Group based emotion recognition from video sequence with hybrid optimization based recurrent fuzzy neural network

Abstract

One of the major and fundamental issue is emotion recognition during the development of an interactive computer system [1-3]. Recognition of facial emotion/expression is essential, because nowadays it place its wide applications in various sectors like psychological distress and pain detection [4]. Some fields like psychology, sociology, and automatic expression recognition, therefore provided a considerable importance for this emotion recognition process to create a highly user affable software and user agents in these fields. This process of automatic facial expression recognition (FER) has exhibited its large implications in the human computer interaction (HCI) field [5]. Recently, the affective computing is considered as the most significant study field in HCI, which highly intends to improve the human-machine interaction by clearly recognizing the emotion Abstract Group-based emotion recognition (GER) is an interesting topic in both security and social area. In this paper, a GER with hybrid optimization based recurrent fuzzy neural network is proposed which is from video sequence. In our work, by utilizing the Neural Network the emotion recognition (ER) is performed from group of people. Initially, original video frames are taken as input and pre-process it from multi user video data. From this pre-processed image, the feature extraction is done by Multivariate Local Texture Pattern (MLTP), gray-level co-occurrence matrix (GLCM), and Local Energy based Shape Histogram (LESH). After extracting the features, certain features are selected using Modified Sea-lion optimization algorithm process. Finally, recurrent fuzzy neural network (RFNN) classifier based Social Ski-Driver (SSD) optimization algorithm is proposed for classification process, SSD is used for updating the weights in the RFNN. Python platform is utilized to implement this work and the performance of accuracy, sensitivity, specificity, recall and precision is evaluated with some existing techniques. The proposed method accuracy is 99.16%, recall is 99.33%, precision is 99%, sensitivity is 99.93% and specificity is 99% when compared with other deep learning techniques our proposed method attains good result.

[Retracted] Automatic Detection Method of Technical and Tactical Indicators for Table Tennis Based on Trajectory Prediction Using Compensation Fuzzy Neural Network

“…e recurrent compensation fuzzy neural network is the combination of the recurrent neural network and compensation fuzzy algorithm. It has both the characteristics of the recurrent neural network and the advantages of the compensation fuzzy algorithm and has good ability to solve the corresponding sequence prediction problems [32][33][34]. As shown in Figure 5, it is the topology of the recurrent compensation fuzzy neural network.…”

Facial expression recognition for low resolution images using convolutional neural networks and denoising techniques

“…The proposed model achieved 99.16% accuracy 99.33% recall 99% precision and 99.93% sensitivity. This method achieved 87.8% accuracy on low resolution images (12) . The issue with facial expression recognition field is small size dataset.…”

Emotional Analysis Model for Social Hot Topics of Professional Migrant Workers

“…The cognitive evaluation of an emotion model for external stimulus signals should begin with the individual's intention and evaluation criteria for the evaluation subject, and then learn from the literature method [ 28 ]. Individuals' subjective wishes, preferences, and individual evaluation criteria determine their emotional expression, so the emotion model should pay attention to the design of wishes, preferences, and evaluation criteria for the cognition of stimulus signals.…”