Human emotion detection and classification using modified Viola-Jones and convolution neural network

Facial expression is a kind of nonverbal communication that conveys information about a person's emotional state. Human emotion detection and recognition remains a major task in computer vision (CV) and artificial intelligence (AI). To recognize and identify the many sorts of emotions, several algorithms are proposed in the literature. In this paper, the modified Viola-Jones method is introduced to provide a robust approach capable of detecting and identifying human feelings such as angerness, sadness, desire, surprise, anxiety, disgust, and neutrality in real-time. This technique captures real-time pictures and then extracts the characteristics of the facial image to identify emotions very accurately. In this method, many feature extraction techniques like gray-level co-occurrence matrix (GLCM), linear binary pattern (LBP) and robust principal components analysis (RPCA) are applied to identify the distinct mood states and they are categorized using a convolution neural network (CNN) classifier. The obtained outcome demonstrates that the proposed method outperforms in terms of determining the rate of emotion recognition as compared to the current human emotion recognition techniques