Abstract | ||
---|---|---|
Fingerprint matching is challenging as the matcher has to minimize two competing error rates: the False Accept Rate and the False Reject Rate. We propose a novel, ef- ficient, accurate and distortion-tolerant fingerprint authen- tication technique based on graph representation. Using the fingerprint minutiae features, a labeled, and weighted graph of minutiae is constructed for both the query finger- print and the reference fingerprint. In the first phase, we obtain a minimum set of matched node pairs by matching their neighborhood structures. In the second phase, we in- clude more pairs in the match by comparing distances with respect to matched pairs obtained in first phase. An op- tional third phase, extending the neighborhood around each feature, is entered if we cannot arrive at a decision based on the analysis in first two phases. The proposed algorithm has been tested with excellent results on a large private livescan database obtained with optical scanners. |
Year | Venue | DocType |
---|---|---|
2000 | WACV | Conference |
Citations | PageRank | References |
61 | 3.23 | 10 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Vinayaka D. Pandit | 1 | 61 | 3.23 |
Ruud M. Bolle | 2 | 2116 | 230.26 |
Vaibhav Vaish | 3 | 579 | 46.38 |
Vaibhav Vaish | 4 | 61 | 3.23 |