Iris Recognition Method Based on Feature Discrimination and Category Correlation

Abstract:

With the increasing number of internet user, the authentication technology is more and more important. Iris recognition as an important method for identification, which has been attention by researchers. In order to improve the predictive accuracy of iris recognition algorithm, the iris recognition method is proposed based feature discrimination and category correlation. The feature discrimination and category correlation are calculated by laplacian score and mutual information. The formula about feature discrimination and category correlation are built. Aiming at texture characteristic of iris image, the multi-scale circular Gabor filter is used to feature extraction. The computational efficiency of algorithm is improved. In order to verify the validity of the algorithm, the CASIA iris database of Chinese Academy of Sciences is used to do the experiment. The experimental results show that our method has high predictive accuracy.

• Periodical: Applied Mechanics and Materials (Volumes 602-605)
• Pages: 1610-1613
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.602-605.1610
• Online since: August 2014
• Authors: Ming Hai Yao*, Na Wang, Jin Song Li
• Keywords: Discrimination, Feature Selection, Iris Recognition, Mutual Information (MI), Relevance

References

[1] Jing Li, Jian Cao, Kaixuan Lu, AImprove the two-phase test samples representation method for palmprint recognition, Optik - International Journal for Light and Electron Optics, vol. 124, no. 24, pp.6651-6656, (2013).

DOI: 10.1016/j.ijleo.2013.05.110

[2] R. Szewczyk, K. Grabowski, M. Napieralska, W. Sankowski, M. Zubert, A. Napieralski, A reliable iris recognition algorithm based on reverse biorthogonal wavelet transforms, Pattern Recognition Letters, vol. 33, no. 8, pp.1019-1026, (2012).

DOI: 10.1016/j.patrec.2011.08.018

[3] Himanshu Rai, Anamika Yadav, Iris recognition using combined support vector machine and Hamming distance approach, Expert Systems with Applications, vol. 41, no. 2, pp.588-593, (2014).

DOI: 10.1016/j.eswa.2013.07.083

[4] Kien Nguyen, Clinton Fookes, Sridha Sridharan, Simon Denman, Feature domain super-resolution for iris recognition, Computer Vision and Image Understanding, vol. 117, no. 10, pp.1526-1535, (2013).

DOI: 10.1016/j.cviu.2013.06.010

[5] Ferhat Kurtulmus, Won Suk Lee, Ali Vardar, Green citrus detection using 'eigenfruit', color and circular Gabor texture features under natural outdoor conditions, Computers and Electronics in Agriculture, vol. 78, no. 2, pp.140-149, (2011).

DOI: 10.1016/j.compag.2011.07.001

[6] He, X., Cai D., Niyogi P., Laplacian score for feature selection. Advances in Nerual Information Processing Systems, Cambridge Ma MIT Press, (2005).

[7] Ding, J. R., Huang, J. H. J., Liu, F. et al., Elastogram features selection and classification based on MRMR and SVM, Journal of Harbin Institute of Technology, vol. 44, no. 5, pp.81-85, (2012).

[8] CASIA-IrisV1[DB/OL]. http: /www. cbsr. ia. ac. cn/IrisDatabase. htm, (2004).

[9] Chih-Chung Chang, Chih-Jen Lin, a library for support vector machimes, http: /www. csie. ntu. edu. tw/~cjlin/libsvm. (2013).