Article: Facial expression recognition based on YOLOv8 deep learning in complex scenes Journal: International Journal of Information and Communication Technology (IJICT) 2025 Vol.26 No.1 pp.89 - 101 Abstract: Accurate and effective facial expression recognition (FER) is of great significance in fields such as intelligent monitoring and emotional computing today. This article proposes a deep learning method based on You Only Look Once Version 8 (YOLOv8), which combines YOLOv8's real-time and efficient object detection capabilities with the feature extraction advantages of convolutional neural networks (CNNs) to improve facial expression recognition performance in complex environments. Firstly, YOLOv8 is used for precise facial detection. Then, the detected facial regions are fed into a feature extraction network, which extracts high-level features related to facial expressions through deep CNN, enhancing the robustness of the model to different complex scenes. The results of the experiment indicate that our approach performs well on publicly available facial expression datasets, especially in complex scenes where it significantly outperforms traditional expression recognition methods. This model provides new ideas for future applications in diverse, dynamic, and complex environments. Inderscience Publishers - linking academia, business and industry through research

Title: Facial expression recognition based on YOLOv8 deep learning in complex scenes

Authors: Chujie Xu; Yong Du; Wenjie Zheng; Tiejun Li; Zhansheng Yuan

Addresses: School of Ocean Information Engineering, Jimei University, Xiamen, 361021, China ' School of Ocean Information Engineering, Jimei University, Xiamen, 361021, China ' School of Ocean Information Engineering, Jimei University, Xiamen, 361021, China ' School of Ocean Information Engineering, Jimei University, Xiamen, 361021, China ' School of Ocean Information Engineering, Jimei University, Xiamen, 361021, China

Abstract: Accurate and effective facial expression recognition (FER) is of great significance in fields such as intelligent monitoring and emotional computing today. This article proposes a deep learning method based on You Only Look Once Version 8 (YOLOv8), which combines YOLOv8's real-time and efficient object detection capabilities with the feature extraction advantages of convolutional neural networks (CNNs) to improve facial expression recognition performance in complex environments. Firstly, YOLOv8 is used for precise facial detection. Then, the detected facial regions are fed into a feature extraction network, which extracts high-level features related to facial expressions through deep CNN, enhancing the robustness of the model to different complex scenes. The results of the experiment indicate that our approach performs well on publicly available facial expression datasets, especially in complex scenes where it significantly outperforms traditional expression recognition methods. This model provides new ideas for future applications in diverse, dynamic, and complex environments.

Keywords: facial recognition; facial expression recognition; FER; convolutional neural network; CNN; YOLOv8.

DOI: 10.1504/IJICT.2025.144013

International Journal of Information and Communication Technology, 2025 Vol.26 No.1, pp.89 - 101

Received: 27 Oct 2024
Accepted: 25 Nov 2024
Published online: 20 Jan 2025 *

Title: Facial expression recognition based on YOLOv8 deep learning in complex scenes

Keep up-to-date