Sie befinden Sich nicht im Netzwerk der Universität Paderborn. Der Zugriff auf elektronische Ressourcen ist gegebenenfalls nur via VPN oder Shibboleth (DFN-AAI) möglich. mehr Informationen...
Applying Multi-class SVMs into Scene Image Classification
Ist Teil von
Innovations in Applied Artificial Intelligence, 2004, p.924-934
Ort / Verlag
Berlin, Heidelberg: Springer Berlin Heidelberg
Erscheinungsjahr
2004
Link zum Volltext
Quelle
Alma/SFX Local Collection
Beschreibungen/Notizen
Grouping images into semantically meaningful categories using the low-level visual features is a challenging and important problem in content-based image retrieval and other applications. In this paper, we show a specific high-level classification problem (scene images classification) using the low level features such as representative colors and Gabor textures. Based on the low level features, we introduce the multi-class SVMs to merge these features with the final goal to classify the different scene images. Experimental results show our method is promising.