An Adaptive Deep Belief Feature Learning Model for Cognitive Emotion Recognition

Cognitive emotion recognition using facial expression is the sub-field of social signal processing. It is broadly utilized in various fields, specifically human interaction and computer vision. Different investigators use learning approaches to construct an efficient system for automatic emotion recognition. However, predicting certain emotions like surprise, fear, sadness, happiness, disgust, and anger is still challenging in computer vision. However, deep learning has attained the interest of various researchers to resolve real-time problems like emotion recognition. This work concentrates on modelling and efficient Deep Belief Feature Learning (DBFL) for emotion recognition. The model uses a deep network layer to predict the feature information and further classification performance. The model gives 98% average prediction accuracy compared to various other approaches. The evaluation of the model is conducted over the public dataset, and the classification outcomes attained by the model demonstrates the significance of the proposed DBFL.