Fast and Robust Personal Identification by Fusion of Finger Vein and Finger-Knuckle-Print Images

Abstract

Finger vein and finger-knuckle-print have been studied for personal identification. Methods utilizing direction and location of finger veins have achieved promising performance. However, it is sensitive to quality of finger vein images and it is slow. In this paper, we develop a fast and robust algorithm for person recognition using a coarse-to-fine classifier. 2DPCA is used for coarse selection of k nearest candidates. To increase the robustness of the algorithm, a candidate person is selected when either its finger vein or finger-knuckle-print is near the corresponding test sample. Competitive coding schema is then conducted on the n (n <= 2k) candidates and test images for final classification. Experimental results show that our method is faster and achieved comparable recognition rate with state-of-the-art methods.