DocumentCode :
167991
Title :
Using Neural Networks with Differential Evolution Learning for Face Recognition
Author :
Shih-Yen Huang ; Cheng-Jian Lin
Author_Institution :
Dept. of Comput. Sci. & Inf. Eng., Nat. Chin-Yi Univ. of Technol., Taichung, Taiwan
fYear :
2014
fDate :
10-12 June 2014
Firstpage :
376
Lastpage :
379
Abstract :
In this paper, we present an innovative method that combines two-dimensional texture and three-dimensional (3D) images surface feature vectors. Next, we use Gabor wavelets extracting local features at different scales and orientations by two-dimensional facial images. Next, we combine the texture with the three-dimensional (3D) images surface feature vectors based on principal component analysis (PCA) to obtain feature vectors from grey and facial surface images. We also propose a differential evolution (DE) algorithm for face recognition based on multilayer neural networks as an identification model. In ours experimental results demonstrate for the recognition different face poses and facial expressions method was efficiency.
Keywords :
evolutionary computation; face recognition; feature extraction; image texture; multilayer perceptrons; principal component analysis; vectors; wavelet transforms; 3D image surface feature vectors; DE algorithm; Gabor wavelets; PCA; differential evolution algorithm; differential evolution learning; face recognition; local feature extraction; multilayer neural networks; principal component analysis; three-dimensional image surface feature vectors; two-dimensional image texture; Face; Face recognition; Feature extraction; Neural networks; Principal component analysis; Three-dimensional displays; Vectors; Differential Evolution; Face Recognition; Gabor Wavelets; Multilayer Neural Networks; Principal Component Analysis;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer, Consumer and Control (IS3C), 2014 International Symposium on
Conference_Location :
Taichung
Type :
conf
DOI :
10.1109/IS3C.2014.104
Filename :
6845896
Link To Document :
بازگشت