Matching Local Invariant Features: How Can Contextual Information Help?

Dro Desire Sidibe 1 Philippe Montesinos 2 Stefan Janaqi 2
1 LHC - Laboratoire Hubert Curien [Saint Etienne]
2 LGI2P - Laboratoire de Génie Informatique et Ingénierie de Production
Abstract : Local invariant features are a powerful tool for finding correspondences between images since they are robust to cluttered background, occlusion and viewpoint changes. However, they suffer the lack of global information and fail to resolve ambiguities that can occur when an image has multiple similar regions. Considering some global information will clearly help to achieve better performances. The question is which information to use and how to use it. While previous approaches use context for description, this paper shows that better results are obtained if contextual information is included in the matching process. We compare two different methods which use context for matching and experiments show that a relaxation based approach gives better results.
Keywords : image matching local invariant features
Document type :
Conference papers
Complete list of metadatas

Cited literature [14 references]  Display  Hide  Download
https://hal-ujm.archives-ouvertes.fr/ujm-00374347
Contributor : Dro Desire Sidibe <>
Submitted on : Wednesday, April 8, 2009 - 2:04:28 PM
Last modification on : Monday, January 13, 2020 - 5:46:03 PM
Long-term archiving on: Friday, October 12, 2012 - 4:26:31 PM

File

article_ec_sipmcs.pdf
Files produced by the author(s)

Identifiers

Collections

UNIV-ST-ETIENNE | CNRS | LAHC | EM-ALES | IOGS | PARISTECH | UDL

Citation

Dro Desire Sidibe, Philippe Montesinos, Stefan Janaqi. Matching Local Invariant Features: How Can Contextual Information Help?. 6th EURASIP Conference focused on Speech and Image Processing, Multimedia Communications and Services., Jun 2007, Maribor, Slovenia. pp.503-506, ⟨10.1109/IWSSIP.2007.4381151⟩. ⟨ujm-00374347⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

322

Files downloads

247

Contact

Informations

CCSD