Enhancement Multi-class Facial Emotion Detection with Emo-VGGNet

Deep learning has the potential to solve computer vision problems, such as image classification and object detection. Facial emotional detection is maybe one of the most challenging problems in this field for many years with the rise of the Convolutional Neural Network (CNN). Many CNN models are available, including AlexNet, VGGNet, GoogLeNet, ResNet and SqueezeNet. In this research, we applied VGGNet for emotional detection, called Emo-VGGNet. We conducted several experiments to enhance the accuracy and efficiency of the models. The best accuracy performance of Emo- VGGNet was 99% for facial emotion detection with multi-class label classification.