Scattering Removal for Finger-Vein Image Enhancement
Jinfeng Yang, Ben Zhang · 2011
In the near-infrared (NIR) light imaging manner, finger-vein images are always degraded greatly due to optical scattering in the biological tissue. This directly leads to difficulty in reliable finger-vein feature representation. To deal with the problem of finger-vein image degradation, this paper proposes a simple but effective image enhancement method based on scattering removal. First, according to the light propagation in biological tissue, a specific optical model is introduced to characterize the intensity of degraded finger-vein image as a linear combination of attenuation component and scattering component. By means of a regularization solution, the scattering component is then estimated to solve the optical model, and thereby the enhanced finger-vein image can be obtained. Finally, experimental results demonstrate the validity of the proposed method in contrast improvement for finger-vein images.