Abstract: Automatic facial expression is an interesting and challenging problem, and impacts important applications in many areas such as human–computer interaction and data-driven animation. Facial expression recognition is the process performed by computers which consist of detect the face in the image, and pre-process the face regions, extracting facial expression features from image by analysing the change in the appearance of facial features and then classifying this information into facial expression categories like fear, happy sad etc. In this research work, an Automatic Facial Expressions Recognition System is presented that recognizes five principal expressions that are Happy, Sad, Neutral, Anger and Disgust. The system uses an efficient approach for the recognition of those expressions on the basis of some extracted features. The whole system is implemented on the dataset of 150 images of frontal facial expressions of happy, sad, neutral, anger and disgust by using MATLAB. The images are collected from the Karolinska Directed Emotional Faces (KDEF) database. We empirically evaluate the facial representation based on local binary pattern (LBP) features. Then recognition performed by KNN classifier with LBP features. The result obtained after implementation is very good.
Keywords: Face Detection, Viola Jones, Feature Extraction, LBP (Local Binary Pattern), KNN Classifier.