A multiple classification system based on a new boosting technique has been approached utilizing differentbiometric traits, that is, color face, iris and eye along with fingerprints of right and left hands, handwriting,palm-print, gait (silhouettes) and wrist-vein for person authentication. The images of different biometrictraits were taken from different standard databases such as FEI, UTIRIS, CASIA, IAM and CIE. This system iscomprised of three different super-classifiers to individually perform person identification. The individualclassifiers corresponding to each super-classifier in their turn identify different biometric features and theirconclusions are integrated together in their respective super-classifiers. The decisions from individual superclassifiersare integrated together through a mega-super-classifier to perform the final conclusion usingprogramming based boosting. The mega-super-classifier system using different super-classifiers in a compactform is more reliable than single classifier or even single super-classifier system. The system has beenevaluated with accuracy, precision, recall and F-score metrics through holdout method and confusion matrixfor each of the single classifiers, super-classifiers and finally the mega-super-classifier. The differentperformance evaluations are appreciable. Also the learning and the recognition time is fairly reasonable. Thereby making the system is efficient and effective.
참고문헌 (36)
- R. Bhati, "A comparative analysis of different neural networks for face recognition using principal component analysis, wavelets and efficient variable learning rate", Proceedings of International Conference on Computer and Communication Technology, pp.526~531 (2010)
- H. Boughrara, "MLP neural network based face recognition system using constructive training algorithm", Proceedings of International Conference on Multimedia Computing and Systems, pp.233~238 (2012)
- S. H. Moi, "A unified approach for unconstrained off-angle iris recognition", Proceedings of International Symposium on Biometrics and Security Technologies, pp.39~44 (2014)
- Z. Lin, "Iris recognition method based on the imaginary coefficients of Morlet wavelet transform", Proceedings of the 7th International Conference on Fuzzy Systems and Knowledge Discovery, pp.573~577 (2010)
- J. Luo, "An improved fingerprint recognition algorithm using EBFNN", Proceedings of the 2nd International Conference on Genetic and Evolutionary Computing, pp.504~507 (2008)
- C. Yu, "A novel principal component analysis neural network algorithm for fingerprint recognition in online examination system", Proceedings of Asia-Pacific Conference on Information Processing, pp.182~186 (2009)
- C. Anton, "Identify handwriting individually using feed forward neural networks", International Journal of Intelligent Computing Research, 1(4), pp.183~188 (2010)
- J. Ashok, "Off-line hand written character recognition using radial basis function", Advanced Networking and Applications, 2(4), pp.792~795 (2011)
- H. Imtiaz, "Palm-print Recognition based on DCT domain statistical features extracted from enhanced image", Proceedings of International Conference on Electrical Engineering and Information & Communication Technology, pp.1~4 (2014)
- A. George, "An efficient system for palm print recognition using ridges", Proceedings of International Conference on Intelligent Computing Applications, pp.249~253 (2014)
- W. Zeng, "View-invariant gait recognition via deterministic learning", Neurocomputing, 175, pp.324~335 (2016)
- S. M. Lajevardi, "Hand vein authentication using biometric graph matching", IET Biometrics, 3(4), pp.302~313 (2014)
- Y. Wang, "Personal identification based on multiple keypoint sets of dorsal hand vein images", IET Biometrics, 3(4), pp.234~245 (2014)
- R. L. Telgad, "Combination approach to score level fusion for Multimodal Biometric system by using face and fingerprint", Proceedings of International Conference on Recent Advances and Innovations in Engineering, pp.1~8 (2014)
- M. S. Almohammad, "Human identification system based on feature level fusion using face and gait biometrics", Proceedings of International Conference on Engineering and Technology, pp.1~5 (2012)
- U. Gawande, "Fingerprint and Iris fusion based recognition using RBF neural network", Journal of Signal and Image Processing, 4(1), pp.142~148 (2013)
- J. Lin, "Robust person identification with face and iris by modified PUM method", Proceedings of International Conference on Apperceiving Computing and Intelligence Analysis, pp.321~324 (2009)
- D. P. Gaikwad, "Multi-modal biometric system using palm print and palm vein features", Proceedings of 2013 Annual IEEE India Conference (INDICON), pp.1~5 (2013)
- E. Perumal, "A multimodal biometric system based on palmprint and finger knuckle print recognition methods", The International Arab Journal of Information Technology, 12(2), pp.118~128 (2015)
- S. Chaudhary, "A new multimodal biometric recognition system integrating iris, face and voice", International Journal of Advanced Research in Computer Science and Software Engineering, 5(4), pp.145~150 (2015)
- J. Huang, "A novel iris segmentation using radial-suppression edge detection", Signal Processing, 89(12), pp.2630~2643 (2009)
- V. Conti, "A frequency-based approach for features fusion in fingerprint and iris multimodal biometric identification systems", IEEE Transactions on Systems, Man, and Cybernetics Part C(Applications and Reviews), 40(4), pp.384~395 (2010)
- S. Kundu, "Intelligent Computing and Applications", pp.11~18 (2014), Springer
- G. Sarker, "A modified radial basis function network for fingerprint identification and localization", Proceedings of International Conference on Advanced Engineering and Technology, pp.26~31 (2013)
- S. Kundu, "A modified radial basis function network for occluded fingerprint identification and localization", International Journal of Computers Information Technology and Engineering, 7(2), pp.103~109 (2013)
- S. Kundu, "A modified RBFN based on heuristic based clustering for location invariant fingerprint recognition and localization with and without occlusion", Proceedings of International Conferences for Convergence of Technology, pp.1~6 (2014)
- S. Kundu, "A new RBFN with modified optimal clustering algorithm for clear and occluded fingerprint identification", Proceedings of the 2nd International Conference on Control, Instrumentation, Energy and Communication, pp.125~129 (2016)
- G. Sarker, "An optimal clustering for fuzzy categorization of cursive handwritten text with weight learning in textual attributes", Proceedings of the 2nd International Conference on Recent Trends in Information Systems, pp.6~11 (2015)
- S. Kundu, "A modified BP network using Malsburg learning for rotation and location invariant fingerprint recognition and localization with and without occlusion", Proceedings of the 7th International Conference on Contemporary Computing, pp.617~623 (2014)
- G. Sarker, "An optimal backpropagation network for face identification and localization", International Journal of Computers and Applications, 35(2), pp.63~69 (2013)
- G. Sarker, "An unsupervised natural clustering with optimal conceptual affinity", Journal of Intelligent Systems, 19(3), pp.289~300 (2010)
- G. Sarker, "An RBF network with optimal clustering for face identification", Engineering Science International Research Journal, 1(1), pp.70~74 (2013)
- G. Sarker, "A modified RBF network with optimal clustering for face identification and localization", International Journal of Advanced Computational Engineering and Networking, 1(3), pp.30~35 (2013)
- S. Kundu, "A person identification system with biometrics using modified RBFN based multiple classifiers", Proceedings of International Conference on Intelligent Computing and Communication, pp.415~424 (2016)
- S. Kundu, "An efficient integrator based on template matching technique for person authentication using different biometrics", Indian Journal of Science and Technology, 9(42) (2016)
- G. Sarker, "A weight learning technique for cursive handwritten text categorization with fuzzy confusion matirx", Proceedings of the 2nd International Conference on Control, Instrumentation, Energy &Communication, pp.188~192 (2016)