Empirical Analysis of Textural and Edge Features for Deepfake Detection
IBIMA Business Review · 01.04.2026
DOI: 10.5171/2025.4632525 ↗Kurz gefasst
Fachartikel in der Zeitschrift IBIMA Business Review, online erschienen am 01.04.2026. Verfasst von Karol JEDRASIAK.
Abstract (Originalsprache)
This study evaluates interpretable textural and edge descriptors for deepfake detection under real-world conditions. Using the new DFRW dataset with 46 371 clips from diffusion and face-swap models, classical features showed strong robustness to compression and re-encoding. The best-performing descriptors: CLBP, LBP, BSIF, HOG, structure tensor coherence, MBH, and checkerboard index, achieved Δp≈0.25–0.30 with stable accuracy above 720p. The results provide quantitative evidence that physics-based, explainable features can reliably separate fake from real content, advancing transparent forensic detection.
Zitieren
APA
JEDRASIAK, K. (2026). Empirical Analysis of Textural and Edge Features for Deepfake Detection. IBIMA Business Review. https://doi.org/10.5171/2025.4632525
Vancouver
JEDRASIAK K. Empirical Analysis of Textural and Edge Features for Deepfake Detection. IBIMA Business Review. 2026. doi:10.5171/2025.4632525
BibTeX
@article{JEDRASIAK2026,
author = {JEDRASIAK, Karol},
title = {Empirical Analysis of Textural and Edge Features for Deepfake Detection},
journal = {IBIMA Business Review},
year = {2026},
doi = {10.5171/2025.4632525}
}
EUVIMED