Iris_recognition

Nowadays, authorizing a person has become a significant need. Authorizing a person based on their behavioral or characteristic traits such as fingerprint, iris, face, etc. has brought in a lot of secure feelings in society. In our work, we present Iris-based Biometric systems that have been considered the most secure and accurate form of identifying an individual because of their unique features and textual richness present in them. In our work, we proposed two modified feature extraction techniques namely Convolutional Neural Networks (CNN) and Gabor filter, and then performed different classification algorithms namely SVM (Support Vector Machine) and Neural Networks (NN), and analyzed the change in accuracies affected by the features extracted from the two different techniques and finally landed with the best combination of CNN-NN with the accuracy of 98%. The CASIA Version 1 benchmark database has been used to perform our experiments for both testing and comparison.