From Oracle to Predicted Masks: Auditing Protection Failures in Grayscale Fundus Image Watermarking on IDRiD
Journal of Imaging · 05.11.2026 · 12 (11) · 553
DOI: 10.3390/jimaging12110553 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 05.11.2026. Verfasst von Preeti Garg und 4 weiteren Autor:innen. Die Arbeit nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Watermark exclusion masks are often evaluated with reference annotations, although image issuance requires a mask that can be generated without them. We measured the difference on 27 IDRiD test fundus images using a sidecar-dependent block-DCT watermark in eight-bit grayscale. With a 64-bit payload, replacing background-only placement by a predicted protection mask reduced mean altered annotated pixels from 479.2 to 221.4 per image (paired mean reduction 257.9; 95% image-bootstrap CI 187.0–337.6). Alterations remained in 23 of 27 images. Class analysis showed no mean reduction for hemorrhages at 64 bits, while optic-disc changes declined by 162.8 pixels; the optic disc is normal anatomy. The lesion-only reduction was 31.2%, compared with 53.8% for the full union. A secondary mask augmented the prediction with a validation-selected green-channel contrast rule. On IDRiD, it reduced mean hemorrhage changes from 146.3 to 46.2 and microaneurysm changes from 12.0 to zero, while optic-disc changes rose from 11.5 to 19.0. On 148 annotated images from 68 visit folders in e-ophtha-MA, the fixed contrast rule reduced mean changes in the combined microaneurysm/small-hemorrhage annotation from 3.00 to 0.23 versus background-only placement (paired reduction 2.77; 95% visit-bootstrap CI 1.01–5.01). The original watermark was recovered exactly after JPEG compression, low-level noise and known-frame resizing, but failed under 3×3 median filtering. A five-head comparator yielded 222.8 mean union changes and 67.6% fewer eligible blocks than the original predictor. Median-filtered 64-bit outputs collapsed to zeros across 20 key/message draws; tested Hamming coding did not restore recovery. The results identify a class-dependent gap between reference and usable masks; the external label did not isolate hemorrhages, and frozen original-model transfer yielded only 3.42% mean exclusion recall.
Zitieren
APA
Garg, P., Gautam, M., Kumar, P., Maitrey, S., & Ranjan, P. (2026). From Oracle to Predicted Masks: Auditing Protection Failures in Grayscale Fundus Image Watermarking on IDRiD. Journal of Imaging, 12(11), 553. https://doi.org/10.3390/jimaging12110553
Vancouver
Garg P, Gautam M, Kumar P, Maitrey S, Ranjan P. From Oracle to Predicted Masks: Auditing Protection Failures in Grayscale Fundus Image Watermarking on IDRiD. Journal of Imaging. 2026;12(11):553. doi:10.3390/jimaging12110553
BibTeX
@article{Garg2026,
author = {Garg, Preeti and Gautam, Madhu and Kumar, Pushpendra and Maitrey, Seema and Ranjan, Pallavi},
title = {From Oracle to Predicted Masks: Auditing Protection Failures in Grayscale Fundus Image Watermarking on IDRiD},
journal = {Journal of Imaging},
year = {2026},
volume = {12},
number = {11},
pages = {553},
doi = {10.3390/jimaging12110553}
}
EUVIMED