An optimal hybrid deep learning-aided facial emotion detection and classification scheme to identify criminal activities

In general, the most significant field of research presently is the identification & recognition of facial expressions or emotions. Moreover, recognition and categorization of face emotion are vital in several areas of research like criminal activities investigation, innovative card application, security, surveillance system and so on. Among these, criminal investigation plays a vibrant part. There exist several methods for facial emotion/expression recognition (FER) systems; however there were some drawbacks like low prediction rate, lower recognition rate, high error rate and so on. For rectifying these existing issues, a new enhanced optimal Deep learning (DL)-based model is presented in this manuscript. In this work, an input facial dataset is extracted and preprocessed using Weighted fuzzy Histogram Equalization (WF-HE). From this, the features are extracted using Deep CNN, followed by an Enhanced glowworm swarm optimization (EGSO)-based feature selection model, at which hyper-parameter tuning is carried out by attaining fitness function values. This, in turn, enhances the performance of the classifier. The categorization for the FER system is carried out using a Hybrid Deep Variational LSTM (DVLSTM) and DenseNet model. The results are estimated in terms of various performance measures, and the analysis is made on three input datasets such as JAFFE, Extended CK+ and FER2013 dataset.