Abstract: The dyadic wavelet transform is adopted to extract the finger-vein pattern from finger images, which contain the vein pattern, shading and noise. Images are transformed from the spatial domain to the wavelet domain, and wavelet coefficients of the vein patterns and the noise are processed by the soft-thresholding denoising method, which can recover the vein pattern from noisy data. The vein images with the denoised coefficients are reconstructed, which are the feature images. Then the template is used to match the vein patterns.

Key words: biometrics, finger vein, wavelet analysis, soft-thresholding denoising