Open Access Open Access  Restricted Access Subscription Access

Design and Evaluation of an Iris Recognition System Based on Deep Learning

Murari Sharma

Abstract


Biometrics the current iris recognizable proof methods that have been distributed throughout the years fundamentally depend on specific conditions, for example, the distance at which the pictures are obtained and the setting of consistent gazing, which requires broad client coordinated effort. These portion/standardize based and "stage based" technique experiences various issues while addressing information lessens the variations brought about by weighty eyelash impediment, movement obscures, movement interpretations, scale, revolutions, pupillary expansion, and unpredictable appearance nearby around the client's eyes in circumstances where there is no confirmation of joint effort. By examining the removals between the separate patches two by two of iris pictures, convolutional brain network-based profound learning grouping models (CNN) can precisely recognize veritable and fraud examinations utilizing iris division, even in very uproarious conditions. When contrasted with other biometric acknowledgment frameworks, the iris surface's capacity to vary across indistinguishable twins' eyes and between the left and right eyes of a similar individual provides it with a safer technique for confirmation. In the examinations, we considered three notable informational indexes (CASIA, Polaris), reaching the resolution that the recommended calculation is compelling, and particularly in circumstances while unequivocally portioning the iris is troublesome.


Full Text:

PDF

References


Daugman, J. G. (1993). High confidence visual recognition of persons by a test of statistical independence. IEEE transactions on pattern analysis and machine intelligence, 15(11), 1148-1161.

Daugman, J. (2007). New methods in iris recognition. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 37(5), 1167-1175.

Arora, S., & Bhatia, M. S. (2018, December). A computer vision system for iris recognition based on deep learning. In 2018 IEEE 8th International Advance Computing Conference (IACC) (pp. 157-161). IEEE.

Liu, S., & Deng, W. (2015, November). Very deep convolutional neural network based image classification using small training sample size. In 2015 3rd IAPR Asian conference on pattern recognition (ACPR) (pp. 730-734). IEEE.

Tan, M., & Le, Q. (2019, May). Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning (pp. 6105-6114). PMLR.

Tan, M., Pang, R., & Le, Q. V. (2020). Efficientdet: Scalable and efficient object detection. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 10781-10790).

Arora, S., & Bhatia, M. S. (2018, December). A computer vision system for iris recognition based on deep learning. In 2018 IEEE 8th International Advance Computing Conference (IACC) (pp. 157-161). IEEE.

Xia, Y., Zhang, Y., Liu, F., Shen, W., & Yuille, A. L. (2020). Synthesize then compare: Detecting failures and anomalies for semantic segmentation. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part I 16 (pp. 145-161). Springer International Publishing.

Sun, G., Wang, W., Dai, J., & Van Gool, L. (2020). Mining cross-image semantics for weakly supervised semantic segmentation. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part II 16 (pp. 347-365). Springer International Publishing.

Ronneberger, O., Fischer, P., & Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18 (pp. 234-241). Springer International Publishing.


Refbacks

  • There are currently no refbacks.