Abstract | ||
---|---|---|
Image copy detection is a major challenge with regard to computational efficiency, memory requirements and accuracy. A popular approach from the literature is to use visual words (or Bag-of-Words) constructed from real value (SIFT and SURF) and binary string salient point descriptors (BRIEF, ORB, BRISK and FREAK). To accommodate large scale data sets, we used the approximate nearest neighbor (ANN) based cluster approach. Our results on several well-known test sets reveal that some of the recent binary string approaches outperformed notable descriptors such as SIFT and SURF. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1145/2578726.2578797 | ICMR |
Keywords | Field | DocType |
notable descriptors,major challenge,binary string salient point,salient feature,visual word,cluster approach,memory requirement,popular approach,image copy detection,large scale data set,approximate nearest neighbor,recent binary string,evaluation | Scale-invariant feature transform,Data set,Copy detection,FREAK,Computer science,Artificial intelligence,k-nearest neighbors algorithm,Computer vision,Pattern recognition,Orb (optics),Machine learning,Visual Word,Salient | Conference |
Citations | PageRank | References |
3 | 0.42 | 10 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Song Wu | 1 | 90 | 5.58 |
Michael S. Lew | 2 | 2742 | 166.02 |