Title:
RESEARCH ON EMOTION RECOGNITION BASED ON FACIAL EXPRESSIONS

Authors:
Yukuan He and Hongli Zhu

Abstract:
With the development of science and technology, emotion recognition has been integrated into every aspect of our life, whether in medical services, public safety or in human-computer interaction, the demand for emotion recognition technology is expanding, therefore, in recent years, emotion recognition based on facial expressions is still a research hotspot. Traditional methods for emotion recognition by extracting extracted feature points and feature classification require a lot of manual operations, and the accuracy and precision are not high. In this paper, we adopt the algorithm of deep learning of convolutional neural network to train the images. the data set used is FER2013, the system can get the picture in real time through the camera for recognition, or by reading the input The experimental results show that the deep learning algorithm for emotion recognition research has higher accuracy and robustness.

Keywords:
: facial expression, emotion recognition, convolutional neural network, deep learning, accuracy

DOI:
http://dx.doi.org/10.52267/IJASER.2021.2404