Biometric verification by palmprint using contourlet transform

Palmprint is a reliable biometric that can be used for identity verification because it is stable and unique for every individual. Palmprint images contain rich, unique features for reliable human identification, which makes it a very competitive topic in biometric research. In this paper, a personal authentication method is proposed which is based on palmprint images and employs contourlet transform for feature extraction process. Contourlet transform extracts image curvatures and smoothness with multidirectional decomposition capability. The proposed method includes three steps, preprocessing, feature extraction, and classification. The central part of each palmprint is determined in preprocessing step. For feature extracting, contourlet transform is applied to the central part of palmprint and then features are extracted from created subbands. Finally, for each image, 384 features are obtained. A last, Naïve Bayes, Support Vector Machine (SVM) and k-Nearest Neighbor (kNN) classifiers are employed. Experiments on three databases resulted recognition accuracies of 99.41%, 92.38%, and 85.34% on PolyU, COEP and IITD databases, correspondingly using kNN classifier. The results demonstrate the efficiency and validity of the proposed method in personal authentication by palmprint images.