Advanced Deep Learning Techniques for High-Quality Synthetic Thermal Image Generation
Mathematics · 27.10.2023 · 11 (21) · 4446
DOI: 10.3390/math11214446 ↗Kurz gefasst
Fachartikel in der Zeitschrift Mathematics, online erschienen am 27.10.2023. Verfasst von Vicente Pavez und 3 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: FONDECYT.
Abstract (Originalsprache)
In this paper, we introduce a cutting-edge system that leverages state-of-the-art deep learning methodologies to generate high-quality synthetic thermal face images. Our unique approach integrates a thermally fine-tuned Stable Diffusion Model with a Vision Transformer (ViT) classifier, augmented by a Prompt Designer and Prompt Database for precise image generation control. Through rigorous testing across various scenarios, the system demonstrates its capability in producing accurate and superior-quality thermal images. A key contribution of our work is the development of a synthetic thermal face image database, offering practical utility for training thermal detection models. The efficacy of our synthetic images was validated using a facial detection model, achieving results comparable to real thermal face images. Specifically, a detector fine-tuned with real thermal images achieved a 97% accuracy rate when tested with our synthetic images, while a detector trained exclusively on our synthetic data achieved an accuracy of 98%. This research marks a significant advancement in thermal image synthesis, paving the way for its broader application in diverse real-world scenarios.
Förderung
- FONDECYT
Zitieren
APA
Pavez, V., Hermosilla, G., Silva, M., & Farias, G. (2023). Advanced Deep Learning Techniques for High-Quality Synthetic Thermal Image Generation. Mathematics, 11(21), 4446. https://doi.org/10.3390/math11214446
Vancouver
Pavez V, Hermosilla G, Silva M, Farias G. Advanced Deep Learning Techniques for High-Quality Synthetic Thermal Image Generation. Mathematics. 2023;11(21):4446. doi:10.3390/math11214446
BibTeX
@article{Pavez2023,
author = {Pavez, Vicente and Hermosilla, Gabriel and Silva, Manuel and Farias, Gonzalo},
title = {Advanced Deep Learning Techniques for High-Quality Synthetic Thermal Image Generation},
journal = {Mathematics},
year = {2023},
volume = {11},
number = {21},
pages = {4446},
doi = {10.3390/math11214446}
}
EUVIMED