Combining regions and patches for object class localization - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2006

Combining regions and patches for object class localization


We introduce a method for object class detection and localization which combines regions generated by image segmentation with local patches. Region-based descriptors can model and match regular textures reliably, but fail on parts of the object which are textureless. They also cannot repeatably identify interest points on their boundaries. By incorporating information from patch-based descriptors near the regions into a new feature, the Region-based Context Feature (RCF), we can address these issues. We apply Region-based Context Features in a semi-supervised learning framework for object detection and localization. This framework produces object-background segmentation masks of deformable objects. Numerical results are presented for pixel-level performance.
Fichier principal
Vignette du fichier
pantofarudorkoschmidhebert_beyondpatches_CombiningRegionsAndPatches.pdf (1.51 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

inria-00548581 , version 1 (20-12-2010)



Caroline Pantofaru, Gyuri Dorkó, Cordelia Schmid, Martial Hebert. Combining regions and patches for object class localization. Conference on Computer Vision and Pattern Recognition Workshop (Beyond Patches workshop, CVPR '06), Jun 2006, New York, United States. pp.23, ⟨10.1109/CVPRW.2006.57⟩. ⟨inria-00548581⟩
144 View
146 Download



Gmail Facebook X LinkedIn More