Presented by: Jingang Yu

Abstruct:

A novel genetically-inspired learning method is proposed for face expression recognition (FER) in learning images. Unlike current research for FER that generally uses visually meaningful feature, we proposed a Genetic Programming based technique, which learns to discover composite operators and features that are evolved from combinations of primitive image processing operations. In this approach, the output of the composite operators is feature vectors used for FER. Our experimental results show that our approach can find good composite operators to effectively extract useful features.