Efficient image region and shape detection by perceptual contour grouping
Bibliographic record
Abstract
Image region detection aims to extract meaningful regions from image. This task may be achieved equivalently by finding the interior or boundaries of regions. The advantage of the second strategy is that once a closure is detected not only its shape information is available, but also the interior property can be estimated with a minimum effort. In this paper, we present a novel method that detects region though region contour grouping based on generic edge token (GET). GETs are a set of perceptually distinguishable edge segment types including linear and non-linear features. In our method, an image is first transformed into GET space on the fly represented by a GET graph. A GET graph presents perceptual organization of GET associations. Two types of perceptual closures, basic contour closure and object contour closure, based upon which all meaningful regions are conducted, are defined and then detected. The detection is achieved by tracking approximate adjacent edges along the GET graph to group the contour closures. Because of the descriptive nature of GET representation, the perceptual structure of detected region shape can be estimated easily based its contour GET types. By using our method, all and only perceptual closures can be extracted quickly. The proposed method is useful for image analysis applications especially real time systems like robot navigation and other vision based automation tasks. Experiments are provided to demonstrate the concept and potential of the method.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| 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) | 0.002 | 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".