Bimodal biometric system based on SIFT descriptors of hand images

Hand shape biometry is among the most popular biometrics employed to characterize a person in forensic applications, due to its simplicity of use and acceptance of individuals. However, this modality presents weaknesses which may make system inaccurate. In fact, people from the same family or twins may have related hand features. Therefore, the performance of the hand verification process depends highly on the hand descriptors. In this paper, we propose a new approach for personal verification combining hand shape and palmprint features extracted using the Scale Invariant Feature Transform (SIFT). This transform was improved its high distinction and efficiency in many applications especially in object recognition and video tracking. Our experiments on IITD hand database demonstrate promising results by fusing at matching level score the hand shape and palmprint modalities. These results are comparable with similar bimodal identification methods.