Facial Expression Recognition Using Facial Effective Areas And Fuzzy Logic

Facial expression recognition plays an important and effective role in the interaction between man and computer. In this article, a new system based on the Fuzzy logic is proposed for this purpose. Fuzzy is one useful approach for fuzzy classification, which can determine the intrinsic division in a set of unlabeled data and find representatives for homogeneous groups. This system recognizes seven basic facial expressions namely fear, surprise, happy, sad, disgust, Neutral and anger. First, We present a novel method for facial region extraction from static image. For determination of face effective areas is used from integral projection curves. This method has high ability in intelligent selection of areas in facial expression recognition system. Extracted facial features fed to fuzzy rule based system for facial expression recognition. Results of tests conducted on JAFFE database indicate that the proposed scheme for facial expression recognition is robust, with good accuracy and generating superior results as compared to other approaches.