Facial Emotion Detection Using Deep Learning

Abstract— Human emotion detection from images is one of the most significant and challenging research tasks in social communication. Deep learning (DL)-based emotion detection provides better performance than traditional image processing methods. This paper presents the design of an artificial intelligence (AI) system capable of detecting emotions through facial expressions. It discusses the procedure of emotion detection, which mainly involves three steps: face detection, feature extraction, and emotion classification. This paper proposes a convolutional neural network (CNN)-based deep learning architecture for emotion detection from images. The performance of the proposed method is evaluated using two datasets: Facial Emotion Recognition Challenge (FER-2013) and Japanese Female Facial Expression (JAFFE). The accuracies achieved by the proposed model are 70.14% and 98.65% for the FER-2013 and JAFFE datasets, respectively. Index Terms—Artificially intelligence (AI), Facial emotion recognition (FER), Convolutional neural networks (CNN), Rectified linear units (ReLu), Deep learning (DL).