Face recognition based on regularized Gabor fusion contour wave two transform

DOI

10.2991/icmmita-16.2016.288How to use a DOI?

Keywords

face recognition; occlusion; contourlet; quadratic transformation; feature selection

Abstract

This paper has, from the aforementioned two perspectives, put forward an algorithm for face recognition through a combined use of local descriptor of geometrical information and neighborhood information on the surface of face. Method: firstly, extract a contour line with a geodesic distance equal to that from the pronasale on the face after posture correction; then extract the local neighborhood information of each point in the re-sampled contour line to constitute the local descriptor; finally, carry out the weighted summation rule fusion of local descriptor between corresponding points of the tested face and collected face, and then use the nearest neighbor classifier to obtain the final recognition results. It indicates that this algorithm, whether in the recognition rate or in the computation complexity, can achieve relatively good effect.

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  - Yingjie Zhao
AU  - Yisu Liu
PY  - 2017/01
DA  - 2017/01
TI  - Face recognition based on regularized Gabor fusion contour wave two transform
BT  - Proceedings of the 2016 4th International Conference on Machinery, Materials and Information Technology Applications
PB  - Atlantis Press
SP  - 1263
EP  - 1267
SN  - 2352-538X
UR  - https://doi.org/10.2991/icmmita-16.2016.288
DO  - 10.2991/icmmita-16.2016.288
ID  - Zhao2017/01
ER  -