Optimized spatial relation-aware graph neural network based facial emotion recognition for reducing video conferencing fatigue

Human emotions can be identified from facial expressions recorded in videos. This provides very low accuracy in real-world uncontrolled environments where various challenges such as variations in lighting and individual appearance must be addressed. Therefore, an Optimized Spatial Relation-aware Graph Neural Network based Facial Emotion Recognition for Reducing Video conferencing Fatigue (FER-SRAGNN-POA-RVF) is proposed in this paper. Here, the input data are collected from Ryerson Emotion dataset. The collected data are pre-processed utilizing Adaptive Multi-Scale Gaussian Co-Occurrence Filtering (AMGCF) to clean up the recorded video. The pre-processed image is given into Modified Spline-Kernelled Chirplet Transform (MSKCT) to extract the geometric features. Then, the extracted features are fed into the Spatial Relation-aware Graph Neural Network (SRAGNN) for facial emotion recognition. Finally, Puzzle Optimization Algorithm (POA) is employed to optimize the SRAGNN parameters. The proposed FER-SRAGNN-POA-RVF method is implemented and the performance metrics attains higher accuracy when compared with existing models.