Article: Face expression classification and recognition based on LBP+GLCM features and attention mechanism in CNN Journal: International Journal of Applied Pattern Recognition (IJAPR) 2025 Vol.8 No.1 pp.1 - 15 Abstract: We propose a lightweight facial expression recognition (FER) model that integrates local binary pattern (LBP) and grey level co-occurrence matrix (GLCM) hybrid features with a channel attention mechanism based on the ECA.Net variant to effectively balance the accuracy-efficiency trade-offs. This model leverages texture features extracted via LBP and LBP+GLCM, combined with attention mechanisms to enhance the focus on salient facial cues. Built upon the VGG16 CNN architecture within the TensorFlow framework, the model was tested on the FER2013 and RAF-DB datasets for cross-validation, achieving a recognition accuracy of 79.89% and 86.77%, respectively. To validate its practical effectiveness, a deployable QT-based user interface system was developed, enabling real-time FER from images, videos, and live camera feeds. This approach aims to meet the increasing demand for lightweight, reliable solutions, particularly in scenarios with limited computational resources, while maintaining high recognition accuracy. Inderscience Publishers - linking academia, business and industry through research

Title: Face expression classification and recognition based on LBP+GLCM features and attention mechanism in CNN

Authors: Xia Zhang; Caini Yan

Addresses: School of Intelligent Manufacturing, Longdong University, Qingyang City, Gansu Province 745000, China ' School of Literature and History, Longdong University, Qingyang City, Gansu Province 745000, China

Abstract: We propose a lightweight facial expression recognition (FER) model that integrates local binary pattern (LBP) and grey level co-occurrence matrix (GLCM) hybrid features with a channel attention mechanism based on the ECA.Net variant to effectively balance the accuracy-efficiency trade-offs. This model leverages texture features extracted via LBP and LBP+GLCM, combined with attention mechanisms to enhance the focus on salient facial cues. Built upon the VGG16 CNN architecture within the TensorFlow framework, the model was tested on the FER2013 and RAF-DB datasets for cross-validation, achieving a recognition accuracy of 79.89% and 86.77%, respectively. To validate its practical effectiveness, a deployable QT-based user interface system was developed, enabling real-time FER from images, videos, and live camera feeds. This approach aims to meet the increasing demand for lightweight, reliable solutions, particularly in scenarios with limited computational resources, while maintaining high recognition accuracy.

Keywords: attention mechanism; facial expression recognition; FER; convolutional neural network; CNN; FER2013 dataset; RAF-DB dataset; local binary pattern; LBP.

DOI: 10.1504/IJAPR.2025.150992

International Journal of Applied Pattern Recognition, 2025 Vol.8 No.1, pp.1 - 15

Received: 10 Feb 2025
Accepted: 26 Aug 2025
Published online: 07 Jan 2026 *

Title: Face expression classification and recognition based on LBP+GLCM features and attention mechanism in CNN

Keep up-to-date