Computational Methodology for Iris Segmentation and Detection in Images from the Eyes Region Using Convolutional Neural Networks
Eye tracking is an application of computer vision responsible for detecting the iris and pupil in the eye region. The usefulness of this tracking contributes to research that assesses cognitive aspects through pupillary reactions identified in these detected regions. Another application in this task is iris recognition in digital biometrics. This study aims to carry out the verification and detection of the iris in images of the eye region occluded by eyelashes, eyelids and specular reflexes, through a deep neural network called At-Unet in this article. In order to assist in eye tracking this method achieves 95.32 % of data coefficient when segmenting the iris of the eyes, indicating the efficiency of this methodology.
Gomai, A. El-Zaart and H. Mathkour, ”A new approach for pupil detection in iris recognition system,” 2010 2nd International Conference on Computer Engineering and Technology, 2010, pp. V4-415-V4-419.
J. Daugman, ”New Methods in Iris Recognition,” in IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), vol. 37, no. 5, pp. 1167-1175, Oct. 2007.
Liu, H. Li, M. Zhang, Jing Liu, Z. Sun and T. Tan, ”Accurate iris segmentation in non-cooperative environments using fully convolutional networks,” 2016 International Conference on Biometrics (ICB), 2016, pp. 1-8.
Arsalan, Muhammad Kim, Dong Lee, Min Owais, Muhammad Kang, Ryoung. (2019). FRED-Net: Fully Residual Encoder-Decoder Network for Accurate Iris Segmentation. Expert Systems with Applications. 122. 10.1016/j.eswa.2019.01.010
Hofbauer Heinz, Jalilian, Ehsaneddin, Uhl Andreas. (2018). Exploiting Superior CNN-based Iris Segmentation for Better Recognition Accuracy. Pattern Recognition Letters. 120. 10.1016/j.patrec.2018.12.021.
C. Wang, J. Muhammad, Y. Wang, Z. He and Z. Sun, ”Towards Complete and Accurate Iris Segmentation Using Deep Multi-Task Attention Network for Non-Cooperative Iris Recognition,” in IEEE Transactions on Information Forensics and Security, vol. 15, pp. 2944-2959, 2020.
A. Elhassouny and F. Smarandache, ”Trends in deep convolutional neural Networks architectures: a review,” 2019 International Conference of Computer Science and Renewable Energies (ICCSRE), 2019, pp. 1-8.
R. Chauhan, K. K. Ghanshala and R. C. Joshi, ”Convolutional Neural Network (CNN) for Image Detection and Recognition,” 2018 First International Conference on Secure Cyber Computing and Communication (ICSCCC), 2018, pp. 278-282.
R.Olaf, F.Philipp, B.Thomas. (2015). U-Net: Convolutional Networks for Biomedical Image Segmentation.
R. El Jurdi, C. Petitjean, P. Honeine and F. Abdallah, ”BB-UNet: U-Net With Bounding Box Prior,” in IEEE Journal of Selected Topics in Signal Processing, vol. 14, no. 6, pp. 1189-1198, Oct. 2020.
W. Zhang, X. Lu, Y. Gu, Y. Liu, X. Meng, and J. Li, “A robust iris segmentation scheme based on improved U-Net.
Simonyan, Karen Zisserman, Andrew. (2014). Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv 1409.1556.
J. Deng, W. Dong, R. Socher, L. Li, Kai Li and Li Fei-Fei, ”ImageNet: A large-scale hierarchical image database,” 2009 IEEE Conference on Computer Vision and Pattern Recognition, 2009, pp. 248-255.
Triyani, Yuli Nugroho, Hanung Adi Rahmawaty, Made Ardiyanto, Igi Choridah, Lina. (2016). Performance analysis of image segmentation for breast ultrasound images. 1-6.
Li, Yung-Hui, Wenny R. Putri, Muhammad S. Aslam, and Ching-Chun Chang. 2021. ”Robust Iris Segmentation Algorithm in Non-Cooperative Environments Using Interleaved Residual U-Net” Sensors 21, no. 4: 1434.