Görünür Dalgaboyu Ortamlarında Daha İyi İris Segmentasyonu için Göz Renklerinden Yararlanma

Abstract

İris segmentasyonu, iris tanıma sistemlerinde çok önemli bir adımdır. Görünür dalga boyu ve sınırsız ortamlarda iris segmentasyonu, ideal ortamlarda IRIS görüntülerini segmentlere ayırmaktan daha zordur. Bu makale, iris bölgesini daha doğru bir şekilde segmentlere ayırmak için insan gözlerinin rengini kullanan yeni bir iris segmentasyon yöntemi önermektedir. Mevcut iris segmentasyon yöntemlerinin çoğu irisin rengini görmezden gelirken veya gri tonlamalı göz görüntüleri ile doğrudan ilgilenirken, önerilen yöntem iris segmentasyon adımını basitleştirmek için iris renginden faydalanır. İlk adımda, beklenen iris merkezini HAAR benzeri özellikler kullanarak tahmin ediyoruz. Iris rengi tespit edilir ve buna göre, iris bölgesini bulmak için bir renk bağlayıcı segmentasyon algoritması uygulanır. Her IRIS renk seti ile ayrı ayrı ele alınmak, yanlış segmentasyon hatalarını önemli ölçüde azaltır ve iris tanıma sisteminin performansını artırır. Ubiris veritabanında önerilen algoritmanın test edilmesinin sonuçları, algoritmamızın farklı gürültü faktörlerine ve ideal olmayan koşullara karşı sağlamlığını göstermektedir.

Keywords

• İris segmentasyonu
• görünür dalga boyu Iris görüntüleri
• renk tabanlı iris segmentasyonu
• göz rengi sınıflandırması
• kısıtlanmamış iris tanıma

Exploiting Eye Colors for Better Iris Segmentation in Visible Wavelength Environments

Abstract

Iris segmentation is a crucial step in iris recognition systems. Iris segmentation in visible wavelength and unconstrained environments is more challenging than ‎segmenting iris images in ideal environments. This paper proposes a new iris segmentation method that exploits the color of human eyes to segment the iris region more accurately. While most of the current iris segmentation methods ignore the color of the iris or deal with ‎grayscale eye images directly, the proposed method takes benefits from iris color to simplify the iris segmentation step. In the first step, we estimate the expected iris center using Haar-like features. The iris color is detected and accordingly, a color-convenient segmentation algorithm is applied to find the iris region. Dealing separately with each iris color set significantly decreases the false segmentation errors and enhances the performance of the iris recognition system. The results of testing the proposed algorithm on the UBIRIS database demonstrate the robustness of our algorithm against different noise factors and non-ideal conditions.

Keywords

• iris segmentation
• visible wavelength iris images
• color-based iris segmentation
• eye color classification
• unconstrained iris recognition

References

1. [1] Kak, N., Gupta, R., & Mahajan, S. (2010). Iris recognition system. International Journal of Advanced Computer Science and Applications, 1(1), 34-40.
2. [2] Daugman, J. (2001). Statistical richness of visual phase information: update on recognizing persons by iris patterns. International Journal of computer vision, 45(1), 25-38.
3. [3] Daugman, J. (2004). Iris recognition border-crossing system in the UAE. International Airport Review, 8(2).
4. [4] Chen, J., Shen, F., Chen, D. Z., & Flynn, P. J. (2016). Iris recognition based on human-interpretable features. IEEE Transactions on Information Forensics and Security, 11(7), 1476-1485.
5. [5] Thepade, D. S., & Mandal, P. R. (2014). Novel iris recognition technique using fractional energies of transformed iris images using haar and kekre transforms. International Journal of Scientific & Engineering Research, 5(4).
6. [6] Sahmoud, S. A. I. (2011). Enhancing iris recognition.
7. [7] Wildes, R. P. (1997). Iris recognition: an emerging biometric technology. Proceedings of the IEEE, 85(9), 1348-1363.
8. [8] Bowyer, K. W., Hollingsworth, K. P., & Flynn, P. J. (2013). A survey of iris biometrics research: 2008–2010. In Handbook of iris recognition (pp. 15-54). Springer, London.

