Abstract
This study provides a comprehensive comparison of various iris recognition algorithms, including Hamming distance, feed-forward neural network, and support vector machine (SVM) methods. The study aims to identify the most accurate and efficient algorithm for iris recognition in biometric authentication systems. The dataset from CASIA and uniform preprocessing techniques ensure fair comparisons. The Hamming distance algorithm achieves 79% recognition accuracy but suffers from high false accept and false reject rates due to its threshold-based nature. The feed-forward neural network algorithm achieves an improved accuracy of 87.5% and handles complex classification tasks effectively. However, it is computationally intensive and requires manual feature selection. To address these limitations, the SVM algorithm is explored using linear, polynomial, and quadratic kernels with techniques like SMO, QP, and LS. The quadratic kernel with the least squares approach stands out, achieving an impressive accuracy of 94.5%. This method supports nonlinear problems, automatically selects optimal features, and serves as an excellent binary classifier. The findings emphasize the superior performance of the SVM-based approach in terms of accuracy, true accept rate, and true reject rate, particularly the quadratic kernel with the least squares method. This study offers valuable insights for developing robust and efficient iris recognition systems for biometric authentication applications.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Daugman, J.: How iris recognition works. IEEE Trans. Circuits Syst. Video Technol. 14(1), 21–30 (2004)
Wildes, R.P.: Iris recognition: an emerging biometric technology. Proc. IEEE 85(9), 1348–1363 (1997)
Ma, L., Tan, T., Wang, Y., Zhang, D.: Efficient iris recognition by characterizing key local variations. IEEE Trans. Image Process. 13(6), 739–750 (2004)
Ávila, C.S., Sánchez-Reillo, R.: Two different approaches for iris recognition using Gabor filters and multiscale zero-crossing representation. Pattern Recogn. 38(2), 231–240 (2005)
Li, D., Pedrycz, W., Pizzi, N.: Fuzzy Wavelet Packet based feature extraction method and its application to biomedical signal classification. IEEE Trans. Biomed. Eng. 52(6), 1132–1139 (2005)
He, F., Liu, Y., Zhu, X., Huang, C.P., Han, Y., Dong, H.: Multiple local feature representations and their fusion based on an SVR model for iris recognition using optimized Gabor filters. EURASIP J. Adv. Sig. Process. 2014(1), 1–17 (2014)
Liu-Jimenez, J., Sánchez-Reillo, R., Ávila, C.S.: Full hardware solution for processing iris biometrics. In: IEEE International Carnahan Conference on Security Technology (2005)
Rossant, F., Eslava, M.T., Thomas, E., Amiel, F., Amara, A.B.: Iris identification and robustness evaluation of a wavelet packets based algorithm. In: International Conference on Image Processing (2005)
Son, B., Kee, G., Byun, Y., Lee, Y.: Iris recognition system using wavelet packet and support vector machines. In: Chae, K.-J., Yung, M. (eds.) WISA 2003. LNCS, vol. 2908, pp. 365–379. Springer, Heidelberg (2004). https://doi.org/10.1007/978-3-540-24591-9_28
Vatsa, M., Singh, R., Noore, A.: Reducing the false rejection rate of iris recognition using textural and topological features. World Acad. Sci. Eng. Technol. Int. J. Comput. Electr. Autom. Control Inf. Eng. 2(7), 2533–2539 (2008)
Proença, H., Alexandre, L.A.: Toward noncooperative IRIs recognition: a classification approach using multiple signatures. IEEE Trans. Pattern Anal. Mach. Intell. 29(4), 607–612 (2007)
Tao, Q., Veldhuis, R.: Hybrid fusion for biometrics: combining score-level and decision-level fusion. In: IEEE Conference on Computer Vision and Pattern Recognition Workshop (2008b)
Pereira, M., Veiga, A.C.P.: A method for improving the reliability of an iris recognition system. In: IEEE Pacific Rim Conference on Communications, Computers and Signal Processing (2005)
Haykin, S.: Neural Networks: a comprehensive foundation (1998)
Davis-Silberman, N., Ashery-Padan, R.: Iris development in vertebrates; genetic and molecular considerations. Brain Res. 1192, 17–28 (2008)
Yu, Li., Wang, K., Zhang, D.: A novel method for coarse iris classification. In: Zhang, D., Jain, A.K. (eds.) ICB 2006. LNCS, vol. 3832, pp. 404–410. Springer, Heidelberg (2005). https://doi.org/10.1007/11608288_54
Sun, Z., Wang, Y., Tan, T., Cu, J.: Robust direction estimation of gradient vector field for iris recognition. In: Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004 (2004)
Vailaya, A., Zhang, H., Yang, C., Liu, F., Jain, A.K.: Automatic image orientation detection. IEEE Trans. Image Process. 11(7), 746–755 (2002)
Dua, M., Gupta, R., Khari, M., Crespo, R.G.: Biometric iris recognition using radial basis function neural network. Soft. Comput. 23(22), 11801–11815 (2019)
Kaur, S., Chaudhary, G., Srivastava, S., Khari, M., Crespo, R.G., Kumar, J.D.: Exploiting feature space using overlapping windows for improving biometric recognition. Comput. Electr. Eng.Electr. Eng. 96, 107552 (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Kumar, G., Gulati, A., Verma, A., Khari, M., Tyagi, G. (2024). Iris Recognition System in the Context of Authentication. In: Santosh, K., et al. Recent Trends in Image Processing and Pattern Recognition. RTIP2R 2023. Communications in Computer and Information Science, vol 2026. Springer, Cham. https://doi.org/10.1007/978-3-031-53082-1_28
Download citation
DOI: https://doi.org/10.1007/978-3-031-53082-1_28
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-53081-4
Online ISBN: 978-3-031-53082-1
eBook Packages: Computer ScienceComputer Science (R0)