Self Geometric Relationship-based matching for palmprint identification using SIFT

Abstract

SIFT-based identification techniques have been broadly criticised in biometrics due to its high false matching rate. To overcome this weakness, a new method for SIFT-based palmprint matching, called the Self Geometric Relationship-based matching (SGR-Matching) is presented. While existing matching techniques consider only the relationship between the SIFT-points of the query image on one hand and the points in the reference image on the other hand, SGR-Matching also takes into account the geometric relationship between the SIFT-points within the query image in comparison with the relationship of the corresponding matched points in the reference image. Assessed with the proposed SGR-Matching, the SIFT-based palmprint identification system has been shown to improve the performance significantly. Furthermore, experimental results have shown the superiority of the proposed technique over state-of-the-art techniques.