Title: Local directional gradients extension for recognising face and facial expressions

Authors: Farid Ayeche; Adel Alti

Addresses: University of Ferhat Abbas Setif-1, Optics and Precision Mechanics Institute, LMETR Laboratory-E1764200, Setif, 19000, Algeria ' Department of Computer Science, Faculty of Sciences, LRSD Laboratory, University Ferhat Abbas Setif-1, Setif, 19000, Algeria; University of Management Information Systems and Production Management, College of Business and Economics, Qassim University, P.O. Box 6633, Buraidah, 51452, KSA

Abstract: This paper proposes new descriptors for recognising face and facial expressions. Our descriptors consist in combining local directional gradients with support vector machine (SVM) linear classification. This combination allows extracting discriminant facial expressions features for better classification accuracy with good efficiency than existing classifiers. Both descriptors are built based on the reduced texture features extracted from the face image based on magnitude and orientation maps on the horizontal and vertical coordinates. JAFFE and YALE benchmarks have been used to evaluate the accuracy and execution time of the requested face in the classification process. The experimental results are very promising and show that the proposed descriptors are effective and efficient compared to current works.

Keywords: facial image; facial expression recognition; FER; texture feature analysis; support vector machine; SVM; effectiveness; histogram of directional gradient; HDG.

DOI: 10.1504/IJISTA.2022.128525

International Journal of Intelligent Systems Technologies and Applications, 2022 Vol.20 No.6, pp.487 - 509

Accepted: 24 Aug 2022
Published online: 25 Jan 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article