A Bayesian hierarchical model for learning natural scene categories

We propose a novel approach to learn and recognize natural scene categories. Unlike previous work, it does not require experts to annotate the training set. We represent the image of a scene by a collection of local regions, denoted as codewords obtained by unsupervised learning. Each region is repr...

Full description

Saved in:
Bibliographic Details
Published in2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) Vol. 2; pp. 524 - 531 vol. 2
Main Authors Fei-Fei, L., Perona, P.
Format Conference Proceeding
LanguageEnglish
Published IEEE 2005
Subjects
Animals
Bayesian methods
Cities and towns
Dictionaries
Frequency
Histograms
Humans
Layout
Unsupervised learning
Vehicles
Online AccessGet full text

Cover

More Information
Summary:We propose a novel approach to learn and recognize natural scene categories. Unlike previous work, it does not require experts to annotate the training set. We represent the image of a scene by a collection of local regions, denoted as codewords obtained by unsupervised learning. Each region is represented as part of a "theme". In previous work, such themes were learnt from hand-annotations of experts, while our method learns the theme distributions as well as the codewords distribution over the themes without supervision. We report satisfactory categorization performances on a large set of 13 categories of complex scenes.
ISBN:0769523722
9780769523729
ISSN:1063-6919
1063-6919
DOI:10.1109/CVPR.2005.16