EUVIMEDEUVIMED entdecken
Crossref

Thermal Emotion Recognition with and without Synthetic Facial Images using Attention-Based EfficientNet5

Tahir Aman, Sintayehu Hirpassa, Kibreab Adane

International Journal of Engineering and Manufacturing · 08.08.2026 · 16 (4) · 211-227

DOI: 10.5815/ijem.2026.04.15 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Engineering and Manufacturing, erschienen am 08.08.2026. Verfasst von Tahir Aman und 2 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Humans use emotions to express their feelings and effectively interact with others. Humans express emotions through hands, voice, gestures, and, most importantly, facial expressions. Facial emotion recognition is widely used in human-computer interaction, security, and healthcare. Traditional facial emotion recognition using visible light is often affected by changing lighting conditions. Thermal images could be used as an alternative solution because it relies on physiological heat patterns that remain consistent regardless of illumination. However, the use of thermal images for emotion recognition has not been extensively explored, primarily due to the scarcity of thermal image datasets. The study utilized the recently published Thermal Emotion dataset, which contains 2,250 thermal images before augmentation. After generating a synthetic dataset using cGAN, the datasets expanded to 6,823 images. To prevent dataset leakage, the study used 80% of the data for training, 10% for validation, and 10% for testing. The study used a bilateral filter to reduce noise while keeping relevant edge information, used CLAHE to enhance local contrast in low-intensity regions, making subtle thermal gradients more distinguishable, used Gaussian smoothing to reduce high-frequency noise, resulting in more stable feature extraction, and used attention mechanisms, CBAM, to allow the model to focus on emotion-relevant facial regions through its channel and spatial attention components. The combination of these techniques improved inter-class separability and contributed to measurable gains in recognition accuracy. The study findings show that inclusions of the bilateral filter, CLAHE cGAN, EfficientNetB5, and the CBAM attention mechanism significantly improved accuracy from 97.04% to 98.81%. For each experiment, ResNet18 classifies human facial emotions into five expressions: Happy, Sad, Angry, Natural, and Surprise. These findings imply that synthetic data generation using a cGAN to overcome data scarcity and an attention mechanism provides robust, lightning-independent solutions for facial emotion recognition.

Zitieren

APA

Aman, T., Hirpassa, S., & Adane, K. (2026). Thermal Emotion Recognition with and without Synthetic Facial Images using Attention-Based EfficientNet5. International Journal of Engineering and Manufacturing, 16(4), 211-227. https://doi.org/10.5815/ijem.2026.04.15

Vancouver

Aman T, Hirpassa S, Adane K. Thermal Emotion Recognition with and without Synthetic Facial Images using Attention-Based EfficientNet5. International Journal of Engineering and Manufacturing. 2026;16(4):211-227. doi:10.5815/ijem.2026.04.15

BibTeX
@article{Aman2026,
  author = {Aman, Tahir and Hirpassa, Sintayehu and Adane, Kibreab},
  title = {Thermal Emotion Recognition with and without Synthetic Facial Images using Attention-Based EfficientNet5},
  journal = {International Journal of Engineering and Manufacturing},
  year = {2026},
  volume = {16},
  number = {4},
  pages = {211--227},
  doi = {10.5815/ijem.2026.04.15}
}
Kostenlos starten →