Context-Aware Facial Expression Recognition Using Deep Convolutional Neural Network Architecture

A frame of reference, which includes additional contextual information, can provide a more accurate and comprehensive understanding of the individual's emotional state. This context might encompass factors such as the person's surroundings, body language, gestures, tone of voice, and the specific situation or events taking place. Previous research in this field has often struggled to recognize emotions within a contextual framework. However, by considering contextual elements in addition to facial expressions, we can gain a more nuanced and precise picture of the individual's emotions. In this paper, we used both context-aware datasets (Emotic, CAER, and CAER-S) and only the facial emotion datasets (Affectnet and AEFW) to signify the context. In this Emotic dataset images are labeled with 26 emotional categories. We utilized these datasets to build a convolutional neural network model that effectively examines both the individual and the overall scenario to accurately identify a wide range of information pertaining to emotional states. The features obtained from these two modules are combined using a specialized fusion network. Through this approach, we demonstrate the significance of emotion recognition within a visual context.