Research on Enhancing Human Finger Vein Pattern Characteristics

Finger-vein pattern can be applied to personal identification. But due to many reasons, the captured finger-vein images are blurred and contain a lot of noise. In this paper, we propose a new method to enhance the contrast of the finger-vein image. It consists of three parts: wavelet denoising, contrast enhancement and binary image. At first, we perform stationary wavelet decomposition and transform the image into four frequency bands: low frequency band LL, middle frequency bands LH and HL, and high frequency band HH. To different frequency bands, we design different denoising method. Then we select a special sort of histogram template equalization method to enhance the contrast of the finger-vein image. Finally, we get the binary image using the OTSU method. Our experimental results in this paper show that the proposed method can properly enhance the contrast of the finger-vein image and gets good effect.