A novel perception oriented image color representation
Bibliographic record
Abstract
The problem of representing image pixels in a way that is consistent with human perception is one of the essential problems in computer vision. An appropriate representation of pixels in an image can be of great help for the subsequent image analysis. A major kind of solutions for pixel color representation is to design novel color spaces from conventional sRGB color space so that the distance in the new color space can isotropically represent the color difference in the sense of human vision. Most of the color spaces, however, often transform the colors in the image using the same metrics. On the contrary, the human vision system can always auto adjust the sense of colors with respect to the view condition. In order to simulate the way that human perceives colors, we propose a novel color representation which can parameterize the color of each pixel with respect to the global color distribution in the current image. The underlying assumption of our proposed representation is the fact that the chrominance in a nature image is limited in the sense of human perception, and we call those colors as dominant colors in the image. We further assume that all the colors in a nature image can be modeled based on those dominant colors. Specifically, we first approximate the global image color distribution by the sum of a series of mixture Gaussian functions. The centroids of these Gaussian functions are regarded as the dominant colors of the image. In order to further model the colors not belonging to any of the Gaussian centroids, a simple linear model is proposed. Our proposed color representation explains the image color in a semantic way, and it can be easy to use for image analysis, such as segmentation, color editing, and compression.
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) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 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".