Local Invariant Representation For Multi-Instance Toucheless Palmprint Identification

Palmprint identification is a popular biometric technology used for personal characterization. Traditional palmprint recognition methods are mostly based on acquisition devices with contact, and this, may affect their user friendliness. In this paper, a toucheless palmprint identification method based on Scale Invariant Feature Transform (SIFT) descriptors and sparse representation method is proposed, in order to extract palmprint features of left and right palms. The fusion scheme is performed at rank level using Support Vector Machines (SVM) classifier and probability distribution to generate the final identity of a person. Experiments evaluated on CASIA palmprint database and a proposed toucheless REST (REgim Sfax Tunisia) hand database, report promising performances which are competitive to other existing palmprint identification methods.