In this project, a Biometric Authentication system using the Iris biometric authentication method is designed. The approach taken is using the CASIA-Thousand-IRIS dataset and model it using the Deep Convolutional Neural Network Architecture, with the minimum image preprocessing such as resizing while keeping the aspect ratio and normalization. It is an end-to-end technique without performing segmentation of the IRIS itself. The results are promising, even without performing training on augmentation; the testing accuracy has reached (91.10%). Finally, for proof of the (biometric authentication system concept), a simple mobile application is designed, and the model is deployed on it (IrisRecognizer) as it was exported to its lite version, where default quantization is performed.
If you find this notebook useful in your research or projects, please consider citing it. Proper citation helps me gain recognition for my work and allows others to follow and build upon it.
D-Redouane, An End-to-end segmentation-free approach Iris Biometric Authentication, Open Source Contribution (GitHub & Kaggle), May 2024. Available at: Github and Kaggle
D-Redouane. (2024). An End-to-end segmentation-free approach for Iris eye Recognition.