Image watermarking in the Hermite transform domain with resistance to geometric distortions
Bibliographic record
Abstract
This paper proposes a novel perceptual watermarking scheme operating in a Hermite transform domain. To achieve an acceptable level of watermark invisibility, masking properties of the Human Vision system (HVS) are exploited in the extraction of relevant local image features (texture, smooth regions, edges) for watermark embedding purpose. Many other works suggest the use of wavelets or contourlets. In our case, image features are extracted efficiently from the Hermite transform image representation which agrees with the Gaussian derivative model of the human visual perception. The resulting weighing mask is used to adapt the watermark strength to image regions during the embedding process. In order to ensure watermark resistance to global affine geometric attacks (rotation, scaling, translation and shearing) the design of the watermarking scheme is modified, mainly, by incorporating a normalization procedure. Image normalization, a means to achieve invariance to geometric transformations, is well known in computer vision and pattern recognition areas. In this new design, both watermark embedding and detection are carried out in the Hermite transform domain of moment-based normalized images. A sequence of tests is conducted on various images. Many removal attacks (JPEG compression, additive noise and filtering) as well as geometric attacks are applied from the Checkmark benchmark. Experimental results show the effectiveness of the whole scheme in achieving its goals in terms of watermark invisibility and robustness.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".