A new approach for recognition of human emotions

Abstract

In the modern world, all elder people and young child are left alone at home. As long, they are staying alone at home will lead some depression and diversion for them. To overcome this problem, robots are implemented with face emotion recognition to understand them and react according to their emotion. Here, a face emotion recognition package is being improved for single person. In this analysis's, the eye feature plays a vital role in classifying the face emotion using Genetic Algorithm. The acquired images have gone through few preprocessing methods which are suitable for face emotion such as grayscale, histogram equalization and filtering. The second part discusses a Genetic Algorithm methodology of estimating the emotions from eye feature alone. 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. The range for minor that is 'b 'for different emotion has been tabulated. The tabulation clearly shows the changes of minor axis for each emotion. It has been successfully classified. Processing time for Genetic Algorithm varies for each emotion.