Finger vein is a promising biometric pattern for personal identification in terms of its security and convenience. In this paper a finger vein recognition algorithm based on two-dimensional principal component analysis is presented. Firstly, a stable region representing finger vein network is cropped from the image plane of an imaging sensor. Then the finger vein features were extracted by 2DPCA method. Finally, finger vein recognition is implemented using the nearest neighbor distance classifier. Experimental results show that the proposed method exhibit an exciting performance in personal identification.
A Finger Vein Recognition Algorithm Based on Gradient Correlation
