Human emotion recognition based on active appearance model and semi-supervised fuzzy C-means

Abstract

Human emotion recognition is an emerging research area in the field of social signal processing. Facial expression is an important means to detect human emotion. The problem is some facial expressions represent similar emotions. Thus, the recognition must consider the ambiguity in the way human expresses emotions through face. Existing methods do not take into account the level of expression's ambiguity. In our research, we specify face points and display the degree of fuzzy cluster on eight face emotions, namely anger, contempt, disgust, happy, surprise, sadness, fear, and neutral. The proposed methods are based on Active Appearance Model (AAM) and semi-supervised Fuzzy C-means (FCM). We tested the system on Cohn Kanade+ dataset of facial expression which provided eight classes of human emotion. Our methods gain an average accuracy rate of 80.71% and surpass the existing Fuzzy Inference System.