Robust Face Recognition Based on DCNN and CRC

DOI

10.2991/ceis-16.2016.23How to use a DOI?

Keywords

face recognition;sparse representation; collabora-tive representation;deep learning

Abstract

Collaborative representation based classification (CRC) has gained popularity in recent years, but the conventional features could not effectively handle the variations of pose and occlusion such as sunglass. In this paper, the deep convolution neural network (DCNN) is introduced in the feature extraction to tackle the facial deformation, particularly, such as pose variation. After analysis on the feasibility of the dictionary construction on DCNN based features, a DCNN feature based occlusion dictionary computing algorithm is then presented to tackle the face recognition with occlusion. Experiments on representative face databases with variations of pose and occlusion demonstrated the effectiveness of the proposed algorithm scheme.

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  - Li-Na Yuan
AU  - Feng Cen
PY  - 2016/11
DA  - 2016/11
TI  - Robust Face Recognition Based on DCNN and CRC
BT  - Proceedings of the 2016 International Conference on Computer Engineering and Information Systems
PB  - Atlantis Press
SP  - 117
EP  - 122
SN  - 2352-538X
UR  - https://doi.org/10.2991/ceis-16.2016.23
DO  - 10.2991/ceis-16.2016.23
ID  - Yuan2016/11
ER  -