ARTIFICIAL NEURAL NETWORKS BASED RECOGNITION OF SELECTED PALMPRINT FEATURES

Biometric recognition suggests a reliable solution to the problem of user authentication in our networked society. Among all biometrics, palmprint-based recognition is one of the most reliable personal identification methods. In this study, a new approach to the palmprint recognition phase is presented. 2D Gabor filters are used for feature extraction of palmprints. After Gabor filtering, standard deviations are computed in order to generate the palmprint feature vector. In addition, Genetic algorithm based feature selection is used to select the best feature subset from the palmprint feature set. Four different algorithms of Artificial Neural Networks are then applied to the feature vectors for recognition of the people. Recognition rate equal to 98 percent are obtained by using conjugate gradient algorithms.