Facial expression analysis is one of the popular fields of research in humancomputer interaction (HCI). It has several applications in next generation userinterfaces, human emotion analysis, behavior and cognitive modeling. In thispaper, a facial expression classification algorithm is proposed which uses Haarclassifier for face detection purpose, Local Binary Patterns (LBP) histogram ofdifferent block sizes of a face image as feature vectors and classifies variousfacial expressions using Principal Component Analysis (PCA). The algorithm isimplemented in real time for expression classification since the computationalcomplexity of the algorithm is small. A customizable approach is proposed forfacial expression analysis, since the various expressions and intensity ofexpressions vary from person to person. The system uses grayscale frontal faceimages of a person to classify six basic emotions namely happiness, sadness,disgust, fear, surprise and anger.
展开▼
