Hand verification system based on multi-features fusion

Abstract

Human hand is a physiological biometric trait employed in order to characterize and identify a person. It is considered as one of the most popular biometric technologies especially in forensic applications, due to its high users acceptance compared to other biometric technologies. In this paper, we pro pose a hand biometric system for personal identity verification, fusing multiple features of the hand at matching score level. In fact, shape and texture are extracted from hand, fingers and palmprint in order to represent the hand image of each person. In the feature extraction strategy, the scale Invariant Feature Transform (SIFT) is extracted from the hand image to describe local invariant features of the hands contour and also extracted from fingers images. In the other hand, Gabor filters are extracted from palmprint images to describe the texture of the hand. The main advantage of these two descriptors (SIFT and Gabor) is that features extracted are invariant to rotation, translation, scale and lighting changes. Personal verification was performed by fusing similarity scores achieved from the hand shape, the fingers and the palmprint. Experimental results show good performances (EER=1.95 %) in hand verification using a database containing 230 different subjects.