文章基本信息

标题：Finger-Knuckle-Print Based Recognition System using LBP and SURF
本地全文：下载
作者：Salil Kumar Verma ; Maitreyee Dutta
期刊名称：International Journal of Computer Science and Information Technologies
电子版ISSN：0975-9646
出版年度：2015
卷号：6
期号：3
页码：2863-2867
出版社：TechScience Publications
摘要：Finger knuckle bending produces a highly unique texture pattern and it can be used as a distinctive biometric identifier. This paper presents a novel combination of local-local information for an efficient fingerknuckle- print (FKP) based recognition system which is robust to scale and rotation. The non-uniform brightness of the FKP due to relatively curvature surface is corrected and texture is enhanced. The local features of the enhanced FKP are extracted using the LBP histogram and the speeded up robust features (SURF). Corresponding features of the enrolled and the query FKPs are matched using nearest-neighbour-ratio method and then the derived LBP and SURF matching scores are fused using weighted sum rule. The proposed system has been evaluated using PolyU FKP database of 7920 images for both identification mode and verification mode.Its parameters have been tuned to get optimum performance. LBP histograms was used for texture feature extraction of a FKP image. SURF has made the system robust against scale and rotation.
关键词：FKP; LBP; SURF; EER; FAR; FRR.