To search, Click below search items. |
| All Published Papers Search Service |
|
|
|
Title |
Fingerprint Registration Using Centroid Structure and Line Segments 1 |
|
Author |
Dequn Zhao, Fei Su, Anni Cai |
| Citation |
Vol. 6 No. 3 pp. 197-202 |
|
Abstract |
In this paper a novel distortion-tolerant fingerprint registration method based on centroid structure vector (CSV) and Vector Line Segment (VLS), is proposed. In this method, minutia features of the query fingerprint are clustered into various clusters and a set of VLS is extracted. Several likely transformations between the query and the template images are estimated by using VLS sets. Then, CSV under each likely transformation is constructed by using the centroids of minutia clusters. The fine transformation is finally determined by the number of VLS pairs together with the similarity level of CSV. Experiment results show that this algorithm is an effective and efficient one for aligning fingerprints with a small number of minutia and heavy distortions. Such situations are often encountered in forensic applications. |
|
Keywords |
Fingerprint, Registration, Clustering, Minutia. |
|
URL |
