Automatic Facial Expression Recognition Based on the Salient Facial Patches

Rejila. R .C; Monisha Menon

CALL FOR PAPERS : Feb-2026

Submission Last Date

25-Feb-26

Submit Manuscript Online

FOR AUTHORS

FOR REVIEWERS

ARCHIEVES

DOWNLOADS

Open Access

Automatic Facial Expression Recognition Based on the Salient Facial Patches

Author(s):

Rejila. R .C , MARIAN ENGINEERING COLLEGE THIRUVANATHAPURAM; Monisha Menon, MARIAN ENGINEERING COLLEGE THIRUVANATHAPURAM

Keywords:

Artificial neural network, Facial expression analysis, Facial landmark detection, Feature extraction, Salient facial patches

Abstract:

Facial expression is an important channel for human communication and it can be applied in many real applications. Facial Expression Recognition is usually performed in three-stages consisting of face detection, feature extraction, and expression classification. The accurate detection of facial landmarks improves the salient patches on face images. This paper proposes a framework for expression recognition by using appearance features of selected facial patches. In some facial patches depending on the position of facial landmarks, these are extracted which are active during emotion elicitation. These active patches are processed to obtain the salient patches. Then artificial neural network and support vector machine is used to classify these features. Then an automated learning-free facial landmark detection technique has been proposed, which achieves similar performances as that of other landmark detection methods, it requires significantly less execution time and better recognition accuracy. The proposed methods are performed well in different resolutions and it providing a solution for expression recognition in low resolution images.