Human emotion detection and classification using modified voila-jones and convolution neural network

Komala K., Jayadevappa D., Shivaprakash G.


Facial expression is a kind of nonverbal communication that conveys information about a person's emotional state. Human emotion detection and recognition is a significant challenge in computer vision and artificial intelligence. 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 emotions such as anger, sadness, pleasure, surprise, fear, 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 GLCM, LBP and RPCA are applied to identify the distinct mood states and they are categorized using a Convolution Neural Network (CNN) classifier. The obtained results show that the proposed method outperforms in terms of determining the rate of emotion recognition as compared to the existing human emotion recognition techniques.


Convolution neural network; Facial emotion recognition; Gray-level co-occurrence matrix; Linear binary pattern; Robust principal components analysis; Viola-jones



  • There are currently no refbacks.

View IJAI Stats

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.