Combining SIFT and BRISK Descriptors to Improve Image Matching Accuracy
Bibliographic record
Abstract
Local descriptor algorithms are foundational in computer vision applications such as image matching and image retrieval. Some local descriptor algorithms extract features containing similar information from images while others extract complementary information. In this work, we investigate the advantages of combining a binary and a non-binary local descriptor algorithm. We propose and compare three methods to combine SIFT and BRISK descriptor algorithms selected because they produce complementary descriptor vectors. First, we propose to combine SIFT and BRISK descriptors using a weighted summation of their individual descriptor distances with learned weights. Our second method converts SIFT into a binary descriptor and concatenates the binary SIFT vector with the BRISK descriptor. The third method is to scale the binary BRISK descriptor vector and concatenate it with the SIFT descriptor. Parameters for combining the descriptors are learned based on the HPatches data set for each of the three methods. Our proposed methods increase the mean Average Precision in the range of 3% to 15.8% over the original BRISK and in the range of 5.9% to 21.8% over the original SIFT algorithm in various evaluation conditions.
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 | 0.003 | 0.009 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.005 | 0.005 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.004 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 0.003 |
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".