EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Facial Expressions Images Generation Using Deep Convolutional Generative Adversarial Network (DCGAN)

Sabreen Ghanim, Ashwan A. Abdulmunem

Journal of Education for Pure Science · 01.03.2026 · 16 (1)

DOI: 10.32792/jeps.v16i1.827 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Education for Pure Science, online erschienen am 01.03.2026. Verfasst von Sabreen Ghanim und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This research presents a DCGAN (deep convolutional generative adversarial network) for synthesizing grayscale facial expressions. The generation of grayscale facial expressions is essential for affective computing and emotion analysis. We presented a Deep Convolutional Generative Adversarial Network model designed for generating monochrome facial expression images, which were considered across two benchmark datasets, FER-2013 and CK+. The proposed implementation also benefits from non-linearity by performing Pixel Normalization and LeakyReLU activation to enhance image similarity and training reliability. As a result, the study achieved an FID of 88 and an IS of 3.0 on FER-2013, and an FID of 0.5 and an IS of 2.0 on CK+, which indicates high achieved image quality and photorealism. In a similar vein, the results estimated data quality and network robustness as well as their interaction with the GAN’s achieved performance. When taken together, the proposed research may serve as a strong lightweight facial expression synthesis baseline, which is likely to stimulate future GAN research and identity-boosting synthesis.

Zitieren

APA

Ghanim, S., & Abdulmunem, A. A. (2026). Facial Expressions Images Generation Using Deep Convolutional Generative Adversarial Network (DCGAN). Journal of Education for Pure Science, 16(1). https://doi.org/10.32792/jeps.v16i1.827

Vancouver

Ghanim S, Abdulmunem AA. Facial Expressions Images Generation Using Deep Convolutional Generative Adversarial Network (DCGAN). Journal of Education for Pure Science. 2026;16(1). doi:10.32792/jeps.v16i1.827

BibTeX
@article{Ghanim2026,
  author = {Ghanim, Sabreen and Abdulmunem, Ashwan A.},
  title = {Facial Expressions Images Generation Using Deep Convolutional Generative Adversarial Network (DCGAN)},
  journal = {Journal of Education for Pure Science},
  year = {2026},
  volume = {16},
  number = {1},
  doi = {10.32792/jeps.v16i1.827}
}
Kostenlos starten →