An Effective New Algorithm for Face Recognition

DOI

10.2991/csic-15.2015.94How to use a DOI?

Keywords

Weber's law, Feature extraction, Face recognition

Abstract

To address the influence of the image pre-processing and feature extraction on the recognition rate in face recognition, we propose a algorithm with high recognition rate and fast face recognition under varying illumination environment. The new algorithm deals with complicated illumination conditions of face image, by employing Weber local descriptor (WLD) and Laplacian-of-Gaussian (LoG) descriptor for the extraction of illumination invariant. The processed image is not only insensitive to illumination but also enhances the edge detail information based on complete linear discriminant analysis (CLDA) algorithm for feature extraction. and nearest neighbor based on Euclidean distance classifier. The new algorithm is tested on Yale and the Extended Yale Database B face database respectively. Compared with other face recognition algorithms, the proposed method has outstanding advantage on recognition rate, recognition speed. As a result, It fully meets the real-time requirement for face recognition.

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  - Rui Kong
AU  - Bing Zhang
PY  - 2015/07
DA  - 2015/07
TI  - An Effective New Algorithm for Face Recognition
BT  - Proceedings of the 2015 International Conference on Computer Science and Intelligent Communication
PB  - Atlantis Press
SP  - 390
EP  - 393
SN  - 2352-538X
UR  - https://doi.org/10.2991/csic-15.2015.94
DO  - 10.2991/csic-15.2015.94
ID  - Kong2015/07
ER  -