Realising Human Empathy Using Artificial Neural Network

Abstract: Human facial expression is controlled by neurons and their neural network. It is also dependent on the muscles of the skin that enables the user to convey the behavior and carry inter human communication. Facial expression recognition is a challenging problem in computer vision. In this paper, we have proposed a novel approach to recognize facial expressions from static images, via extraction and selection of salient features points and finding the corresponding feature vectors. We have also constructed an authentic emotion databases by combination of the available databases and the real time images that we have used in our experimental work. Finally, we perform several experiments and show that our neural network approach can be successfully used for emotion recognition. Our main aim is to work upon five different emotions which include neutral, happy, sad, surprised and angry. Using only two-thirds of the total features, our approach achieves a classification rate (CR) which is higher than the CR obtained using all features. Our system also outperforms several existing methods, evaluated on the combination of existing and self-generated databases