Pruning local feature correspondences using shape context
Bibliographic record
Abstract
We propose a novel approach to improve the distinctiveness of local image features without significantly affecting their robustness with respect to image deformations. Local image features have proven to be successful in computer vision tasks involving partial occlusion, background noise, and various types of image deformations. However, the relatively high number of outliers that have to be rejected from the correspondences set, formed during the search for similar features, still plagues this approach. The task of rejecting outliers is usually based on estimating the global spatial transform suffered by the features in the correspondences set. This presents two problems: (i) it cannot properly deal with non-rigid objects, and (ii) it is sensitive to a high number of outliers. Here, we address these problems by combining typical local features with shape context. A performance evaluation shows that this new semi-local feature generally provides higher distinctiveness and robustness to image deformations, thus potentially increasing the inlier/outlier ratio in the correspondences set. Also, we show that in wide baseline stereo matching, and non-rigid motion applications, the use of the novel semi-local feature not only provides robustness to non-rigid deformations, but also produces a higher inlier/outlier ratio than the standard Hough clustering of the global spatial transform of parameters.
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 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.003 | 0.001 |
| Bibliometrics | 0.004 | 0.003 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.002 | 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".