Title :
Discriminant Graph Structures for Facial Expression Recognition
Author :
Zafeiriou, Stefanos ; Pitas, Ioannis
Author_Institution :
Dept. of Electr. & Electron. Eng., Imperial Coll. London, London
Abstract :
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.
Keywords :
face recognition; graph theory; discriminant graph structures; elastic graph matching; facial expression recognition; kernel Fisher discriminant analysis; Cost function; Face detection; Face recognition; Feature extraction; Humans; Infrared detectors; Kernel; Linear discriminant analysis; Robustness; Spatial databases; Elastic graph matching; Fisher´s linear discriminant analysis; Kernel techniques; expandable graphs;
Journal_Title :
Multimedia, IEEE Transactions on
DOI :
10.1109/TMM.2008.2007292