Improving image segmentation using edge information
Bibliographic record
Abstract
We report methods for image segmentation that combine region growing and edge detection. Existing schemes that use region-based processing provide unambiguous segmentation, but they often divide regions that are not clearly separated, while merging regions across a break in an otherwise strong edge. Edge-based schemes are subject to noise and global variation in the picture (e.g. illumination), but do reliably identify strong boundaries. Our combined algorithm begins by using region growing to produce an over-segmented image. This phase is fast (order N, where N is the number of pels in the image). We then modify the over-segmented output of the region growing using edge criteria such as edge strength, edge smoothness, edge straightness and edge continuity. Two techniques-line-segment subtraction and line-segment addition-have been investigated. In the subtraction technique, the weakest edge (based on a weighted combination of the criteria) is removed at each step. In addition technique, the strongest edge is used to seed a multi-segment line that grows out from it at both ends. At every junction, the adjoining edge that has the highest edge strength is appended. We have also investigated a form of look-ahead, where the growing of lines depends on the strength of the adjoining edge and those to which it is linked. The overall procedure for both techniques, current results and the areas for improvement and expansion have been discussed.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.005 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 teacher head, 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".