A robust two step approach for fingerprint identification

Due to the complex distortions involved in two impressions of the same finger, fingerprint identification is still a challenging problem. In this paper, we propose a two step fingerprint identification approach based on the triplets of minutiae. The features that we use to find the potential corresponding triangles include angles, triangle orientation, triangle direction, maximum side, minutiae density and ridge counts. In the first step, based on the number of corresponding triangles between the query fingerprint and the model database constructed offline, hypotheses are generated. In the second step, called verification, false corresponding triangles are eliminated by applying constraints to the transformation between two potential corresponding triangles. The experimental results on National Institute of Standards and Technology special fingerprint database 4, NIST-4, show that the proposed approach provides a reduction by a factor of 10 for the number of the hypotheses that need to be considered if linear search is used and can achieve a good performance even when a large portion of fingerprints in the database are of poor quality. (C) 2003 Elsevier Science B.V. All rights reserved.