Journal article
Relaxed matching kernels for robust image comparison
- Abstract:
-
The popular bag-of-features representation for object recognition collects signatures of local image patches and discards spatial information. Some have recently attempted to at least partially overcome this limitation, for instance by "spatial pyramids" and "proximity" kernels. We introduce the general formalism of "relaxed matching kernels" (RMKs) that includes such approaches as special cases, allow us to derive useful general properties of these kernels, and to introduce new ones. As an e...
Expand abstract
Actions
Authors
Bibliographic Details
- Journal:
- 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR
- Publication date:
- 2008-01-01
- DOI:
- Source identifiers:
-
292403
Item Description
- Pubs id:
-
pubs:292403
- UUID:
-
uuid:fc2b1759-b812-4011-87bb-34e9c6058007
- Local pid:
- pubs:292403
- Deposit date:
- 2012-12-19
Terms of use
- Copyright date:
- 2008
If you are the owner of this record, you can report an update to it here: Report update to this record