Biometric identification based on low-quality hand vein pattern images

Vein pattern is used as biometric feature in recent 20 years and It attracts much attention from 2000. A complete vein pattern recognition system contains three key procedures, vein image collection, vein pattern segment and feature extraction. In this paper, we adopt low-cost collection devices and discuss all the three parts in details. First a novel image collection way is proposed, which could enhance the contrast. Then a denoising algorithm using wavelets thresholding based on Besov norm regularization is discussed. This algorithm could remove the high noise while do not hurt the contrast. Finally, two novel robust features specially designed for vein pattern are put forward. Experimental results show that our system is as successful as traditional high-price system. In conclusion, our research makes using low-cost devices to recognize vein patterns possible.