Paper Info
Title
Multi-mode Emotion Recognition Based on Generalized Discriminative Canonical Correlation Analysis
Abstract
In recent years, emotion recognition encounters difficulties: accuracy and robustness. In order to improve performance of the emotion recognition system, here we present a novel multimode emotion recognition system, including visual and audio information. Meanwhile, a feature fusion algorithm named Generalized discriminative canonical correlation analysis (GDCCA) is proposed and utilized in this system. First, we extract video image features through 2D Gabor wavelet and obtain the statistical and annotation features of audio. Then the above features are fused by GDCCA to be a fusion feature which is fed into SVM classifier to get the recognition results. Finally, the novel emotion recognition system is applied on the database of BUBE (Beihang University Biomodal Emotion Database) and the experiments provide extensive illustrations of the systems performance.
Year
DOI
Venue
2018
10.1145/3290589.3290590
Proceedings of the 2018 International Conference on Sensors, Signal and Image Processing
Keywords
DocType
ISBN
2D Gabor wavelet, Feature fusion, Generalized discriminative canonical correlation analysis (GDCCA), Multimode emotion recognition system, annotation features
Conference
978-1-4503-6620-5
Citations 
PageRank 
References 
0
0.34
11
Authors
3
Name
Order
Citations
PageRank
Lijiang Chen130423.22
Wentao Dou200.68
Xia Mao3335.95