Title :
Building Palm Vein Capturing System for Extraction
Author :
Wang, Jing-Wein ; Chen, Tzu-Hsiung
Author_Institution :
Inst. of Photonics & Commun., Nat. Kaohsiung Univ. of Appl. Sci., Kaohsiung, Taiwan
Abstract :
The palm vein pattern is unique to individuality which pattern does not change over time apart from size. This feature makes it suitable for one-to-many matching, for which fingerprint and face recognition may not be robust. In this paper, we set up a creatively vein-image capturing system and present a novel framework, composed of image enhancement, feature extraction, noise removal, thinning, skeletonization, and pruning for vein pattern extraction. In our experiments, 25 persons of different ages above 20 including five girls and twenty boys, each has 20 images per person was acquired at different intervals, 10 images for left hand and 10 images for right hand. The performance of the accurate extraction rate is 93.4% on average, 94.8% on right hand and 91.9% on left hand, respectively.
Keywords :
biometrics (access control); blood vessels; feature extraction; image enhancement; image matching; image thinning; feature extraction; image enhancement; image pruning; image skeletonization; image thinning; noise removal; one-to-many matching; palm vein-image capturing system; vein pattern extraction; Biometrics; Feature extraction; Image edge detection; Image segmentation; Noise; Skin; Veins; Palm vein; accurate extraction rate; vein pattern extraction; veinimage capturing;
Conference_Titel :
Systems Engineering (ICSEng), 2011 21st International Conference on
Conference_Location :
Las Vegas, NV
Print_ISBN :
978-1-4577-1078-0
DOI :
10.1109/ICSEng.2011.61
