Improving Fingerprint Recognition Based on Crease Detection

Conventional algorithms for fingerprint recognition are mainly based on minutiae information. But it is difficult to extract minutiae accurately and robustly for elder people. One of main reasons is that there are too many creases on the fingertips of elder people. In this paper, we will propose a novel algorithm to improve fingerprint recognition based on crease detection. First, creases are extracted by using some special filters. Then the minutiae detected by using conventional algorithms can be further processed and those on or near the creases are discarded as false minutiae. The experimental results show that the performance can be improved by applying crease detection to discard the false minutiae. The false rejection rate can be reduced 6% on average for the fingerprints with creases.