Hierarchical conditional random field for multi-class image classification
| Autor: | Michael Ying Yang, Förstner, W., Drauschke, M. |
|---|---|
| Přispěvatelé: | Department of Earth Observation Science |
| Jazyk: | angličtina |
| Rok vydání: | 2010 |
| Předmět: | |
| Zdroj: | VISAPP 2010-Proceedings of the International Conference on Computer Vision Theory and Applications, 464-469 STARTPAGE=464;ENDPAGE=469;TITLE=VISAPP 2010-Proceedings of the International Conference on Computer Vision Theory and Applications Scopus-Elsevier |
| Popis: | Multi-class image classification has made significant advances in recent years through the combination of local and global features. This paper proposes a novel approach called hierarchical conditional random field (HCRF) that explicitly models region adjacency graph and region hierarchy graph structure of an image. This allows to set up a joint and hierarchical model of local and global discriminative methods that augments conditional random field to a multi-layer model. Region hierarchy graph is based on a multi-scale watershed segmentation. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|