Hybrid Facial Emotion Recognition Using CNN-Based Features

In computer vision, the convolutional neural network (CNN) is a very popular model used for emotion recognition. It has been successfully applied to detect various objects in digital images with remarkable accuracy. this paper, we extracted learned features from pre-trained CNN and evaluated different machine learning (ML) algorithms perform classification. Our research looks at impact of replacing standard SoftMax classifier other ML by applying them FC6, FC7, FC8 layers Deep Convolutional Neural Networks (DCNNs). Experiments were conducted on two well-known architectures, AlexNet VGG-16, using dataset masked facial expressions (MLF-W-FER dataset). The results our experiments demonstrate that Support Vector Machine (SVM) Ensemble classifiers outperform both VGG-16 architectures. These able achieve improved accuracy between 7% 9% each layer, suggesting layer DCNN SVM or ensemble can be an efficient method enhancing image classification performance. Overall, demonstrates potential combining strengths CNNs better recognition tasks. By extracting variety classifiers, provide framework investigating alternative methods improve