From Partition Trees to Semantic Trees
This paper proposes a solution to bridge the gap between semantic and visual information formulated as a structural pattern recognition problem. Instances of semantic classes expressed by Description Graphs are detected on a region-based representation of visual data expressed with a Binary Partition Tree. The detection process builds instances of Semantic Trees on the top of the Binary Partition Tree using an encyclopedia of models organised as a hierarchy. At the leaves of the Semantic Tree, classes are defined by perceptual models containing a list of low-level descriptors. The proposed solution is assessed in different environments to show its flexibility.
Unable to display preview. Download preview PDF.
- 1.Leung, T.K., Burl, M.C., Perona, P.: Finding faces in cluttered scenes using random labeled graph matching. In: IEEE International Conference on Computer Vision, ICCV 1995, Cambridge, USA, pp. 637–644 (1995)Google Scholar
- 6.Vilaplana, V., Giró, X., Salembier, P., Marqués, F.: Region-based extraction and analysis of visual objects information. In: 4th Int. Workshop on Content-Based Multimedia Indexing, CBMI 2005, Riga, Latvia, pp. SSI.3.1–SSI.3.9 (2005)Google Scholar
- 8.Ferran Bennstrom, C., Casas, J.: Object representation using colour, shape and structure criteria in a binary partition tree. In: IEEE Intern. Conf. on Image Processing, ICIP 2005, Genova, Italy, vol. 3, pp. 1144–1147 (2005)Google Scholar