Latent Palm Fused with Fingerprint to Improve Authentication Performance
Karthikeyani. K, Thangasamy. S and Latha. L. Article: Latent Palm Fused with Fingerprint to Improve Authentication Performance. IJCA Proceedings on Machine Learning: Challenges and Opportunities Ahead MLCONF:1-5, April 2014. Full text available. BibTeX
@article{key:article,
author = {Karthikeyani. K and Thangasamy. S and Latha. L},
title = {Article: Latent Palm Fused with Fingerprint to Improve Authentication Performance},
journal = {IJCA Proceedings on Machine Learning: Challenges and Opportunities Ahead},
year = {2014},
volume = {MLCONF},
pages = {1-5},
month = {April},
note = {Full text available}
}
Abstract
Biometric Authentication systems adopt a suitable image processing technique to manipulate the biometric images. It refers to verifying a person using their biometric traits that includes physiological, biological and/or behavioral traits like iris, face, fingerprint, voice, hand writing etc. , A biometric characteristic should be unique, universal, permanent and acceptable. In this work, the texture feature of palm and finger print extracted using Gabor filter and fusion is done by concatenation. The high dimensionality of fused features are reduced using ant colony optimization(ACO) algorithm and finally only the most significant features are used for classification of genuine and imposter users. Any two-class classifier can be used for classification. Three classifiers namely a SVM classifier with Linear and RBF kernels and NC (Normalized Correlation) are used for classification and the results were compared. A classification accuracy of 98. 6% is discussed in literature for high resolution scanner images. The least Total Error ever reported in literature is 7. 94% [12] This work aims at improving the accuracy of classification of the authentication system with noisy samples, while reducing the Total Error (TE), False Acceptance Rate (FAR), False Rejection Rate (FRR) and Equal Error Rate (EER). For evaluation of the system a real time database was constructed with a finger and palm print scanner. The database consists of four samples each for an individual.
References
- K. Krishneswari, S. Arumugam, "An improved Genetic Optimized neural network for multimodal biometrics", In JSIR, Vol. 72, pp. 23-30 (2013).
- R. Ragavendra, B. Dorizzi, Ashok Rao, G. Hemantha Kumar, "Designing efficient fusion schemes for multimodal biometric systems using face and palm print", Pattern Recognition, Elsevier, Vol. 44, pp. 1076-1088 (2011).
- G. M. Lu, D. Zhang, K. Q. Wang, "Palm print recognition using Eigen palms features", Pattern Recognition Letters,24(9-10) ,pp. 1463-1467, 2002
- . Mink . A, R. Snelick, U. Uludag, M. Indovina, and A. Jain, "Large scale evaluation of Multimodal Authentication Using State-of-the –Art Systems", IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, Vol. 27, No. 3, pp. 450-455
- M. Hemandhalu et. al,"Fusion of hand based biometrics using Particle Swarm Optimization" Proc. IEEE, 2008. The IEEE website. [Online]. Available: http://www. ieee. org/
- . Krishneswari,S. Arumugam,"An Improved Genetic Optimized Neural network for multimodal Biometrics ", In JSIR, Vol. 72,2013. pp-23-30.
- Qian Tao et. al,"Threshold optimized decision-level fusion and its applications to biometrics", Pattern Recognition in Elsevier, Vol. 42,2009. pp. 823-836.
- Yanmin Gong et. al,"Quasi-convex optimization of Metrics in Biometric Score Fusion",Sixth International Conference on Image and Graphics,IEEE 2011.
- Norman Poh and Josef Kittler,"On Using Error Bounds to Optimize Cost-Sensitive Multimodal Biometric Authentication",IEEE,2008. The IEEE website. [Online]. Available: http://www. ieee. org/
- Tobias Scheidat , "Parameter Optimization for Biometric Fingerprint Recognition using Genetic algorithm",In International conference on MM&Sec,Geneva,Switzerland. ACM,2006.
- Z. Guo, D. Zhang and W. Li , "Palmprint verification using Binary orientation co-occurrence Vector", Pattern Recognition Letters, vol. 30, No. 13, 2009. pp. 1219-1227.
- Dakshina Ranjan Kisku ," Human Identity Verification Using Multispectral Palm print Fusion",JSIP,vol. 3 ,2012. pp. 263-273 pp. 1076-1088.
- C. J. C. Burges, "A Tutorial on Support Vector Machines for Pattern Recognition", Data Mining and knowledge Discovery, Vol. 2, No. 2, 1998, pp. 121-167.
- Chang-Chun Lin, Lu-Chan Tseng, Website reorganization using an ant colony system, Expert System with Applications, Vol. 37, 2010, pp. 7598-7605,
- Prabhakar. S, Pankanti. S, A. K. Jain, Biometric Recognition: Security and Privacy Concerns, IEEE Security & Privacy, 2003, pp. 33-42.
- Kittler. J, Hatef. M, Diun. R, Maatas. J, "On combining classifiers", IEEE Trans on Pattern Analysis and Machine Intelligence. vol. 20, 1998.
- Jain A. K, S. Prabhakr, A. Ross,"An Introduction to biometric Recognition", IEEE Trans. Circuits' System Video Technol. , Vol. 14, 2004, pp. 4-20 (A special on video and image-based biometric systems).
- . C. Bergamini, "Combining different biometric traits with one-class classification", Signal Processing, Vol. 89, 2009, pp. 2117- 2127.
- CASIA Palm print database, (2007). Available on: http://www. sinobiometrics. com
- BIT Finger print database , (2011) . Available on: http://www. biometrics. idealtest. org.