MétaCan
Menu
Back to cohort

Combining SIFT and BRISK Descriptors to Improve Image Matching Accuracy

2024· article· en· W4403024210 on OpenAlexaff
Sina Ghaffari, Kin Fun Li, David W. Capson

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicAdvanced Image and Video Retrieval Techniques
Canadian institutionsUniversity of Victoria
Fundersnot available
KeywordsScale-invariant feature transformArtificial intelligenceComputer scienceMatching (statistics)Image matchingPattern recognition (psychology)Computer visionImage (mathematics)MathematicsStatistics

Abstract

fetched live from OpenAlex

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 distilled prediction

Teacher imitation

Not 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.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.779
Threshold uncertainty score0.825

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0010.002
Open science0.0000.001
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

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.

Opus teacher head0.013
GPT teacher head0.300
Teacher spread0.287 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designBench or experimental
Domainnot available
GenreMethods

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".

Quick stats

Citations0
Published2024
Admission routes1
Has abstractyes

Explore more

Same topicAdvanced Image and Video Retrieval TechniquesFrench-language works237,207