Short Research Advanced Project: Development of strategies for automatic facial feature extraction and emotion recognition

Emotions are a fundamental part of the personal and social skills of the human being. The behavior, intelligence, reason and decision making process are some of the topic that can be influenced by the emotional state of a person. In this paper we develop a computational way for emotion recognition though images using the Cohn-Kanade database to train a pattern recognition neural network and Viola Jones object detector to extract the information of the facial expression. The resulting neural network showed an overall accuracy of 90.7% in recognizing between 6 basic emotions such a surprise, fear, happiness, sadness, disgust and anger.