Research on Enhancing Human Finger Vein Pattern Characteristics Based on Adjacent Node Threshold Image Method

An image of a finger captured under infrared light contains not only the vein pattern but also irregular shading produced by the various thicknesses of the finger bones and muscles. In this paper, we propose a new method to enhance the contrast of the finger vein image. It consists of five parts: wavelet denoising, normalization, adjacent node threshold image method, eliminate black block and burr, thinning. Firstly, we perform stationary wavelet decomposition and transform the image into four frequency bands and design different denoising methods to different frequency bands. Then, we nomalizate efficitive gray value range of finger-vein image to [0, 255]. And then, the binary image is got by adjacent node threshold image method. In the next, small blocks and burr are eliminated basing on the area size and by median filter algorithm separately. Finally, we obtain the skeleton by the quick thinning algorithm. The experiments show that the proposed method can properly enhance the contrast of the finger-vein image and make the skeleton express geometric structure of the hand vein image better.