Emotion recognition from color facial images based on multilinear image analysis and Log-Gabor filters

Author

Lajevardi, Seyed Mehdi ; Hussain, Zahir M.

Author_Institution

Sch. of Electr. & Comput. Eng., RMIT Univ., Melbourne, VIC, Australia

fYear

2010

fDate

8-9 Nov. 2010

Firstpage

1

Lastpage

6

Abstract

A novel approach is proposed for emotion recognition from low resolution color facial images. The 3D color images are unfolded to 2D matrix based on multilinear algebra. Then, the features are extracted from them by Log-Gabor filters. The optimum features are selected based on mutual information. These features are classified using linear discriminant analysis (LDA) classifier. Experimental results carry out that the proposed method has large improvement in emotion recognition for 3D color facial images. Furthermore, the color subspace has a great impact in the rate of emotion recognition from low resolution images.

Keywords

Gabor filters; emotion recognition; feature extraction; image colour analysis; image resolution; statistical analysis; 2D matrix; 3D color facial images; LDA; Log-Gabor filters; emotion recognition; feature extraction; linear discriminant analysis classifier; low resolution color facial images; multilinear algebra; multilinear image analysis; mutual information; Color; Emotion recognition; Feature extraction; Image color analysis; Mutual information; Tensile stress; Vectors; Color emotion recognition; Log-Gabor filters; facial expression recognition; multilinear image analysis;

fLanguage

English

Publisher

ieee

Conference_Titel

Image and Vision Computing New Zealand (IVCNZ), 2010 25th International Conference of

Conference_Location

Queenstown

ISSN

2151-2191

Print_ISBN

978-1-4244-9629-7

Type

conf

DOI

10.1109/IVCNZ.2010.6148802

Filename

6148802