K-plet and CBFS : A Graph based Fingerprint Representation and Matching Algorithm

In this paper, we present a new fingerprint matching algorith m based on graph matching principles. We define a new representation called K-plet to encode the local neighborhood of each minutia. We also pre sentCBFS(Coupled BFS), a new dual graph traversal algorithm for consolidatin g all the local neighborhood matches and analyze its computational complexity. The proposed algorithm is robus t to non-linear distortion since only local neighborhoods are matched at each stage. Ambiguities in minutiae pairings are olved by employing a dynamic programming based optimization approach. The coupled BFS algorithm provides a very generic way of consolidating the local matches. No explicit alignment is required during the entire matchin g process. We present an experimental evaluation of the proposed approach and showed that it exceeds the performanc e of the NIST BOZORTH3 [9] matching algorithm. The paper also provides an extensive survey and taxonomy of e xisting minutiae based matching algorithms.