期刊名称：International Journal of Innovative Research in Science, Engineering and Technology
印刷版ISSN：2347-6710
电子版ISSN：2319-8753
出版年度：2016
卷号：5
期号：12
页码：20743
DOI：10.15680/IJIRSET.2016.0512110
出版社：S&S Publications
摘要：In this paper, performance of subspace methods for achieving expression recognition and classificationhas been evaluated. Enhancement of Gabor magnitude and phase parts have been carried out by fusing Gabor filterwith geometrical feature vectors. LDA based algorithms have been developed to recognize seven different facialexpressions such as happy, neutral, angry, disgust, sad, fear and surprise using JAFFE database. Performance ofsubspace methods have been measured for different dimensions by proposing kernel local and global feature preservingsymmetrical weighted discriminant analysis methods against dimensional reduction of fused dataset. Proposedalgorithm yields better performance compared to state of art approaches
关键词：Feature extraction; Gabor filter; subspace; class discrimination; expression recognition.
