Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/34301
Title: Online personal verification by palmvein image through palmprint-like and palmvein information
Authors: Li, Q
Li, X
Guo, Z
You, J 
Keywords: Biometric authentication
Fusion
Matched filter
Palmprint
Palmvein
Texture coding
Issue Date: 2015
Publisher: Elsevier
Source: Neurocomputing, 2015, v. 147, no. 1, p. 364-371 How to cite?
Journal: Neurocomputing 
Abstract: Recently, palmvein recognition has been attracting much research interest. The joint use of palmprint and palmvein features can effectively increase the accuracy, robustness of palm based biometric techniques. And, as it is an inner vessel structure feature, palmveins can increase the anti-spoof and liveness detection capability of a palm based biometric system. However, lack of techniques to separate palmveins from palmprints in one image weakens the anti-spoof and liveness detection capability. This paper presents a novel online personal verification system by fusing palmprint and palmvein information. The proposed system includes: (1) A single camera and single light source to simplify the imaging system and save data collection time; (2) A morphological palmprint erasing technique to increase the accuracy of palmvein segmentation; (3) The fusion of palmprint and palmvein information to further improve the system accuracy. The experimental results demonstrated that since palmprints and palmveins contain complementary information, much higher accuracy could be achieved by fusing them than using only one of them. In addition, the whole verification procedure can be completed within 1. s, which implies that the system can work in real time.
URI: http://hdl.handle.net/10397/34301
ISSN: 0925-2312
EISSN: 1872-8286
DOI: 10.1016/j.neucom.2014.06.050
Appears in Collections:Journal/Magazine Article

Access
View full-text via PolyU eLinks SFX Query
Show full item record

Page view(s)

52
Last Week
4
Last month
Checked on Aug 13, 2017

Google ScholarTM

Check

Altmetric



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