Name
Abstract | ||
|---|---|---|
The SIFT (Scale Invariant Feature Transform) descriptor is a widely used method for matching image features. However, perfect scale invariance can not be achieved in practice because of sampling artefacts, noise in the image data, and the fact that the computational effort limits the number of analyzed scale space images. In this paper we propose a modification of the descriptor's regular grid of orientation histogram bins to an irregular grid. The irregular grid approach reduces the negative effect of scale error and significantly increases the matching precision for image features. Results with a standard data set are presented that show that the irregular grid approach outperforms the original SIFT descriptor and other state-of-the-art extentions. |
Year | DOI | Venue |
|---|---|---|
2009 | 10.1007/978-3-642-02611-9_26 | ICIAR |
Keywords | Field | DocType |
matching precision,irregular grid approach,scale error,image data,perfect scale invariance,image feature,irregular grid,irregular orientation histogram binning,scale invariant feature transform,scale space image,regular grid,original sift descriptor,scale space,image features,scale invariance | Histogram,Computer vision,Scale-invariant feature transform,Scale invariance,Pattern recognition,Regular grid,Computer science,Feature (computer vision),Irregular Z-buffer,Scale space,Artificial intelligence,Grid | Conference |
Volume | ISSN | Citations |
5627 | 0302-9743 | 9 |
PageRank | References | Authors |
0.57 | 12 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Yan Cui | 1 | 9 | 0.57 |
| Nils Hasler | 2 | 272 | 11.28 |
| Thorsten Thormählen | 3 | 9 | 0.57 |
| Hans-Peter Seidel | 4 | 12532 | 801.49 |