Name
Abstract | ||
|---|---|---|
We consider detection of local image symmetry using linear filters. We prove a simple criterion for determining if a filter is sensitive to a group of symmetries. We show that derivative-of-Gaussian (DtG) filters are excellent at detecting local image symmetry. Building on this, we propose a very simple algorithm that, based on the responses of a bank of six DtG filters, classifies each location of an image into one of seven Basic Image Features (BIFs). This effectively and efficiently realizes Marr's proposal for an image primal sketch. We summarize results on the use of BIFs for texture classification, object category detection, and pixel classification. |
Year | DOI | Venue |
|---|---|---|
2009 | 10.1007/978-3-642-02256-2_29 | SSVM |
Keywords | Field | DocType |
approximate symmetry type,simple criterion,image primal sketch,local image symmetry,texture classification,dtg filter,linear filter,basic image features,object category detection,pixel classification,simple algorithm,image features,linear filtering | Feature detection (computer vision),Pattern recognition,Linear filter,Image texture,Group theory,Feature (computer vision),Artificial intelligence,SIMPLE algorithm,Homogeneous space,Mathematics,Local symmetry | Conference |
Volume | ISSN | Citations |
5567 | 0302-9743 | 13 |
PageRank | References | Authors |
0.88 | 19 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Lewis D. Griffin | 1 | 381 | 45.96 |
| Martin Lillholm | 2 | 256 | 21.72 |
| Mike Crosier | 3 | 13 | 0.88 |
| Justus Sande | 4 | 13 | 0.88 |