In this paper, a new method to extract person-independent expression feature based on HOSVD (Higher-Order Singular Value Decomposition) is proposed for facial expression recognition. With the assumption that similar persons have similar facial expression appearance and shape, person-similarity weighted expression feature is used to estimate the expression feature of the test person. As a result, the estimated expression feature can reduce the influence of individual caused by insufficient training data and becomes less person-dependent, and can be more robust to new persons. The proposed method has been tested on Cohn-Kanade facial expression database and Japanese Female Facial Expression (JAFFE) database. Person-independent experimental results show the efficiency of the proposed method.
Person-Similarity Weighted Feature for Expression Recognition
Asian Conference on Computer Vision ; 2007 ; Tokyo, Japan November 18, 2007 - November 22, 2007
2007-01-01
10 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Facial Expression , Gesture Recognition , Test Person , Expression Recognition , Facial Expression Recognition Computer Science , Image Processing and Computer Vision , Computer Imaging, Vision, Pattern Recognition and Graphics , Pattern Recognition , Artificial Intelligence , Biometrics , Algorithm Analysis and Problem Complexity
Exemplar-Guided Similarity Learning on Polynomial Kernel Feature Map for Person Re-identification
British Library Online Contents | 2017
|First-Person Activity Recognition: Feature, Temporal Structure, and Prediction
British Library Online Contents | 2016
|British Library Online Contents | 2018
|POINT TO SET SIMILARITY COMPARISON AND DEEP FEATURE LEARNING FOR VISUAL RECOGNITION
Europäisches Patentamt | 2018
|