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.
A Bayesian hierarchical model for learning natural scene categories
2005-01-01
2117095 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Hierarchical Bayesian models for unsupervised scene understanding
British Library Online Contents | 2015
|Hierarchical Unsupervised Learning of Facial Expression Categories
British Library Conference Proceedings | 2001
|Depth map generation based on scene categories
British Library Online Contents | 2009
|A Bayesian Approach to Unsupervised One-Shot Learning of Object Categories
British Library Conference Proceedings | 2003
|