Multi-Class Facial Emotion Recognition Using Hybrid Dense Squeeze Network

Abstract

Automatic facial expression recognition (FER) is utilized in various applications like psychoanalysis, intelligent driving, robot manufacturing, etc. Numerous researchers have been looking for better techniques to improve the accuracy of FER. In fact, FER under laboratory conditions has almost achieved top accuracy. Besides, label deviations or errors caused by annotators’ subjectivity also make the FER task much tougher. Thus, more and more researchers begin to find new ways to handle with the FER problems. In this work, a new deep learning (DL) model called dense squeeze network with improved red deer optimization (DenseSNet_IRDO) is proposed for the recognition of facial emotions. The steps used for FER are pre-processing, fused deep feature extraction-selection and classification. Initially, the facial images are pre-processed using improved trilateral filter (ITF) for improving the quality of images. Next, the fusion of feature extraction and selection is performed using the DenseSNet. Here the extraction of deep features is done with the dense network and the relevant features are selected with the squeeze network. Finally, the last layer of squeeze network performs the classification of various facial emotions. Here, the loss in the classification is optimized using IRDO. This DenseSNet_IRDO architecture is more robust and avoids overfitting that occurs while training the small dataset. The datasets used in this work are CK[Formula: see text], JAFEE and FERFIN. The proposed FER classification using datasets CK[Formula: see text], JAFEE and FERFIN with DenseSNet_IRDO model achieved the accuracy of 99.91%, 99.90% and 99.89%, respectively. Thus, the proposed DenseSNet_IRDO classifier model obtained higher accuracy in the detection of FER than other methods.