Isaac Scientific Publishing

Frontiers in Signal Processing

Research on Human Eye Iris Recognition Based on Inception v3

Download PDF (538.3 KB) PP. 63 - 68 Pub. Date: October 15, 2019

DOI: 10.22606/fsp.2019.34001

Author(s)

  • Yuewen Tang*
    Southwest Minzu University, ChengDu, China
  • Xiangkui Li
    Southwest Minzu University, ChengDu, China
  • Yulian Jiang
    Southwest Minzu University, ChengDu, China

Abstract

Iris recognition has certain application prospects in access control systems, financial fields, and airport security. Before the appearance of the deep learning method, the iris recognition method relies on artificial method for feature extraction. This method will consume a lot of time and affect the efficiency of recognition. In this recognition study, we adopt the method of deep learning. On the basis of a large amount of image data and the guarantee of computer computing ability, in order to exceed the iris recognition accuracy of previous recognition methods.In this paper, the improved Inception v3 model is used to classify and recognize the iris database provided by the Chinese Academy of Sciences in the Tensorflow framework. Finally, the accuracy of image recognition can reach 98% through the training of the model.

Keywords

Inception v3, Tensorflow, iris recognition.

References

[1] Deng L,Yu D.Deep learning:methods and applications[J].Foundations and Trends in Signal Processing, 2014, 7(3-4):197-387.

[2] Schmidhuber J.Deep learning in neural networks: An overview[J].Neural networks,2015,61:85 一117.

[3] Li H.Deep learning for natural language processing: advantages and challenges[J]. National Science Review, 2017,51(1):24-26.

[4] Harmon L D, Khan M K, Lasch R, et al. Machine identification of human faces[J]. Pattern Recognition, 1981, 13(2):97-110.

[5] Ding C, Tao D. Trunk-branch ensemble convolutional neural networks for video-based face recognition[J].IEEE transactions on pattern analysis and machine intelligence, 2017, 40(4):1002-1014.

[6] Wang F Y,Zhang J J, Zheng X,et al.Where does A1phaGo go: From church-turing thesis to A1phaGo thesis and beyond[J].IEEE/CAA Journal of Automatic Sinica,2016,3(2):113-120.