Detection of semantic objects using description graphs

10 years 4 months ago
Detection of semantic objects using description graphs
This paper presents a technique to detect instances of classes (objects) according to their semantic definition in the form of a Description Graph. Classes are defined as combinations of instances of lower level semantic classes and allow the definition of a Semantic Tree that organizes classes in semantic levels. At the bottom level of the Semantic Tree, classes are defined by a perceptual model containing a list of low-level descriptors. The proposed detection algorithm follows a bottom-up/top-down approach, building Semantic Trees on a region-based representation of the media. The flexibility of the approach is assessed on different examples of planar objects, such as frontal faces, groups of islands, flags and traffic signs.
Ferran Marqués, Xavier Giro
Added 23 Oct 2009
Updated 27 Oct 2009
Type Conference
Year 2005
Where ICIP
Authors Ferran Marqués, Xavier Giro
Comments (0)