Efficient-SwishNet Based System for Facial Emotion Recognition

Abstract

Facial emotion recognition (FER) is an important research area in artificial intelligence and has many applications i.e., face authentication systems, e-learning, entertainment, deepfakes detection, etc. FER is still a challenging task due to more intra-class variations of emotions. Although existing deep learning methods have achieved good performance for FER. However, still there exists a need to develop efficient and effective FER systems robust to certain conditions i.e., variations in illumination, face angles, gender, race, background settings and people belonging to diverse geographical regions. Moreover, a generalized model for classification of human emotions is required to be implemented in computer systems so that they can interact with humans according to their emotions and improve their interaction. This work presents a novel light-weight Efficient-SwishNet model for emotion recognition that is robust towards the aforementioned conditions. We have introduced a low-cost, smooth unbounded above and bounded below Swish activation function in our model. Property of unboundedness helps to avoid saturation while smoothing helps in optimization and generalization of the model. Performance of the proposed model is evaluated on five diverse datasets including CK+, JAFFE, FER-2013, KDEF and FERG datasets. We also performed cross-corpora evaluation to show the generalizability of our model. The proposed model achieves very high recognition rate for all datasets that proves the merit of the proposed framework for both the human facial images and stylized cartoon characters. Moreover, we conducted an ablation study with different variants of our model to prove its efficiency and effectiveness for emotions identification.

Simple Histogram Equalization Technique Improves Performance of VGG Models on Facial Emotion Recognition Datasets

“…Using a generalized adaptive (N+M)-tuplet cluster loss function and identity-aware mining schemes, the proposed method achieved an accuracy of approximately 97.1% on the CK+ dataset and 78.53% on the MMI dataset [64]. Dar et al used EfficientNet-b0 for feature extraction and transfer learning due to its accuracy and computational efficiency balance [65]. They customized the EfficientNet-b0 architecture by incorporating Swish activation functions after every 2D convolution layer, enhancing performance through non-monotonic, smooth unbounded above/bounded below properties.…”

“…Puthanidam [61] Hybrid CNN 89.58% Chen et al [62] ACD 99.12% Dar et al [65] Efficient-SwishNet 88.3% Fei et al [68] MobileNet + SVM 86.4% Mahesh et al [73] Feed-Forward Network 88.87% Sahoo et al [72] Pre-trained VGG19 93% Proposed Model…”

Algorithms used for facial emotion recognition: a systematic review of the literature

“…Subsequently, these facial expressions become a key mechanism for conveying and understanding emotions, an inevitable part of human-computer interaction, and a key technology in the field of artificial intelligence (14). Furthermore, ELsayed et al (2023) argue that there are various categories of emotions that can be classified as anger, happiness, fear, surprise, contempt, disgust, and sadness (18).…”

“…A Convolutional Neural Network (CNN) has one or more convolutional layers, they are grouping layers and fully connected and are used in image recognition. CNN can be applied to 2D and 3D data arrays, and uses image processing after collecting data that have different formats, i.e., natural, false, grayscale (18).…”

“…Creates binary code at each pixel in the neighborhood according to the central pixel value. The feature selection algorithm used is derived from LBP for all available images, LBP extracts features and CNN classifies images into groups according to facial expressions (18). It compares the intensity of pixels with their neighbors to obtain Local Binary Patterns (LBP) (27).…”