Genetic algorithm for various face emotions classification

Abstract

The eye feature plays a vital role in classifying the face emotion using Genetic Algorithm. The acquired images have gone through few preprocessing methods such as grayscale, histogram equalization and filtering. Among the edge detection methods, Sobel method performed very well in segmenting the image. The projection profile is found to be suitable feature extraction method comparing with other two methods in respect of time of processing. The second part discusses a Genetic Algorithm methodology of estimating the emotions from eye feature alone. Observation of various emotions lead to a 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. Processing time for Genetic Algorithm varies for each emotion.