Emotion Recognition Using Convolutional Neural Network (CNN)

Abstract Emotion is an expression that human use in expressing their feelings. It can be express through facial expression, body language and voice tone. Humans’ a major way conveying emotion since it the most powerful, natural universal signal to humans’ condition. However, has similar patterns, very confusing recognizing using naked eye. For instance, afraid surprised one another. Thus, this will lead confusion determining expression. Hence, study aims develop mobile based application for recognition recognize on real-time. The Deep Learning technique, Convolutional Neural Network (CNN) implemented study. MobileNet algorithm deployed train model recognition. There are four types of expressions recognized which happy, sad, surprise, disgusting. As result, obtained 85% accuracy. In future, developed could improved by adding more face categories.