Scene classification using bag-of-regions representations

Date
2007-06
Advisor
Supervisor
Co-Advisor
Co-Supervisor
Instructor
Source Title
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Print ISSN
Electronic ISSN
Publisher
IEEE
Volume
Issue
Pages
Language
English
Type
Conference Paper
Journal Title
Journal ISSN
Volume Title
Series
Abstract

This 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.

Course
Other identifiers
Book Title
Keywords
Bayesian networks, Clustering algorithms, Mathematical models, Codebooks, Global features, Outdoor scenes, Spatial relationships, Image classification
Citation
Published Version (Please cite this version)