Finger Vein and Finger Dorsal Texture Recognition Joint Optimization based on Sparse Representation

DOI

10.2991/eeeis-16.2017.43How to use a DOI?

Keywords

sparse representation; sparse multi-value pattern; locally collaborative representation based classification; joint optimization

Abstract

We introduce the sparse binary pattern (SBP),which is a feature extract method combined SRC with LBP.SBP is robust to illumination. In the paper, we put forward improvement in two directions: multi-value pattern and weighted pattern. Drawing lessons Finger Vein and Finger Dorsal Texture on LTP, we propose sparse ternary pattern (STP); considering different local block makes different contribution to finger vein and finger dorsal texture, we put forward the weighted sparse binary pattern (WSBP).Each improvement makes competitive results. At last, we consider the joint optimization of sparse multi-value pattern and Locally collaborative representation classification (LCRC),namely, we use sparse multi-value pattern in the feature extraction module and use or locally collaborative representation based classification (LCRC) in the classification module. The extensive experiments show that the joint optimization has more advantages than single optimization.

Copyright

© 2017, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Jun Li
AU  - Hai-Wei Liang
AU  - Wen-Ming Yang
PY  - 2016/12
DA  - 2016/12
TI  - Finger Vein and Finger Dorsal Texture Recognition Joint Optimization based on Sparse Representation
BT  - Proceedings of the 2nd Annual International Conference on Electronics, Electrical Engineering and Information Science (EEEIS 2016)
PB  - Atlantis Press
SP  - 329
EP  - 334
SN  - 2352-5401
UR  - https://doi.org/10.2991/eeeis-16.2017.43
DO  - 10.2991/eeeis-16.2017.43
ID  - Li2016/12
ER  -