Quality assessment of finger-vein image

In this paper, we propose a novel quality assessment of finger-vein images for quality control purpose. First of all, we divide a finger vein image into a set of non-overlapping blocks. In order to detect the local vein patterns, each block is projected into the Radon space using an average Radon transform. A local quality score is estimated for each block according to the curvature in the corresponding Radon space, based on which a global quality score of the finger-vein is computed and assessed. Experimental results show that our approach can effectively identify the low quality finger-vein images, which is also helpful in improving the performance of a finger-vein recognition system.