Estimating Face Emotion using Genetic Algorithm

Abstract

Recognition of emotion through face features (Face Emotion) is a recent concept undertaken by several researchers. Face features have to be extracted from face images before applying the emotion recognition techniques. This paper contemplates these aspects in two parts. The first part describes various processing stages in order to obtain a suitable processed image for applying techniques of face emotion recognition. Several stages of processing lead to segmentation of image. Three methods are proposed in extracting the features and their capabilities are compared. The second part discusses a Genetic Algorithm methodology of estimating the emotions from eye feature alone. Observation of various emotions lead to an unique characteristic of eye, that is, the eye exhibits ellipses of different parameters in each emotion. Genetic Algorithm is adopted to optimize the ellipse characteristics of the eye features. A new form of fitness function is proposed for the Genetic Algorithm. It is ensured through several experiments that the optimized parameters of ellipse reveal various emotional characteristics.