MS-POFT: multiscale phase-orientation guided feature transform for multi-modal image matching
Bibliographic record
Abstract
Multi-modal remote sensing image (MRSI) matching has always been a challenging task. Traditional image matching methods often fail to obtain satisfactory results in most cases due to temporal differences, complex geometric distortions, and non-linear radiometric differences (NRDs). The key to addressing MRSI matching lies in mitigating NRDs to achieve robust extraction and description of features. This paper proposes a multiscale phase-orientation guided feature transform (MS-POFT) for multi-modal image matching. Two novel strategies are investigated and integrated into MS-POFT to improve the matching performance. A phase-structured adaptive detection is designed by the complementation of phase stretching transform and adaptive sliding windows, which ensures stable feature point extraction across different scales. Then, a new feature descriptor suitable for multi-modal images, called MS-PGLOH, is constructed based on phase and gradient principal direction in multiscale space. We performed comparison experiments on various multimodal datasets from remote sensing, natural sceneries, night surveillance, medical and temporal changes. Our experimental results both in qualitative and quantitative ways show that our proposed MS-POFT outperforms other comparison methods. MS-POFT successfully matched all given image pairs, achieving satisfactory results in terms of the number of correct matches (NCM), proportion of corrections ratio (PCR), and a reduced root-mean-square error (RMSE) of approximately 1.36.
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 | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".