A novel PSO-ViT approach for facial emotion recognition

ABSTRACT

Facial Emotion Recognition is gaining interest from researchers in various fields due to its numerous applications. The Vision Transformer (ViT) outperforms convolutional neural network (CNN)-based systems significantly in terms of performance when compared to contemporary image categorisation algorithms. In this context, the primary objective of this paper is to present an innovative and efficient deep learning model for facial emotion recognition. This hybrid intelligent model combines the Vision Transformer with Particle Swarm Optimization (PSO). The proposed model accurately identified the majority of emotions in images, achieving an accuracy of 95.93% for the Fer2013plus dataset and 100% for the CK+ dataset, as demonstrated through experiments conducted on both datasets. According to the results, the proposed facial expression recognition approach has either outperformed or closely matched the performance of state-of-the-art methods.

KEYWORDS:

• Facial emotion recognition
• Vision Transformer
• particle swarm optimization

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Funding

There has been no financial support for this work.

Notes on contributors

Imtiez Fliss

Imtiez Fliss is a Computer Science Assistant Professor at the National School of Computer Sciences, University of Manouba, Tunisia. She earned her engineering degree in Computer Science from the National School of Computer Sciences (Tunisia) in 2008, followed by a master’s degree in Artificial Intelligence and Decision Making in 2009, and a Ph.D. in Computer Science in 2013. Currently, she serves as the Head of the Robotics and Soft Computing team at Laria Laboratory. Her research interests span Decision Making, Artificial Intelligence, Soft Computing, Text Mining, Sentiment Analysis, Computer Vision, and the diagnosis and prognosis of multiple faults in continuous, discrete, and hybrid complex systems.

Wiem Zemzem

Wiem Zemzem studied at the National School of Computer Sciences, Manouba University, in Tunisia, where she received her computer engineering degree in 2011, her master of computer science in 2012, and her PhD thesis in 2017. She taught at several institutions including the Higher School of Economic and Commercial Sciences of Tunis, the Higher Institute of Technological Studies in Communications of Tunis (Tunisia) and the College of Computer and Information Science at Jouf University (Saudi Arabia). Since 2022, she has been an Assistant Professor at the Higher School of Communication in Tunis. Her research interests primarily focus on machine learning and autonomous systems.