Bergmann S, Moussa D, Rieß C (2026)
Publication Language: English
Publication Type: Journal article, Online publication
Publication year: 2026
Book Volume: 85
Article Number: 95
DOI: 10.1007/s11042-026-21317-3
Open Access Link: https://rdcu.be/e1YuJ
Many biometry methods extract task-relevant information from images. In forensic applications, these images may stem from uncontrolled sources like surveillance cameras in the wild. Such devices oftentimes strongly compress the data, which can significantly complicate biometric tasks. This issue is exacerbated by the emergence of AI compression, which may provide visually appealing images that are of questionable value for biometric identification. The purpose of this work is to investigate potential pitfalls of AI compression. We evaluate six AI compression methods including the recently standardized JPEG AI on the four biometric modalities of irises, fingerprints, fabrics and tattoos. We qualitatively show multiple cases when AI compression achieves misleading results. Tattoos in particular includes misrepresentations of color or shapes at strong compression rates. The quantitative evaluation shows impact on recognition rates when there are few identifying features, such as in low-resolution iris images. Further results show that compressors with MSE loss are prone to omit important image details, and MSE+LPIPS loss may hallucinate features. The findings in this paper aim at raising awareness to these pitfalls, and aiding the development robust biometric algorithms for images in the wild.
APA:
Bergmann, S., Moussa, D., & Rieß, C. (2026). Polished pixels: impact of AI compression on image-based evidence. Multimedia Tools and Applications, 85. https://doi.org/10.1007/s11042-026-21317-3
MLA:
Bergmann, Sandra, Denise Moussa, and Christian Rieß. "Polished pixels: impact of AI compression on image-based evidence." Multimedia Tools and Applications 85 (2026).
BibTeX: Download