9. [9] Liu, N., Li, H., Zhang, M., Liu, J., Sun, Z., & Tan, T. (2016). Accurate iris segmentation in non-cooperative environments using fully convolutional networks. In 2016 International Conference on Biometrics (ICB) (pp. 1-8). IEEE.
10. [10] Sahmoud, S. A., & Abuhaiba, I. S. (2013). Efficient iris segmentation method in unconstrained environments. Pattern Recognition, 46(12), 3174-3185.
11. [11] Daugman, J. (2009). How iris recognition works. In The Essential Guide to Image Processing (pp. 715-739). Academic Press.
12. [12] Tan, T., He, Z., & Sun, Z. (2010). Efficient and robust segmentation of noisy iris images for non-cooperative iris recognition. Image and vision computing, 28(2), 223-230.
13. [13] Proença, H., & Alexandre, L. A. (2007). The nice. i: noisy iris challenge evaluation-part i. In 2007 First IEEE International Conference on Biometrics: Theory, Applications, and Systems (pp. 1-4). IEEE.
14. [14] Tisse, C. L., Martin, L., Torres, L., & Robert, M. (2002). Person identification technique using human iris recognition. In Proc. Vision Interface (Vol. 294, No. 299, pp. 294-299).
15. [15] Shamsi, M., Saad, P. B., Ibrahim, S. B., & Kenari, A. R. (2009). Fast algorithm for iris localization using Daugman circular integro differential operator. In 2009 International Conference of Soft Computing and Pattern Recognition (pp. 393-398). IEEE.
16. [16] Pedersen, S. J. K. (2007). Circular hough transform. Aalborg University, Vision, Graphics, and Interactive Systems, 123(6).
17. [17] Uhl, A., & Wild, P. (2012). Weighted adaptive hough and ellipsopolar transforms for real-time iris segmentation. In 2012 5th IAPR international conference on biometrics (ICB) (pp. 283-290). IEEE.
18. [18] Huang, J., Wang, Y., Tan, T., & Cui, J. (2004, August). A new iris segmentation method for recognition. In Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004. (Vol. 3, pp. 554-557). IEEE.
19. [19] Kong, W. K., & Zhang, D. (2001). Accurate iris segmentation based on novel reflection and eyelash detection model. In Proceedings of 2001 International Symposium on Intelligent Multimedia, Video and Speech Processing. ISIMP 2001 (IEEE Cat. No. 01EX489) (pp. 263-266). IEEE.
20. [20] Ma, L., Wang, Y., & Tan, T. (2002). Iris recognition using circular symmetric filters. In Object recognition supported by user interaction for service robots (Vol. 2, pp. 414-417). IEEE.
21. [21] Banerjee, S., & Mery, D. (2015). Iris segmentation using geodesic active contours and grabcut. In Image and Video Technology (pp. 48-60). Springer, Cham.
22. [22] Shah, S., & Ross, A. (2009). Iris segmentation using geodesic active contours. IEEE Transactions on Information Forensics and Security, 4(4), 824-836.
23. [23] Ouabida, E., Essadique, A., & Bouzid, A. (2017). Vander Lugt Correlator based active contours for iris segmentation and tracking. Expert Systems with Applications, 71, 383-395.
24. [24] Ross, A., & Shah, S. (2006). Segmenting non-ideal irises using geodesic active contours. In 2006 Biometrics Symposium: Special Session on Research at the Biometric Consortium Conference (pp. 1-6). IEEE.
25. [25] Badrinarayanan, V., Kendall, A., & SegNet, R. C. (2015). A deep convolutional encoder-decoder architecture for image segmentation. arXiv preprint arXiv:1511.00561, 5.
26. [26] Wang, C., Zhu, Y., Liu, Y., He, R., & Sun, Z. (2019). Joint iris segmentation and localization using deep multi-task learning framework. arXiv preprint arXiv:1901.11195.
27. [27] Zhao, Z., & Kumar, A. (2017). Towards more accurate iris recognition using deeply learned spatially corresponding features. In Proceedings of the IEEE international conference on computer vision (pp. 3809-3818).
