Iris Location and Recognition by Deep-Learning Networks Based Design for Biometric Authorization

In this work, the effective deep-learning network based design is studied for iris biometric authentication. Firstly, the system locates and detects the position of the iris by the YOLO based deep-learning detector, and then it strengthens the iris features by histogram equalization. Finally, the iris image is classified by the VGG-16 based model. By the self-made near infrared (NIR) database, the proposed deep-learning based design achieves the recognition accuracies up to 98% at the mode with intruders. Besides the performances of false acceptance rate (FAR) and false rejection rate (FRR) are also evaluated. Compared with the previous studies, the proposed design provides the effective performance of accuracy and does not need the iris segmentation process.

[1]  Thuong Le-Tien,et al.  Iris-based Biometric Recognition using Modified Convolutional Neural Network , 2018, 2018 International Conference on Advanced Technologies for Communications (ATC).

[2]  Chulhee Lee,et al.  Fast Detection of Objects Using a YOLOv3 Network for a Vending Machine , 2019, 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS).

[3]  Weihong Deng,et al.  Very deep convolutional neural network based image classification using small training sample size , 2015, 2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR).

[4]  John Daugman,et al.  High Confidence Visual Recognition of Persons by a Test of Statistical Independence , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Hong-Yuan Mark Liao,et al.  YOLOv4: Optimal Speed and Accuracy of Object Detection , 2020, ArXiv.

[6]  Quoc V. Le,et al.  EfficientDet: Scalable and Efficient Object Detection , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

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

[8]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Shefali Arora,et al.  A Computer Vision System for Iris Recognition Based on Deep Learning , 2018, 2018 IEEE 8th International Advance Computing Conference (IACC).