COMPUTER VISION TECHNOLOGIES TO IMPROVE THE IMAGE QUALITY OF THE IRIS
DOI:
https://doi.org/10.5281/zenodo.22840549Abstract
The article addresses the problem of improving the quality of eye region images in computer vision systems for biometric identification. A multi-stage image processing algorithm is proposed that includes face detection, localization of the eye region, extraction of the pupil and iris, segmentation of biometrically significant areas, and image quality enhancement by filtering, normalization and contrast enhancement. The main attention is paid to increasing the information content of the textural features of the iris and the periocular region in images obtained from conventional surveillance cameras under low light, noise, blur and limited resolution. The novelty of the work lies in combining glare removal, local contrast enhancement and neural network super-resolution in a single preprocessing pipeline for ordinary RGB cameras. Experimental results show that the proposed approach improves the quality of visual data and the extraction of biometric features and increases the effectiveness of subsequent identification.Keywords
computer vision, biometric identification, iris, periocular region, image processing, segmentation, image quality improvement, video surveillance, feature extraction, multimodal biometricsReferences
Daugman, J. (2004). How iris recognition works. IEEE Transactions on Circuits and Systems for Video Technology, 14(1), 21–30. https://doi.org/10.1109/TCSVT.2003.818350
Proença, H., & Alexandre L., A. (2005). UBIRIS: A noisy iris image database. Image Analysis and Processing, 3617, 970–977. https://doi.org/10.1007/11553595_119
Bowyer K., W., Hollingsworth, K., & Flynn P., J. (2008). Image understanding for iris biometrics: A survey. Computer Vision and Image Understanding, 110(2), 281–307. https://doi.org/10.1016/j.cviu.2007.08.005
Nguyen, K., Fookes, C., Ross, A., & Sridharan, S. (2018). Iris recognition with off-the-shelf CNN features: A deep learning perspective. IEEE Access, 6, 18848–18855. https://doi.org/10.1109/ACCESS.2017.2784352
Zhao, Z., & Kumar, A. (2017). Towards more accurate iris recognition using deeply learned spatially corresponding features. Proceedings of the IEEE International Conference on Computer Vision (ICCV), 3829–3838. https://doi.org/10.1109/ICCV.2017.411
Nguyen, K., Proença, H., & Alonso-Fernandez, F. (2024). Deep learning for iris recognition: A survey. ACM Computing Surveys, 56(9), 1–35. https://doi.org/10.1145/3651306
Yin, Y., He, S., Zhang, R., Chang, H., & Zhang, J. (2025). Deep learning for iris recognition: A review. Neural Computing and Applications, 37(17), 11125–11173. https://doi.org/10.1007/s00521-025-11109-5
Tapia J., E., Gonzalez, S., & Busch, C. (2022). Iris liveness detection using a cascade of dedicated deep learning networks. IEEE Transactions on Information Forensics and Security, 17, 42–52. https://doi.org/10.1109/TIFS.2021.3132582
Park, U., Ross, A., & Jain A., K. (2009). Periocular biometrics in the visible spectrum: A feasibility study. 2009 IEEE 3rd International Conference on Biometrics: Theory, Applications, and Systems (BTAS), 1–6. https://doi.org/10.1109/
Viola, P., & Jones, M. (2001). Rapid object detection using a boosted cascade of simple features. Proceedings of the, 1. https://doi.org/10.1109/CVPR.2001.990517
Lugaresi, C., Tang, J., Nash, H., McClanahan, C., Uboweja, E., Hays, M., Zhang, F., & Chang, C. (2019). -L., Yong M. G., Lee J., Chang W.-T., Hua W., Georg M., Grundmann M. MediaPipe: A framework for building perception pipelines [Electronic resource]. 1906.08172.
Zuiderveld, K. (1994). Contrast limited adaptive histogram equalization. Graphics Gems IV / ed. by P. S. Heckbert, 474–485. https://doi.org/10.1016/B978-0-12-336156-1.50061-6
Wang, X., Yu, K., Wu, S., Gu, J., Liu, Y., Dong, C., Qiao, Y., & Loy C., C. (2018). ESRGAN: Enhanced super-resolution generative adversarial networks. Computer Vision, 11133, 63–79. https://doi.org/10.1007/978-3-030-11021-5_5
Wang, X., Xie, L., Dong, C., & Shan, Y. (2021). Real-ESRGAN: Training real-world blind super-resolution with pure synthetic data. Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), 1905–1914. https://doi.org/10.1109/ICCVW54120.2021.00217
Alzubi, J., Nayyar, A., & Kumar, A. (2018). Machine learning from theory to algorithms: An overview. Journal of Physics: Conference Series, 1142. https://doi.org/10.1088/1742-6596/1142/1/012012
OpenCV Documentation. Open Source Computer Vision Library [Electronic resource]. – URL: https://docs.opencv. org/4.x/ (accessed: 17.09.2026).
Downloads
Published
How to Cite
Issue
Section
