A Novel Finger Vein Image Quality Evaluation Method Based on Triangular Norm

The quality of finger vein images is a critical factor in affecting the performance of finger vein recognition systems. In this paper, a novel finger vein image evaluation method is proposed to reduce the influence of low quality images on recognition performance. Firstly, the gradient, image contrast, and information entropy of a finger vein image are extracted as image quality scores. Secondly, the score fusion approach based on Triangular norm is proposed to discriminate image quality. Finally, experimental results show that the proposed approach can effectively identify low quality finger vein images and help to improve finger vein recognition performance.