A Study of Minutiae Matching Algorithm Based on Orientation Validation

Zhongchao Shi, Jin Qi, Xuying Zhao, Yangsheng Wang

Abstract: In this paper, we promote a new fingerprint minutia matching algorithm based on orientation validation. Firstly, we use 1 Nearest Neighbor of the minutiae local structure to find some corresponding point pairs and get the best one by clustering. Secondly, A structure matching algorithm is used to match the global minutiae, and a matching table is used to avoid multi-minutiae match to one minutia and vice versa. Moreover, we promote a new decision method based on orientation validation, and a new rule is proposed to make the final judgment. Finally, the experimental results conducted in DB3, from FVC2002, show that the performance of our algorithm is good.