Classifiers in IRIS Biometrics for Personal Authentication

Machine learning is that which provides the systems the ability to improve on experience without being programmed. Higher accuracy rate is a challenging problem with Iris biometrics. In this paper the best performance based on the classifiers for iris biometric is identified. The normalized iris images are downloaded from IIT Delhi database. The features are extracted from normalized iris images using the techniques such as histogram and wavelet transform. The extracted features are then classified using Neural Networks and Support Vector Machine. The study shows that support vector machine has far better recognition rate than back propagation neural network. The proposed technique provides accuracy at the rate of 96.7% than the neural network.