Abstract | ||
---|---|---|
A key challenge in feature correspondence is the difficulty in differentiating true and false matches at a local descriptor level. This forces adoption of strict similarity thresholds that discard many true matches. However, if analyzed at a global level, false matches are usually randomly scattered while true matches tend to be coherent (clustered around a few dominant motions), thus creating a c... |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/TPAMI.2017.2652468 | IEEE Transactions on Pattern Analysis and Machine Intelligence |
Keywords | Field | DocType |
Coherence,Noise measurement,Robustness,Computational modeling,Pattern matching,Mathematical model,Optical imaging | k-nearest neighbors algorithm,Computer vision,Pattern recognition,Noise measurement,Regression,Computer science,RANSAC,Robustness (computer science),Coherence (physics),Artificial intelligence,Optical imaging,Pattern matching | Journal |
Volume | Issue | ISSN |
40 | 1 | 0162-8828 |
Citations | PageRank | References |
18 | 0.52 | 40 |
Authors | ||
7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Wen-Yan Lin | 1 | 340 | 9.90 |
Fan Wang | 2 | 18 | 0.52 |
Ming-Ming Cheng | 3 | 1914 | 82.32 |
Sai Kit Yeung | 4 | 60 | 4.97 |
Philip H. S. Torr | 5 | 9140 | 636.18 |
M.N. Do | 6 | 39 | 4.78 |
Jiangbo Lu | 7 | 1009 | 48.99 |