ABSTRACT

Facial expression analysis is rapidly becoming an area of intense interest in computer science and human-computer interaction design communities. The most expressive way humans display emotions is through facial expressions. In this paper a method is implemented using 2D appearance-based local approach for the extraction of intransient facial features and recognition of four facial expressions. The algorithm implements Radial Symmetry Transform and further uses edge projection analysis for feature extraction and creates a dynamic spatiotemporal representation of the face, followed by classification into one of the expression classes. The algorithm achieves an accuracy of 81.0% for facial expression recognition from grayscale image.