Iris recognition based on sectors

被引：0

作者：

Yang S. ^{[1
]}

Wu X. ^{[1
]}

Karn P. ^{[1
]}

He X. ^{[1
]}

机构：

[1] College of Electronics and Info. Eng., Sichuan Univ., Chengdu

来源：

Wu, Xiaohong (wxh@scu.edu.cn) | 1600年 / Sichuan University卷 / 48期

关键词：

Bayesian fusion; Iris recognition; Low-rank matrix; Sparse representation;

D O I：

10.15961/j.jsuese.2016.s1.022

中图分类号：

学科分类号：

摘要：

In order to improve the correct recognition rate for poor quality iris images, a sectored-based method for iris recognition was proposed. Not like the conventional recognition method, the algorithm divided the iris image into different sectors, recognized different sectors separately and combined their results using Bayesian fusion based on sparsity concentration index value. The low-rank matrix of each sector was selected as iris feature, and sparse representation based classification was used as classifier. Because different regions of the iris had different qualities, the algorithm can reduce the impact of poor quality regions on the recognition result. Experiment results on CASIA-Iris-Interval and IIT Delhi V1 iris database showed that the proposed algorithm has better correct recognition rate and strong robustness for poor quality iris images. The studies of the number of sectors and training images demonstrated that the eight of the sector number is suitable and a test iris image could be well represented by seven training images from the same class. © 2016, Editorial Department of Journal of Sichuan University (Engineering Science Edition). All right reserved.

引用

页码：150 / 156

页数：6

共 22 条

[1]

Jain A.K., Rose A., Prabhakar S., An introduction to biometric recognition, IEEE Transactions on Circuits and System for Video Technology, 14, 1, pp. 4-20, (2004)

[2]

Adler F.H., Physiology of the eye: Clinical application, AMA Arch Ophthalmol, 45, 5, pp. 612-614, (1951)

[3]

Daugman J., High confidence visual recognition of persons by a test of statistical independence, IEEE Transactions on Pattern Analysis and Machine Intelligence, 15, 11, pp. 1148-1161, (1993)

[4]

Wildes R.P., Iris recognition: An emerging biometric technology, Proceeding of the IEEE, 85, 9, pp. 1348-1363, (1997)

[5]

Daugman J., Probing the uniqueness and randomness of iris codes: Results from 200 billion iris pair comparisons, Proceedings of the IEEE, 94, 11, pp. 1927-1935, (2006)

[6]

Proenca H., Alexandre L.A., Iris segmentation methodology for non-cooperative recognition, IEE Proceedings-Vision, Image and Signal Processing, 153, 2, pp. 199-205, (2006)

[7]

Li P., Ma H., Iris recognition in non-ideal imaging conditions, Pattern Recognition Letters, 33, 8, pp. 1012-1018, (2012)

[8]

Pillai J.K., Patel V.M., Chellappa R., Sparsity inspired selection and recognition of iris images, Biometrics: Theory, Applications, and Systems (BTAS), pp. 1-6, (2009)

[9]

Karn P., He X., Yang S., Et al., Iris recognition based on robust principal component analysis, Journal of Electronic Imaging, 23, 6, (2014)

[10]

Candes E.J., Li X.D., Ma Y., Et al., Robust principal component analysis, Journal of the ACM, 58, 3, (2011)

← 1 2 3 →