Human Emotions Detection Using Hybrid CNN Approach

Automated Facial emotion detection is a challenging task during human-computer interaction. In this paper, we have used the hybrid CNN approach to recognize human emotions and based upon its features, categorized them into sub-categories. This research uses a FER13 dataset for emotion recognition and trained our model accordingly to get optimal results in terms of accuracy and loss. The system performance gains average accuracy rate of 88.10%. The system has been successfully recognized seven basic emotion classes. Thus, the proposed method is proven to be effective in terms of more accuracy and minimum loss for face emotion detection.