Real-time Facial Emotion Recognition with Deep Neural Networks
Main Article Content
Abstract
Face emotions are an important part of human communications that helps to perceive others’ intentions and behaviours. This crucial element creates a connection and interpersonal communications can be apprehended using this factor. So, there is no wonder that numerous researches have been dedicated to this matter during recent decades and facial emotion recognition is a critical matter in computer vision and artificial intelligence. One of the challenges of AI is to achieve high accuracy and great performance in the model. Fortunately, this has been dealt with by emerging deep learning networks and setting aside traditional machine learning methods. In this study, we established a model called ResEZAP (Residual Extended Zero Average Pooling) of deep learning networks for real-time facial emotion recognition and achieving an acceptable accuracy by reducing computational complexity. In this paper, the FER2013 dataset is used for training and the model accuracy with the test dataset is 69.74.
Downloads
Metrics
Article Details
Licensing
TURCOMAT publishes articles under the Creative Commons Attribution 4.0 International License (CC BY 4.0). This licensing allows for any use of the work, provided the original author(s) and source are credited, thereby facilitating the free exchange and use of research for the advancement of knowledge.
Detailed Licensing Terms
Attribution (BY): Users must give appropriate credit, provide a link to the license, and indicate if changes were made. Users may do so in any reasonable manner, but not in any way that suggests the licensor endorses them or their use.
No Additional Restrictions: Users may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
