Discriminant Graph Structures for Facial Expression Recognition

作者：Zafeiriou Stefanos^*; Pitas Ioannis

来源：IEEE Transactions on Multimedia, 2008, 10(8): 1528-1540.

DOI：10.1109/TMM.2008.2007292

• Elastic graph matching
• expandable graphs
• Fisher's linear discriminant analysis
• Kernel techniques

In this paper, a series of advances in elastic graph matching for facial expression recognition are proposed. More specifically, a new technique for the selection of the most discriminant facial landmarks for every facial expression (discriminant expression-specific graphs) is applied. Furthermore, a novel kernel-based technique for discriminant feature extraction from graphs is presented. This feature extraction technique remedies some of the limitations of the typical kernel Fisher discriminant analysis (KFDA) which provides a subspace of very limited dimensionality (i.e., one or two dimensions) in two-class problems. The proposed methods have been applied to the Cohn-Kanade database in which very good performance has been achieved in a fully automatic manner.

• 出版日期2008-12