Automatic Fingerprint Matching using Improved Vector Matching Algorithm

The performance of an automatic fingerprint identification system is essentially determined by its fingerprint matching algorithm. In this paper, a novel improved fingerprint image matching algorithm based on vector matching method with variable weight modification is proposed. That is features are extracted from fingerprint image as "vector points" and an improved vector matching method with weight modification is used to match these features. Experiment result in this paper shows that this fingerprint matching algorithm not only improve the accuracy but also effectively reduce FAR with maintaining the same FRR. We believe this method has a great advantage and opens a new way to improve the performance of fingerprint recognition system.