A near-infrared quality assessment method for palm-dorsa vein image

In this paper, we present a new quality assessment method for palm-dorsa vein image based on multi-feature fusion according to the characteristics of palm-dorsa vein image. We develop a quality assessment function by computing the four parameters of gray variance, information entropy, cross point and area of effect respectively and then weighted fusing. We then feed the function value back to the regulating device with near-infrared light source. The experiment results show that this new method is efficient for getting ideal palm-dorsa vein image by regulating light intensity.