An Improved Method for Human Identification Based on Iris Recognition Using Hybrid Convolutional Neural Networks and Grey Wolf Optimization

Subject Areas : Artificial Intelligence Tools in Software and Data Engineering

Israa Turki Atiyah ¹ , zahra rezaei ²

1 - 1Department of Computer Engineering, Isfahan (Khorasgan) Branch, Islamic Azad University, Isfahan, Iran
2 - Department of Computer Engineering, Marvdasht Branch, Islamic Azad University, Marvdasht, Iran

Received: 2024-09-08 Accepted : 2025-05-13 Published : 2025-09-22

Keywords: CNN algorithms, GWO technique, feature selection, CASIA.,

Abstract :

     Identifying a person through the iris is important in the security and medical fields. Biometric engineering image processing has a crucial application in iris facial recognition. This paper proposes the suggested Grey Wolf Optimizer-Convolutional Neural Networks (GWO-CNN) technique. The SVM algorithm was used for selecting the best GWO features. The proposed algorithm was performed on several standard datasets. The proposed GS-CNN technique demonstrates the performance of experimental evaluation on the CASIA database. The results show that the proposed GS-CNN technique outperforms other classifiers, achieving the highest accuracy of 98% on the CASIA-V1 dataset and 96% on the CASIA-Iris-Interval dataset. This highlights the effectiveness of the GS-CNN approach in iris recognition tasks.

 

References:


[1] Banaie-Dezfouli, M., M.H. Nadimi-Shahraki, and Z. Beheshti, R-GWO: Representative-based grey wolf optimizer for solving engineering problems. Applied Soft Computing, 2021. 106: p. 107328.
[2] Mirjalili, S., S.M. Mirjalili, and A. Lewis, Grey wolf optimizer. Advances in engineering software, 2014. 69: p. 46-61.
[3] Meng, X., J. Jiang, and H. Wang, AGWO: Advanced GWO in multi-layer perception optimization. Expert Systems with Applications, 2021. 173: p. 114676.
[4] Zhao, Z. and A. Kumar. Towards more accurate iris recognition using deeply learned spatially corresponding features. in Proceedings of the IEEE international conference on computer vision. 2017.
[5] Arsalan, M., et al., Deep learning-based iris segmentation for iris recognition in visible light environment. Symmetry, 2017. 9(11): p. 263.
[6] Karakaya, M. Deep learning frameworks for off-angle iris recognition. in 2018 IEEE 9th International Conference on Biometrics Theory, Applications and Systems (BTAS). 2018. IEEE.
[7] Zanlorensi, L.A., et al. The impact of preprocessing on deep representations for iris recognition on unconstrained environments. in 2018 31st SIBGRAPI conference on graphics, patterns and images (SIBGRAPI). 2018. IEEE.
[8] Varkarakis, V., S. Bazrafkan, and P. Corcoran. A deep learning approach to segmentation of distorted iris regions in head-mounted displays. in 2018 IEEE Games, Entertainment, Media Conference (GEM). 2018. IEEE.
[9] Li, Y.-H., P.-J. Huang, and Y. Juan, An efficient and robust iris segmentation algorithm using deep learning. Mobile Information Systems, 2019. 2019.
[10] Khalifa, N.E.M., et al., Deep iris: deep learning for gender classification through iris patterns. Acta Informatica Medica, 2019. 27(2): p. 96.
[11] Liu, M., et al., Fuzzified image enhancement for deep learning in iris recognition. IEEE Transactions on Fuzzy Systems, 2019. 28(1): p. 92-99.
[12] Lozej, J., et al. Influence of segmentation on deep iris recognition performance. in 2019 7th International Workshop on Biometrics and Forensics (IWBF). 2019. IEEE.
[13] Wang, C., et al., Joint iris segmentation and localization using deep multi-task learning framework. arXiv preprint arXiv:1901.11195, 2019.
[14] Sardar, M., S. Banerjee, and S. Mitra, Iris segmentation using interactive deep learning. IEEE Access, 2020. 8: p. 219322-219330.
[15] Thakkar, S. and C. Patel. Iris recognition supported best gabor filters and deep learning cnn options. in 2020 International Conference on Industry 4.0 Technology (I4Tech). 2020. IEEE.
[16] Ben Chaabane, S., R. Harrabi, and H. Seddik, Iris Recognition System Using Advanced Segmentation Techniques and Fuzzy Clustering Methods for Robotic Control. Journal of Imaging, 2024. 10(11): p. 288.
[17] Sarwade, J.M., et al., A novel approach for iris recognition system using genetic algorithm. Journal of Artificial Intelligence and Technology, 2024. 4(1): p. 9-17.
[18] He, S. and X. Li, EnhanceDeepIris Model for Iris Recognition Applications. IEEE Access, 2024.
[19] Zhou, W., et al., Histogram of oriented gradients feature extraction from raw bayer pattern images. IEEE Transactions on Circuits and Systems II: Express Briefs, 2020. 67(5): p. 946-950.
[20] Dalal, N. and B. Triggs. Histograms of oriented gradients for human detection. in 2005 IEEE computer society conference on computer vision and pattern recognition (CVPR'05). 2005. IEEE.