Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
534099 | Pattern Recognition Letters | 2012 | 9 Pages |
Combinatorial pyramids represent the image as a stack of successively reduced combinatorial maps, which encode the whole image at different levels of abstraction. Within this framework, this paper proposes to conduct the perceptual organization of the image content in two consecutive stages. The first stage builds the lower set of levels of the hierarchy according to simple face (regions) features (colour and size). On the top of this hierarchy, the second stage will mainly employ boundary features, encoded in the darts of the combinatorial maps, to obtain a second set of levels of abstraction. The Berkeley data set BSDS300 is used to quantitatively compare the performance of the proposal to a number of perceptual grouping approaches, showing that it yields better or similar results than most of these algorithms while offering two interesting features: computation at multiple image resolutions and preservation of the image topology.
► Image content is perceptually organized in a bottom-up fashion. ► Image topology is preserved at all levels of the hierarchy. ► Edges and regions descriptors are efficiently combined. ► The approach has been successfully evaluated using the challenging BSDS300.