Hand dorsal vein recognition based on hierarchically structured texture and geometry features

Authors:
Xiangrong Zhu;Di Huang
Affiliations:
IRIP, School of Computer Science and Engineering, Beihang Univ., Beijing, China;IRIP, School of Computer Science and Engineering, Beihang Univ., Beijing, China
Venue:
CCBR'12 Proceedings of the 7th Chinese conference on Biometric Recognition
Year:
2012

Citing 8
Cited 0

Thinning Methodologies-A Comprehensive Survey

IEEE Transactions on Pattern Analysis and Machine Intelligence
Feature extraction of finger-vein patterns based on repeated line tracking and its application to personal identification

Machine Vision and Applications
Palm Vein Verification System Based on SIFT Matching

ICB '09 Proceedings of the Third International Conference on Advances in Biometrics
Personal authentication using hand vein triangulation and knuckle shape

IEEE Transactions on Image Processing
Online biometric authentication using hand vein patterns

CISDA'09 Proceedings of the Second IEEE international conference on Computational intelligence for security and defense applications
Bipartite graph matching for computing the edit distance of graphs

GbRPR'07 Proceedings of the 6th IAPR-TC-15 international conference on Graph-based representations in pattern recognition
Study of hand-dorsa vein recognition

ICIC'10 Proceedings of the 6th international conference on Advanced intelligent computing theories and applications: intelligent computing
Biometric verification using thermal images of palm-dorsa vein patterns

IEEE Transactions on Circuits and Systems for Video Technology

Quantified Score

Hi-index	0.00

Visualization

Abstract

In recent years, hand dorsal vein has attracted increasing attentions of researchers in the domain of biometrics. This paper proposes a novel approach for hand dorsal vein identification, making use of both the texture and geometry features. The proposed approach works in a hierarchical way: 1) the coarse step segments the vein region and calculates its skeleton to feed the following operations, and the Energy Cost extracted in the Thinning process (TEC) is also used to reduce a large number of false candidates, greatly improving the efficiency; 2) in the fine step, both texture and geometry clues are represented by Local Binary Patterns (LBP) and the graph composed by the crossing points and endpoints of vein pattern respectively, and the two modalities are finally combined for decision making. The proposed method is evaluated on the NCUT dataset containing 2040 hand dorsal vein images of 102 subjects, and the experimental results clear highlight its effectiveness.