Low Spatial Resolution Face Recognition Based on Compressive Sensing

DOI

10.2991/amcce-15.2015.109How to use a DOI?

Keywords

Low spatial resolution; compressive sensing; convex optimization; principal component analysis

Abstract

In order to effectively increase robust to recognize low spatial resolution face, this paper tried to take compressive sensing(CS). Firstly, all train face images or their corresponding feature vectors were taken to form sparse representation matrix. Secondly, test face’s sparse coefficients were estimated by convex optimization. Lastly, the test face was decided as the class with minimum residuals. Two face databases (AT&T and AR) were employed to evaluate the performance of some CS algorithms such as SRC, RSC and CRC. The experiments showed that compared with PCA and FLD, the CS algorithms increased recognition rate for low resolution.

Copyright

© 2015, 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  - Xiao Hu
AU  - Shaohu Peng
AU  - Jiyong Yan
AU  - Zhen He
PY  - 2015/04
DA  - 2015/04
TI  - Low Spatial Resolution Face Recognition Based on Compressive Sensing
BT  - Proceedings of the 2015 International Conference on Automation, Mechanical Control and Computational Engineering
PB  - Atlantis Press
SP  - 593
EP  - 598
SN  - 1951-6851
UR  - https://doi.org/10.2991/amcce-15.2015.109
DO  - 10.2991/amcce-15.2015.109
ID  - Hu2015/04
ER  -