EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Morphological Convolutional Neural Network for Efficient Facial Expression Recognition

Robert iD, Sarifuddin Madenda iD, Suryadi Harmanto iD, Michel Paindavoine iD, Dina Indarti iD

Journal of Imaging · 15.04.2026 · 12 (4) · 171

DOI: 10.3390/jimaging12040171 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 15.04.2026. Verfasst von Robert und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Informatic Engineering, Gunadarma University, Depok 16424, Indonesia. Die Arbeit nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Higher Education, Science, and Technology, Indonesia, Indonesia Ministry of Higher Education, Science, and Technology.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Schlagwörter

Stichwörter der Autor:innen

convolutional neural networkdeep learningfacial expression recognitionmathematical morphologymulti-source datasetsubject-independent evaluation

Autor:innen und Institutionen

  • Department of Informatic Engineering, Gunadarma University, Depok 16424, Indonesia.
  • LEAD, CNRS, UMR5022, Université Bourgogne Europe, 11 Esplanade Erasme, 21000 Dijon, France.

ORCID-Profile: Robert, Sarifuddin Madenda, Suryadi Harmanto, Michel Paindavoine, Dina Indarti

Förderung

  • Ministry of Higher Education, Science, and Technology, Indonesia
  • Indonesia Ministry of Higher Education, Science, and Technology

Zitieren

APA

Robert, Madenda, S., Harmanto, S., Paindavoine, M., & Indarti, D. (2026). Morphological Convolutional Neural Network for Efficient Facial Expression Recognition. Journal of Imaging, 12(4), 171. https://doi.org/10.3390/jimaging12040171

Vancouver

Robert, Madenda S, Harmanto S, Paindavoine M, Indarti D. Morphological Convolutional Neural Network for Efficient Facial Expression Recognition. Journal of Imaging. 2026;12(4):171. doi:10.3390/jimaging12040171

BibTeX
@article{Robert2026,
  author = {Robert and Madenda, Sarifuddin and Harmanto, Suryadi and Paindavoine, Michel and Indarti, Dina},
  title = {Morphological Convolutional Neural Network for Efficient Facial Expression Recognition},
  journal = {Journal of Imaging},
  year = {2026},
  volume = {12},
  number = {4},
  pages = {171},
  doi = {10.3390/jimaging12040171}
}
Kostenlos starten →