Towards finger-vein image restoration and enhancement for finger-vein recognition

• A new biological optical model is proposed to reasonably describe the process of finger-vein image degradation.
• A new scattering removal method is proposed to effectively improve the visibility of finger-vein images.
• A new Gabor based filtering method is proposed to enhance venous regions as well as suppressing fake veins and noises.

Biometric recognition based on human finger-vein patterns is an emerging technique and has been receiving increasing attention. Due to light attenuation in biological tissue, the collected finger-vein images are often seriously degraded. This makes finger-vein feature representation unreliable, and inevitably impairs the accuracy of finger-vein recognition. Exploring suitable ways of finger-vein image restoration and enhancement is indispensable for finger-vein based personal identification. In this paper, we first analyze the intrinsic factors causing the degradation of finger-vein images, and propose a simple but effective scattering removal method to improve the visibility of finger-vein images. Moreover, to handle venous region enhancement problem effectively, a directional filtering method based on a family of Gabor filters is proposed. Finally, a Phase-Only-Correlation strategy is used to measure the similarity of the enhanced finger-vein images. Experiments performed on a large finger-vein image database show that the proposed method is effective and reliable in finger-vein image restoration and enhancement.