Raqamli Transformatsiya va Sun’iy Intellekt
FACIAL EMOTION RECOGNITION USING SHALLOW CONVOLUTIONAL NEURAL NETWORK AND IMPROVED FER-2013 DATASET
1 Jizzakh branch of National University of Uzbekistan named after Mirzo Ulugbek.
Abstract
It is very easy and simple for a person to sense his inner feelings by looking at his face. That is, in the process of evaluating the emotional state of the person standing in front of him, the human brain sees the facial structure of the other person and can quickly analyze it. However, the ability of a computer to understand and respond to human emotions is considered one of the most difficult problems in the fields of modern computer vision and deep learning. Despite the fact that many studies have been carried out on the evaluation of the emotional state of a person, the proposed solutions are not effective enough. Several convolutional neural network models developed in this field can also solve the problem in a rather narrow scope. In this article, we proposed a shallow convolutional neural network and an augmented and improved fer-20103 dataset in order to speed up the training process and improve previous results. The proposed architecture was tested and analyzed on an updated dataset.
References
No references listed for this article.