Name
Abstract | ||
|---|---|---|
We argue for the importance of explicit semantic modelling in human-centred texture analysis tasks such as retrieval, annotation, synthesis, and zero-shot learning. To this end, low-level attributes are selected and used to define a semantic space for texture. 319 texture classes varying in illumination and rotation are positioned within this semantic space using a pair wise relative comparison procedure. Low-level visual features used by existing texture descriptors are then assessed in terms of their correspondence to the semantic space. Textures with strong presence of attributes connoting randomness and complexity are shown to be poorly modelled by existing descriptors. In a retrieval experiment semantic descriptors are shown to outperform visual descriptors. Semantic modelling of texture is thus shown to provide considerable value in both feature selection and in analysis tasks. |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1109/CVPR.2013.165 | Computer Vision and Pattern Recognition |
Keywords | Field | DocType |
semantic data,semantic modelling,analysis task,texture class,explicit semantic,semantic space,enriching texture analysis,texture descriptors,retrieval experiment semantic descriptors,visual descriptors,low-level attribute,human-centred texture analysis task,image annotation,feature extraction,visualization,weaving,rotation,learning artificial intelligence,mathematical model,randomness,semantics,object recognition,image retrieval,complexity,feature selection,vectors,image texture,texture,support vector machines,illumination,image classification | Computer vision,Automatic image annotation,Pattern recognition,Computer science,Image texture,Image retrieval,Artificial intelligence,Semantic computing,Semantics,Semantic data model,Cognitive neuroscience of visual object recognition,Visual Word | Conference |
Volume | Issue | ISSN |
2013 | 1 | 1063-6919 |
Citations | PageRank | References |
13 | 0.71 | 19 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Tim Matthews | 1 | 13 | 0.71 |
| Mark S. Nixon | 2 | 3080 | 304.45 |
| Mahesan Niranjan | 3 | 775 | 120.43 |