Deep facial emotion recognition model using optimal feature extraction and dual-attention residual U-Net classifier

Human facial emotion recognition (FER) system has become an active research area and it has attracted various research communities for its wide ranging and promising applications especially in the cybersecurity field. Recognizing various facial expressions corresponding to the emotional forms is considered as a significant task in the system of FER. Typically, the automated system of FER consists of two major and important steps like feature extraction, and facial emotion recognition. In this work, initially the input data is acquired and the features are extracted from the input facial image with the use of Fuzzy Eigen Weighted based feature extraction model (FEW-FE). Among the extracted features, an optimal and best features are selected by means of feature selection technique, which employs Chaotic Spider Monkey Optimization algorithm (CSMO) so as to find best fitness function solution. The use of this optimization technique for the feature subset selection aids the enhancement of classifier performance. Then, the recognition process is carried using Dual-attention residual U-Net classifier framework. The performance evaluation of this proposed model is carried over three input datasets considered such as CK+, FER2013, and JAFFE in terms of recognition accuracy, precision, recall, and F-measure. The comparison is made for the feature extraction and classifier model with that of various existing methodologies which shows the effectiveness of proposed system over other traditional schemes. This proposed design is applicable in the cybersecurity system to detect a person's emotional state from their expression.