EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Facial Emotion Recognition Based on Improved ResNet50 Using Hybrid Pooling and Adaptive Leaky ReLU

Rasha Thamer Shawi, Ahmed Abd Ali Abdulkadhim, Farah Neamah Abbas

International Journal of Scientific Research in Science, Engineering and Technology · 01.06.2025 · 12 (3) · 728-737

DOI: 10.32628/ijsrset251290 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Scientific Research in Science, Engineering and Technology, online erschienen am 01.06.2025. Verfasst von Rasha Thamer Shawi und 2 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Given the broad applications of facial emotion recognition technology, it has gained significant attention in recent years, spanning many fields, including human-computer interaction, healthcare, market research, and economic requirements. There are several types of emotions in humans, including anger, disgust, fear, happiness, neutrality, sadness, and surprise. Through these expressions, Methods can be implemented Facial emotion recognition. The ResNet50 improvement proposed aims to improve the representation and classification of facial expressions. In this study, we improve Resnet50 in two important areas to improve its efficiency. The first is to replace global average pooling with hybrid pooling and use a learnable α weight. The second is to improve Adaptive Leaky ReLU using a learnable parameter during training. In order to verify the validity of the proposed improvement, we used the well-known FER2013 and CK+ datasets and the proposed method showed an accuracy of 96.6% and 96.32%, respectively.

Zitieren

APA

Shawi, R. T., Abdulkadhim, A. A. A., & Abbas, F. N. (2025). Facial Emotion Recognition Based on Improved ResNet50 Using Hybrid Pooling and Adaptive Leaky ReLU. International Journal of Scientific Research in Science, Engineering and Technology, 12(3), 728-737. https://doi.org/10.32628/ijsrset251290

Vancouver

Shawi RT, Abdulkadhim AAA, Abbas FN. Facial Emotion Recognition Based on Improved ResNet50 Using Hybrid Pooling and Adaptive Leaky ReLU. International Journal of Scientific Research in Science, Engineering and Technology. 2025;12(3):728-737. doi:10.32628/ijsrset251290

BibTeX
@article{Shawi2025,
  author = {Shawi, Rasha Thamer and Abdulkadhim, Ahmed Abd Ali and Abbas, Farah Neamah},
  title = {Facial Emotion Recognition Based on Improved ResNet50 Using Hybrid Pooling and Adaptive Leaky ReLU},
  journal = {International Journal of Scientific Research in Science, Engineering and Technology},
  year = {2025},
  volume = {12},
  number = {3},
  pages = {728--737},
  doi = {10.32628/ijsrset251290}
}
Kostenlos starten →