Bibliographic record
Abstract
Quality assessment of image data plays a vital role in various applications, e.g., the evaluation and optimization of visual processing algorithms and the monitoring of visual communication systems. Although subjective assessment is the most reliable means to measure image quality, it is not always feasible in practical applications. Therefore, objective image quality metrics (IQMs) that can accurately predict the subjective judgments of average human observers have gained considerable attentions from research community. In the past few decades, numerous IQMs have been proposed to estimate the perceived quality of visual data. Depending on the availability of a reference (i.e., perfect quality) image to compare with, they can be categorized into full-reference (FR) and no-reference (NR) IQMs. Most existing IQMs are designed to rely on image features in the grayscale domain. Despite their reasonable performance in dealing with traditional distortions (e.g. additive white Gaussian noise or Gaussian blur), such grayscale IQMs tend to underestimate the visual disturbance caused by chromatic distortions, e.g., degradation caused from color gamut mapping or tone mapping algorithms.\nThis study proposes new color IQMs capable of handling image data exhibiting both chromatic and achromatic distortions by incorporating perceptual color attributes, e.g., hue and chroma. Both FR and NR IQMs are introduced for different target applications. In particular, the proposed solutions properly process directional hue data using directional statistical tools, addressing the general limitation of existing approaches that treating hue data as linear data. Extensive validation performed on large-scale databases demonstrates the proposed IQMs correlate well with the subjective ratings over commonly encountered chromatic and achromatic distortions, indicating that the appropriate handling of highly informative hue data improves the prediction accuracy of color IQMs. These promising results indicate that they can be deployed on a wide range of color image processing problems as generalized quality assessment solutions.
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 | 0.006 | 0.011 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.004 | 0.003 |
| Science and technology studies | 0.000 | 0.002 |
| Scholarly communication | 0.004 | 0.004 |
| Open science | 0.003 | 0.003 |
| Research integrity | 0.001 | 0.003 |
| Insufficient payload (model declined to judge) | 0.002 | 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".