DocumentCode
3349962
Title
A robust algorithm for fingerprint singular point detection and image reference direction determination based on the analysis of curvature map
Author
Qi, Jin ; Xie, Mei
Author_Institution
Electr. Eng. Dept., Univ. of Electron. & Sci. Technol. of China, Chengdu
fYear
2008
fDate
21-24 Sept. 2008
Firstpage
1051
Lastpage
1054
Abstract
A novel fingerprint singular point (SP) detection algorithm is proposed in this paper based on the analysis of curvature maps computed from fingerprint images. And a fingerprint image reference direction (FIRD) is defined and computed using curvature map and orientation field. Because each fingerprint image owns one and only on FIRD, FIRD can be used as the reference frame orientation when performing fingerprint match. A series of experiments are done on a public domain collection of fingerprint images, Set B (training database) of DB3 in FVC2002, to evaluate our method proposed here. The results demonstrate the good accuracy and efficiency of the algorithm in this paper.
Keywords
fingerprint identification; object detection; curvature map; fingerprint singular point detection; image reference direction determination; public domain collection; robust algorithm; training database; Algorithm design and analysis; Application software; Biometrics; Detection algorithms; Fingerprint recognition; Image analysis; Image databases; Image matching; Robustness; Transaction databases; Curvature; Fingerprint Reference Direction; Fingerprint Singular Point;
fLanguage
English
Publisher
ieee
Conference_Titel
Cybernetics and Intelligent Systems, 2008 IEEE Conference on
Conference_Location
Chengdu
Print_ISBN
978-1-4244-1673-8
Electronic_ISBN
978-1-4244-1674-5
Type
conf
DOI
10.1109/ICCIS.2008.4670781
Filename
4670781
Link To Document