We consider the problem of segmenting an image into foreground and background, with foreground containing solely objects of interest known a priori. We propose an integration model that incorporates both edge detection and object part detection results. It consists of two parallel processes: low-level pixel grouping and high-level patch grouping. We seek a solution that optimizes a joint grouping criterion in a reduced space enforced by grouping correspondence between pixels and patches. Using spectral graph partitioning, we show that a near global optimum can be found by solving a constrained eigenvalue problem. We report promising experimental results on a dataset of 15 objects under clutter and occlusion.
Object-specific figure-ground segregation
01.01.2003
946970 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Object-Specific Figure-Ground Segregation
British Library Conference Proceedings | 2003
|A Model of Figure-Ground Segregation from Kinetic Occlusion
British Library Conference Proceedings | 1995
|Segmentation by Color Coalition Labeling for Figure-Ground Segregation in Decoration Designs
British Library Conference Proceedings | 2003
|