DocumentCode :
2464947
Title :
Deflection Angle Detection Method Study for Two Fingerprint Images Based on the Fingerprint Character Ring
Author :
Lu, Jie ; Hu, Xuxiao ; Wang, Puyu
Author_Institution :
Zhejiang Wellcom Biometrics Co. Ltd., Hangzhou, China
Volume :
3
fYear :
2010
fDate :
16-17 Dec. 2010
Firstpage :
321
Lastpage :
325
Abstract :
Since the fingerprint image is quasi-periodical, to reduce the True Rejection Rate (TRR) and the Fault Acception Rate (FAR) of image matching, this paper presented a new deflection angle detection method for two fingerprint images based on the character ring of image amplitude-frequency figure. First, rotation and translation between the two images are separated in theory. Then character rings are extracted respectively and coordinate transformation is taken. Thus the offset is calculated by phase correlation algorithm and turned into deflection angle. Matching experiment using this method shows that the TRR is 0.7137% and the FAR is 0.
Keywords :
correlation methods; feature extraction; fingerprint identification; image matching; FAR; TRR; coordinate transformation; deflection angle detection method study; fault acception rate; feature extraction; fingerprint character ring; fingerprint images; image amplitude-frequency figure; image matching; phase correlation algorithm; quasi-periodical; true rejection rate; Correlation; Fingerprint recognition; Fingers; Frequency domain analysis; Image matching; Noise; Pixel; character ring; deflection angle; detection; fingerprint image;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Intelligent Systems (GCIS), 2010 Second WRI Global Congress on
Conference_Location :
Wuhan
Print_ISBN :
978-1-4244-9247-3
Type :
conf
DOI :
10.1109/GCIS.2010.89
Filename :
5709385
Link To Document :
بازگشت