Dense matching and image segmentation using projective geometry.
Bibliographic record
Abstract
Dense matching and image segmentation are fundamental image analysis operations. These operations are required by many computer vision applications. Artificial view-synthesis, 3D scene reconstruction, token tracking and augmented reality are examples of applications that rely heavily on these primitives. The speed and accuracy of such applications rely on the quality of the matching and segmentation. As a result, solutions to these problems have been widely researched. However, due to the difficulty of these problems, there is no universal solution. Most solutions to these two problems make certain assumptions. First, dense matching and image segmentation are often viewed as separate problems. Second, most image segmentation techniques operate on only a single image. This introduces a technique that simultaneously performs image segmentation and dense matching of planar surfaces in a stereo pair of images. Using three matched points from an arbitrary plane, and four other matched points, a projective mapping, known as a homography, is calculated. This homography is used to iteratively grow a region in both images. The result is a matched and segmented plane. Practical tests comparing the computation time of this method to traditional matching techniques are presented. These results are used to motivate the use of the planar technique as a primary step for reducing the overall computation time for dense matching and image segmentation. Source: Masters Abstracts International, Volume: 41-04, page: 1116. Adviser: Bubaker Boufama. Thesis (M.Sc.)--University of Windsor (Canada), 2002.
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 | 0.001 |
| 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".