Machine Vision and Applications
Digital Image Processing (3rd Edition)
Digital Image Processing (3rd Edition)
Hi-index | 0.00 |
This paper presents a tri-value template fuzzy match algorithm to reduce the effect of fuzzy edges and tips of infrared finger vein image in the template matching. The proposed method segments the vein feature image into three areas: subject area, fuzzy area and background area and compute the average distance of non-background point to non-background area as the dissimilarity score between the two templates. The proposed approach is robust against the fuzzy edges and tips, and does not require knowledge of correspondence among those points in the two templates. The minimum error rate, 0.54% to 456 near-infrared finger vein images, shows that the proposed method is feasible and practical.