Facial Expression Recognition Based on Anatomical Structure of Human Face

Automatic analysis of human facial expressions is one of the challengingproblems in machine vision systems. It has many applications in humancomputerinteractions such as, social signal processing, social robots,deceit detection, interactive video and behavior monitoring. In this paper,we develop a new method for automatic facial expression recognitionbased on facial muscle anatomy and human face structure. The algorithmfinds approximate location of effective facial muscles and extractsfeatures by measuring skin texture in 11 local patches. Seven facialexpressions, including neutral are being classified in this study usingAdaBoost classifier and other classifiers on MMI databases. Experimentalresults show that analyzing skin texture from selected local patches givesaccurate and efficient information in order to identify different facialexpressions.

کلیدواژه ها:

Facial expression analysis ، Human facial anatomy ، Adaboost classifier ، Support vector machine