Novel Method of Face Feature Extraction and the Realization based on DSP

DOI

10.2991/icmse-15.2015.12How to use a DOI?

Keywords

Feature extraction; Face recognition; Discrete Wavelet Transform (DWT); Principal Components Analysis (PCA); Linear Discriminant Analysis (LDA).

Abstract

Face recognition is an attractive article in pattern recognition and artifical intelligence field. From the actual requirements, the DSP hardware structure is introduced, two feature extraction algorithms are used; and then a method is proposed. the method is based on combination Discrete Wavelet Transform (DWT) with Principal Components Analysis (PCA) and Linear Discriminant Analysis LDA ,and nearest neighbor is used as a classifier.The results evaluated using the classification and recognition of ORL face database. Finally in order to verify the real-time, CCS development environment optimization program is used to achieve the algorithm in DSP platform.Experimental results demonstrated that recognition rate and recognition speed are all satisfactory improvemented.

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  - Jinqing Liu
AU  - Yin Liu
AU  - Qunzhen Fan
PY  - 2015/12
DA  - 2015/12
TI  - Novel Method of Face Feature Extraction and the Realization based on DSP
BT  - Proceedings of the 2015 6th International Conference on Manufacturing Science and Engineering
PB  - Atlantis Press
SP  - 61
EP  - 66
SN  - 2352-5401
UR  - https://doi.org/10.2991/icmse-15.2015.12
DO  - 10.2991/icmse-15.2015.12
ID  - Liu2015/12
ER  -