Real Time Facial Expression Recognition System Based on Deep Learning

Abstract

The automatic detection of facial expressions is an active research topic, since its wide fields of applications in human-computer interaction, games, security or education. However, the latest studies have been made in controlled laboratory environments, which is not according to real world scenarios. For that reason, a real time Facial Expression Recognition System (FERS) is proposed in this paper, in which a deep learning approach is applied to enhance the detection of six basic emotions: happiness, sadness, anger, disgust, fear and surprise in a real-time video streaming. This system is composed of three main components: face detection, face preparation and face expression classification. The results of proposed FERS achieve a 65% of accuracy, trained over 35558 face images..

Untitled

“…Machine learning is a technique to implement artificial intelligence (Mediaroom Solutions, 2019;Bustamante, Rodriguez, & Esenarro, 2019), without programming millions of rules and decision trees.…”

Convolutional Neural Networks on Assembling Classification Models to Detect Melanoma Skin Cancer

“…Training and evaluation strategy Based on the statistical principle "Pareto's Law," a proposed training and evaluation split of 80 and 20. This law describes the statistical phenomenon whereby a small proportion of any population contributing to a common effect [44] contributes to most of the impact. The 80/20 rule suggests that, in any given example, the few (20%) are vital and the many (80%) are trivial.…”

“…See Figure 1. [44] Note: Division of training and evaluation (80/20), followed by the application of K-Fold.…”