An Efficient Fingerprint Matching Approach Based on Minutiae to Minutiae Distance Using Indexing with Effectively Lower Time Complexity

Abstract

Fingerprint matching is the main module of fingerprint-based person authentication system. Accuracy of fingerprint matching is an important objective of this type authentication system. Multiple features are used for better matching accuracy but more features add more computational complexity as well as time and space complexity. In this paper, we proposed an approach of fingerprint based authentication system where fingerprint matching is carried out using spacial information (distance) of minutiae points only. This approach is simple and it needs very small space to store templates. We have used an indexing technique to speed up the matching process. In our experiment, we have used FVC2004 fingerprint data-set as input data and investigated the false non-match ratio and false matching ratio for DB2, DB3 and DB4 also.