An accurate finger vein based verification system

This paper makes use of finger vein to propose an accurate personal authentication system. A matched filtering at various scales is applied on the vein image to reduce the effects of noise occurred due to non-uniform illumination, low local contrast, hairs and skin texture. Vein image is also enhanced by using global characteristics. Local and global characteristics of enhanced vein images are fused to obtain accurate vein pattern. Extracted veins are used for matching such that the problem of geometric deformations can be handled efficiently. For performance evaluation, a publicly available database of 3132 unconstrained finger vein images acquired from 156 subjects is used. Performance of the proposed system is found to be better than the various existing systems. (C) 2014 Elsevier Inc. All rights reserved.