An improved method for finger-vein image enhancement

Finger vein, as a biological characteristic of individual, has been increasingly utilized for personal identification in advanced security applications. Nonetheless, the finger-vein images always are low in quality, which seriously affect the vein-feature extraction and classification. Hence, establishing a reasonable finger-vein enhancement strategy is indispensable in reality. In this paper, an improved approach, incorporating directional decomposition and Frangi filtering, is proposed to enhance finger veins. First, background subtraction is processed to improve image contrast and eliminate uneven illumination. Then, the vein information as ridge-like directional characters in image is detected by directional filter bank and enhanced through Frangi filtering after noise removal. Finally, the enhanced images are obtained from enhanced directional images using a finer reconstruction rule. Experimental results show that the proposed approach is much more effective and robust in enhancing finger-vein images.