Recognition of Human Facial Expression in a Video Image using the Active Appearance Model

Abstract

Abstract —Tracking human facial expression within a video image has many useful applications, such as surveillance and teleconferencing, etc. Initially, the Active Appearance Model (AAM) was proposed for facial recognition; however, it turns out that the AAM has many advantages as regards continuous facial expression recognition. We have implemented a continuous facial expression recognition system using the AAM. In this study, we adopt an independent AAM using the Inverse Compositional Image Alignment method. The system was evaluated using the standard Cohn-Kanade facial expression database, the results of which show that it could have numerous potential applications. Keywords —Active Appearance Model, Facial Expression Recognition, Image Alignment Method 1. I NTRODUCTION Facial expression recognition is a crucial method of inferring human emotions. Facial emo-tions are basically categorized into six facial expressions (surprise, fear, sadness, anger, disgust, happiness). The process flow of the present system is shown in Figure 1. Facial-expression im-ages are captured from a web camera. The active appearance model includes various parameters of shape and appearance. With these images, an AAM