Scene classification using bag-of-regions representations

Simple item page
dc.contributor.authorGökalp, Demiren_US
dc.contributor.authorAksoy, Selimen_US
dc.coverage.spatialMinneapolis, MN, USA
dc.date.accessioned2016-02-08T11:44:01Z
dc.date.available2016-02-08T11:44:01Z
dc.date.issued2007-06en_US
dc.departmentDepartment of Computer Engineeringen_US
dc.descriptionDate of Conference: 17-22 June 2007
dc.descriptionConference name: IEEE Conference on Computer Vision and Pattern Recognition, 2007
dc.description.abstractThis paper describes our work on classification of outdoor scenes. First, images are partitioned into regions using one-class classification and patch-based clustering algorithms where one-class classifiers model the regions with relatively uniform color and texture properties, and clustering of patches aims to detect structures in the remaining regions. Next, the resulting regions are clustered to obtain a codebook of region types, and two models are constructed for scene representation: a "bag of individual regions" representation where each region is regarded separately, and a "bag of region pairs" representation where regions with particular spatial relationships are considered, together. Given these representations, scene classification is done using Bayesian classifiers. We also propose a novel region selection algorithm that identifies region types that are frequently found in a particular class of scenes but rarely exist in other classes, and also consistently occur together in the same class of scenes. Experiments on the LabelMe data set showed that the proposed models significantly out-perform a baseline global feature-based approach. © 2007 IEEE.en_US
dc.identifier.doi10.1109/CVPR.2007.383375en_US
dc.identifier.urihttp://hdl.handle.net/11693/27090
dc.language.isoEnglishen_US
dc.publisherIEEE
dc.relation.isversionofhttp://dx.doi.org/10.1109/CVPR.2007.383375en_US
dc.source.titleProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognitionen_US
dc.subjectBayesian networksen_US
dc.subjectClustering algorithmsen_US
dc.subjectMathematical modelsen_US
dc.subjectCodebooksen_US
dc.subjectGlobal featuresen_US
dc.subjectOutdoor scenesen_US
dc.subjectSpatial relationshipsen_US
dc.subjectImage classificationen_US
dc.titleScene classification using bag-of-regions representationsen_US
dc.typeConference Paperen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Scene classification using bag-of-regions representations.pdf
Size:
1.62 MB
Format:
Adobe Portable Document Format
Description:
Full Printable Version
Download

Collections

Department of Computer Engineering