Deep-Learning Based Joint Iris and Sclera Recognition with YOLO Network for Identity Identification

By jointly consideration of the partial iris and sclera region, no sclera and iris separation calculation is needed, and both of the sclera and iris information is used at the same time, and then the identity information is enhanced to avoid being forged. By the deep learning based YOLOv2 model, the visible-light eye images are marked with the jointly partial iris and sclera region, and the identity classifier is trained to inference the correct personal identity. By using the self-made and visible-light eye image database to evaluate the system performance, the proposed deeplearning based joint iris and sclera recognition reaches the mean Average Precision (mAP) up to 99%. Besides, compared with the previous works, the proposed design is more effective without using any iris and sclera segmentation process.

[1]  Edward J. Delp,et al.  A New Human Identification Method: Sclera Recognition , 2012, IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans.

[2]  Ali Farhadi,et al.  YOLO9000: Better, Faster, Stronger , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Eliza Yingzi Du,et al.  An Efficient Parallel Approach for Sclera Vein Recognition , 2014, IEEE Transactions on Information Forensics and Security.

[4]  Chih-Peng Fan,et al.  Sclera Recognition by Density Sampling Features Based Vascular Structure Rapid Matching for Identity Identification , 2018, 2018 IEEE 7th Global Conference on Consumer Electronics (GCCE).

[5]  Ali Farhadi,et al.  YOLOv3: An Incremental Improvement , 2018, ArXiv.

[6]  John Daugman,et al.  How iris recognition works , 2002, IEEE Transactions on Circuits and Systems for Video Technology.

[7]  Saurabh Maheshwari,et al.  Contrast limited adaptive histogram equalization based enhancement for real time video system , 2014, 2014 International Conference on Advances in Computing, Communications and Informatics (ICACCI).

[8]  Ali Farhadi,et al.  You Only Look Once: Unified, Real-Time Object Detection , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Miguel Angel Ferrer-Ballester,et al.  Sclera recognition using dense-SIFT , 2013, 2013 13th International Conference on Intellient Systems Design and Applications.

[10]  Wai Lok Woo,et al.  Robust Sclera Recognition System With Novel Sclera Segmentation and Validation Techniques , 2017, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[11]  Chin-Wang Tao,et al.  Iris Recognition Using Gabor Filters and the Fractal Dimension , 2009, J. Inf. Sci. Eng..

[12]  Yoshimitsu Kuroki,et al.  Sift feature point selection by using image segmentation , 2017, 2017 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS).

[13]  Banshidhar Majhi,et al.  Unconstrained iris recognition using F-SIFT , 2011, 2011 8th International Conference on Information, Communications & Signal Processing.

[14]  Peter M. Corcoran,et al.  Biometrics and Consumer Electronics: A Brave New World or the Road to Dystopia? [Soapbox] , 2013, IEEE Consumer Electronics Magazine.

[15]  Chih-Peng Fan,et al.  Effective Scale-Invariant Feature Transform Based Iris Matching Technology for Identity Identification , 2018, 2018 IEEE International Conference on Consumer Electronics-Taiwan (ICCE-TW).

[16]  Pradeep M. Patil,et al.  The Comparison of Iris Recognition using Principal Component Analysis, Log Gabor and Gabor Wavelets , 2012 .