An original approach to texture-based classification of regions, for image indexing and retrieval, is presented. The system addresses automatic macro-textured ROI detection, and classification: we focus our attention on those objects that can be characterized by a texture as a whole, like trees, flowers, walls, clouds, and so on. The proposed architecture is based on the computation of the /spl lambda/ vector from each selected region, and classification of this feature by means of a pool of suitably trained support vector machines (SVM). This approach is an extension of the one previously developed by some of the authors to classify image regions on the basis of the geometrical shape of the objects they contain. Theoretical remarks, motivation of the approach, experimental setup, and the first satisfactory results on natural scenes are reported.
Texture classification for content-based image retrieval
2001-01-01
731628 byte
Conference paper
Electronic Resource
English
Texture Classification for Content-Based Image Retrieval
British Library Conference Proceedings | 2001
|Regular-texture image retrieval based on texture-primitive extraction
British Library Online Contents | 1999
|Perceptive Visual Texture Classification and Retrieval
British Library Conference Proceedings | 2003
|Perceptive visual texture classification and retrieval
IEEE | 2003
|A smart content-based image retrieval system based on color and texture feature
British Library Online Contents | 2009
|