| Autor: |
Veerappan, Manoj Kumar, Baskaran, Aravind Prasad, Venkatachalam, Senthil Balaji, Ramanujam, Rengaraj Alias Muralidharan, Narayanan, Lakshmi Kanthan |
| Předmět: |
|
| Zdroj: |
AIP Conference Proceedings; 2024, Vol. 2802 Issue 1, p1-9, 9p |
| Abstrakt: |
Since machines have high operational ability and analyze data much faster than humans, it is happened to keep trust on the machine than over the people. As per the quote "Face is the index of mind" the machine is needed to be taught with the phenomenon of Facial Emotion Recognition (FER) is significant for Human-Computer Interaction such as clinical practice and behavioral description. Accurate and robust FER by computer models remains challenging due to the heterogeneity of human faces and variations in images such as different facial pose and lighting. Among all techniques for FER, deep learning models, especially Convolutional Neural Networks (CNNs) have shown great potential due to their powerful automatic feature extraction and computational efficiency. In this work, the highest single-network classification accuracy has been achieved on the FER2013 dataset. The VGGNet architecture has been adopted, which fine-tune its hyperparameters rigorously, and experiment with various optimization methods. To our best knowledge, our model achieves state-of-the-art single-network accuracy of 73.28% on FER2013 without using external training data. [ABSTRACT FROM AUTHOR] |
| Databáze: |
Complementary Index |
| Externí odkaz: |
|
