Facial Expression Recognition to Aid Visually Impaired People

Abstract

Facial expression recognition systems can help a visually impaired person to identify the emotions of the person with whom she interacts, assisting in her non-verbal communication. Among the various researches carried out in recent years on recognition of facial expressions, the best results obtained come from methods that use deep learning, mainly with the use of convolutional neural networks. This work presents a literature review on the problem of recognition of facial expressions, through the use of convolutional neural networks and proposes two approaches in which the first one uses pre-trained CNN models together with the Linear SVM classifier that, applied to the bases CK+ and JAFFE data, obtained maximum accuracy of 89.6% and 95.7%, respectively. And in the second approach, a CNN model built from scratch is used with the CK+ and FER2013 databases, which obtained accuracy rates of 85% and 65.8%, respectively.