Image Facial Expression Recognition based on Active Muscles and their Notable Triangle Points
Journal
2025 21st International Symposium on Biomedical Image Processing and Analysis (SIPAIM)
Publisher
IEEE
Date Issued
2025
Author(s)
Aguilera-Hernández, Edgar I.
Cruz-Aceves, Ivan
Hernández-Aguirre, Arturo
Type
text::conference output::conference proceedings
Abstract
During emotion experience originated in psychological changes, the effect in face muscles results in a characteristic set of contractions associated to specific emotions. This paper propose an intuitive representation of these interactions with the objective of facial expression recognition through geometric features. In medical research, it has generated insights regarding emotional state, cognitive function, and pain level during clinical procedures leading to an effective patient treatment, assisting diagnosis and monitoring disease progression mainly in neurological conditions. Starting from a facial muscle modeling using triangles, it utilizes an initial 68 landmarks fitting algorithm, and later the computation of triangle notable points to work as anchors of specific muscles. Secondly, the optimization process through stochastic techniques is applied to set the point type combination so that the F1-Score is maximized. Experimental results were performed with conventional classifiers and no fine tuning, accomplishing an accuracy, precision, recall and F1-score of 0.88 for KDEF dataset, while 0.84, 0.86, 0.84, and 0.84 respectively for the JAFFE dataset, proving to be a reliable technique in the expression recognition problem. ©The authors ©IEEE.
License
Acceso Restringido
How to cite
Aguilera-Hernández, E. I., Cruz-Aceves, I., Hernández-Aguirre, A., Moya-Albor, E., & Brieva, J. (2025). Image Facial Expression Recognition based on Active Muscles and their Notable Triangle Points. In 2025 21st International Symposium on Biomedical Image Processing and Analysis (SIPAIM) (pp. 1–5). IEEE. 2025 21st International Symposium on Biomedical Image Processing and Analysis (SIPAIM). https://doi.org/10.1109/sipaim67325.2025.11283199