Fiche publication
Date publication
avril 2026
Journal
Journal of imaging
Auteurs
Membres identifiés du Cancéropôle Est :
Pr PAINDAVOINE Michel
Tous les auteurs :
Robert,Madenda S, Harmanto S, Paindavoine M, Indarti D
Lien Pubmed
Résumé
This study proposes a morphological convolutional neural network (MCNN) architecture that integrates morphological operations with CNN layers for facial expression recognition (FER). Conventional CNN-based FER models primarily rely on appearance features and may be sensitive to illumination and demographic variations. This work investigates whether morphological structural representations provide complementary information to convolutional features. A multi-source and multi-ethnic FER dataset was constructed by combining CK+, JAFFE, KDEF, TFEID, and a newly collected Indonesian Facial Expression dataset, resulting in 3684 images from 326 subjects across seven expression classes. Subject-independent data splitting with 10-fold cross-validation was applied to ensure reliable evaluation. Experimental results show that the proposed MCNN1 model achieves an average accuracy of 88.16%, while the best MCNN2 variant achieves 88.7%, demonstrating competitive performance compared to MobileNetV2 (88.27%), VGG19 (87.58%), and the morphological baseline MNN (50.73%). The proposed model also demonstrates improved computational efficiency, achieving lower inference latency (21%) and reduced GPU memory usage (64%) compared to baseline models. These results indicate that integrating morphological representations into convolutional architectures provides a modest but consistent improvement in FER performance while enhancing generalization and efficiency under heterogeneous data conditions.
Mots clés
convolutional neural network, deep learning, facial expression recognition, mathematical morphology, multi-source dataset, subject-independent evaluation
Référence
J Imaging. 2026 04 15;12(4):
