Bias analyses of spontaneous facial expression database

Author

Zhaoyu Wang ; Shangfei Wang ; Yachen Zhu ; Qiang Ji

Author_Institution

Key Lab. of Comput. & Communicating Software of Anhui Province Sch. of Comput. Sci. & Technol., Univ. of Sci. & Technol. of China, Hefei, China

fYear

2012

fDate

11-15 Nov. 2012

Firstpage

2926

Lastpage

2929

Abstract

In this paper, cross-corpora evaluations are used to analyze the bias of spontaneous facial expression databases. Local binary pattern, Gabor, eigenface and fisherface features are extracted and applied to the four spontaneous expression databases: USTC-NVIE, VAM, Belfast Naturalistic and SEMAINE to recognize arousal (high/low) and valance (positive/negative) respectively. Experimental results indicate that there exists bias among different spontaneous expression databases. The emotion-induction methods, the variety of subjects and the quantity of raters may have caused such a bias.

Keywords

Gabor filters; feature extraction; visual databases; Belfast Naturalistic; Gabor feature extraction; SEMAINE; USTC-NVIE; VAM; arousal recognition; bias analysis; cross-corpora evaluations; eigenface feature extraction; emotion-induction methods; fisherface feature extraction; local binary pattern; rater quantity; spontaneous facial expression database; subject variety; valance recognition; Databases; Face recognition; Feature extraction; Principal component analysis; Training; Videos;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition (ICPR), 2012 21st International Conference on

Conference_Location

Tsukuba

ISSN

1051-4651

Print_ISBN

978-1-4673-2216-4

Type

conf

Filename

6460778