Emotion Detection using Convolutional Neural Network

Johanna Freeda G, Lavanya C, Lekhaa Shree D, Nivedhitha M, Kavitha C

Abstract: The emotions of a human represent the mental states of feelings that arise without consciousness and effort and are accompanied by physiological changes in facial muscles which implies expressions on face. Some of the spontaneous emotions are happy, sad, anger, disgust, fear, surprise etc. Facial expressions play an important role in nonverbal communication that appears due to internal feelings of a person which reflects on the faces. In order to find the humans emotion through modeling, a extensive research has been carried out in past decades. But still it is far behind from human vision system. In this paper, we are using deep Convolutional Neural Network (CNN) to provide better prediction of human emotions and involving Frames by Frames. FERC-2013 and imdb database has been applied for training in this algorithm. In the proposed system we have experimented the emotion detection based on CNN which provides quite good result and the obtained accuracy may give insights to the researchers for future model of computer based emotion detection system.

Keywords: emotion detection, deep learning, convolutional neural networks, machine learning, facial expressions