UM
Status已發表Published
A new fingerprint thinning algorithm
Fang B.; Wen H.; Liu R.-Z.; Tang Y.-Y.
2010-12-01
Source Publication2010 Chinese Conference on Pattern Recognition, CCPR 2010 - Proceedings
Pages1048-1051
AbstractFingerprint thinning is a critical step in fingerprint identification system, and it's also the last step of preprocessing. The performance of a minutiae extraction algorithm relies heavily on the quality of the thinning algorithm. Moreover, the efficiency of the algorithm is a crucial factor in real-time identification system. A new thinning algorithm for fingerprint image which based on directional image is proposed in this paper. The algorithm needs no iteration. It's fast to implement and the thinning result is single pixel wide and with one pixel precision width around the center line. Experimental results proved that the proposed algorithm is both fast and accurate. ©2010 IEEE.
KeywordBiometrics Directional image Fingerprint recognition Fingerprint thinning
DOI10.1109/CCPR.2010.5659273
URLView the original
Language英語English
Fulltext Access
Citation statistics
Document TypeConference paper
CollectionUniversity of Macau
AffiliationChongqing University
Recommended Citation
GB/T 7714
Fang B.,Wen H.,Liu R.-Z.,et al. A new fingerprint thinning algorithm[C], 2010, 1048-1051.
APA Fang B.., Wen H.., Liu R.-Z.., & Tang Y.-Y. (2010). A new fingerprint thinning algorithm. 2010 Chinese Conference on Pattern Recognition, CCPR 2010 - Proceedings, 1048-1051.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Fang B.]'s Articles
[Wen H.]'s Articles
[Liu R.-Z.]'s Articles
Baidu academic
Similar articles in Baidu academic
[Fang B.]'s Articles
[Wen H.]'s Articles
[Liu R.-Z.]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Fang B.]'s Articles
[Wen H.]'s Articles
[Liu R.-Z.]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.