28. [28] Gangwar, A., & Joshi, A. (2016). DeepIrisNet: Deep iris representation with applications in iris recognition and cross-sensor iris recognition. In 2016 IEEE international conference on image processing (ICIP) (pp. 2301-2305). IEEE.
29. [29] Sahmoud, S., & Fathee, H. N. (2020). Fast Iris Segmentation Algorithm for Visible Wavelength Images Based on Multi-color Space. In International Conference on Advanced Concepts for Intelligent Vision Systems (pp. 239-250). Springer, Cham.
30. [30] Viola, P., & Jones, M. (2001). Rapid object detection using a boosted cascade of simple features. In Proceedings of the 2001 IEEE computer society conference on computer vision and pattern recognition. CVPR 2001 (Vol. 1, pp. I-I). Ieee.
31. [31] Bao, P., Zhang, L., & Wu, X. (2005). Canny edge detection enhancement by scale multiplication. IEEE transactions on pattern analysis and machine intelligence, 27(9), 1485-1490.
32. [32] Proença, H., & Alexandre, L. A. (2005). UBIRIS: A noisy iris image database. In International Conference on Image Analysis and Processing (pp. 970-977). Springer, Berlin, Heidelberg.
33. [33] Gragnaniello, D., Poggi, G., Sansone, C., & Verdoliva, L. (2014, November). Contact lens detection and classification in iris images through scale invariant descriptor. In 2014 Tenth International Conference on Signal-Image Technology and Internet-Based Systems (pp. 560-565). IEEE.
34. [34] Puhan, N. B., Sudha, N., & Sivaraman Kaushalram, A. (2011). Efficient segmentation technique for noisy frontal view iris images using Fourier spectral density. Signal, Image and Video Processing, 5(1), 105-119.
35. [35] Proença, H., & Alexandre, L. A. (2006). Iris segmentation methodology for non-cooperative recognition. IEE Proceedings-Vision, Image and Signal Processing, 153(2), 199-205.
36. [36] Bazrafkan S, Thavalengal S, Corcoran P. (2018). An end-to-end deep neural network for iris segmentation in unconstrained scenarios. Neural Networks. 106:79‐95.
37. [37] Chen Y, Wang W, Zeng Z, Wang Y. (2019). An adaptive CNNs technology for robust iris segmentation. IEEE Access. 7:64517‐64532
38. [38] Fathee, H., & Sahmoud, S. (2021). Iris segmentation in uncooperative and unconstrained environments: State-of-the-art, datasets and future research directions. Digital Signal Processing, 118, 103244.
39. [39] Li, Xi, Tian Li, Shaoyi Li, Bin Tian, Jianping Ju, Tingting Liu, and Hai Liu. (2023). "Learning fusion feature representation for garbage image classification model in human–robot interaction." Infrared Physics & Technology 128: 104457.
40. [40] Liu, Tingting, Jixin Wang, Bing Yang, and Xuan Wang. (2021). "NGDNet: Nonuniform Gaussian-label distribution learning for infrared head pose estimation and on-task behavior understanding in the classroom." Neurocomputing 436: 210-220.
41. [41] Liu, Tingting, Bing Yang, Hai Liu, Jianping Ju, Jianyin Tang, Sriram Subramanian, and Zhaoli Zhang. (2022). "GMDL: Toward precise head pose estimation via Gaussian mixed distribution learning for students’ attention understanding." Infrared Physics & Technology 122 (2022): 104099.
42. [42] Jeong, D.S., Hwang, J.W., Kang, B.J., Park, K.R., Won, C.S., Park, D.K. and Kim, J., (2010). A new iris segmentation method for non-ideal iris images. Image and vision computing, 28(2), pp.254-260.
43. [43] Toizumi, Takahiro, Koichi Takahashi, and Masato Tsukada. (2023). "Segmentation-free direct iris localization networks." In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp. 991-1000.
44. [44] Chen, Ying, Huimin Gan, Huiling Chen, Yugang Zeng, Liang Xu, Ali Asghar Heidari, Xiaodong Zhu, and Yuanning Liu. (2023) "Accurate iris segmentation and recognition using an end-to-end unified framework based on MADNet and DSANet." Neurocomputing 517: 264-278.