Title :
Finger-vein matching based on adaptive vector field estimation
Author :
Jinfeng Yang ; Meijing Wu ; Wanyin Wang ; Yihua Shi
Author_Institution :
Tianjin Key Lab. for Adv. Signal Process., Civil Aviation Univ. of China, Tianjin, China
fDate :
Sept. 30 2012-Oct. 3 2012
Abstract :
In this paper, a new finger-vein vector field estimation method is proposed for the primitive finger-vein feature representation. First, a set of spatial curve filters (SCFs) is built based on a variable curve model in curvature and orientation. To make SCFs adaptive to vein-width variations, a curve length field (CLF) estimation method is then proposed. Next, with the CLF constrain, a vein vector field is established for finger-vein feature description. Finally, finger-vein matching performance is evaluated using Phase-Only-Correlation (POC) measure. Experimental results show that the proposed method is highly powerful in improving finger-vein matching accuracy.
Keywords :
curve fitting; filtering theory; fingerprint identification; image matching; image representation; CLF constraint; CLF estimation method; POC measure; SCF; adaptive vector field estimation method; curve length field estimation method; finger-vein matching; finger-vein matching accuracy; phase-only-correlation measure; primitive finger-vein feature representation; spatial curve filter; variable curve model; vein-width variation; Abstracts; Accuracy; Estimation; Feature extraction; Magnetic resonance; Vectors; Biometrics; curve filter; finger-vein matching; vector field;
Conference_Titel :
Image Processing (ICIP), 2012 19th IEEE International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
978-1-4673-2534-9
Electronic_ISBN :
1522-4880
DOI :
10.1109/ICIP.2012.6466816
