Konferenční příspěvek

Vretos N., Solachidis V., Somol P., Pitas I.

Proc. 16th European Signal Processing Conference (EUSIPCO- 2008)

EURASIP

Lausanne, Switzerland

2008

RNDr. Petr Somol, Ph.D. (ÚTIA - Oddělení rozpoznávání obrazů)

facial expression, facial meshes, recognition, feature selec

In this paper we introduce a new method for facial expression recognition. In order to be able to recognize the six main facial expressions we use a grid approach and therefore we establish our new feature space based on the angles that each grid’s edge form. This way we undertake several affine transformations such as translation, rotation and scaling which in other approaches are considered very harmful in the overall accuracy of a facial expression recognition algorithm. We will therefore demonstrate how we create this feature space, as well as how we apply a feature selection process within this space. The angular nature of the data impose some considerations which will be clarified in this paper.