Multiresolution techniques are often used for image segmentation, emulating the human visual process. More precisely, image pyramids are especially well adapted for multiresolution representation. A new concept is proposed that uses a pyramid approach in image segmentation, by simulating the human vision in its attention focusing process. The method introduces local pyramids in reply to inherent limitations of the classical structure, especially the case of elongated or countless objects. To show the robustness of such a new technique, experimental results and comparisons with classical methods are given.
Using local pyramids for more robust object delineation
01.01.1996
623509 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Using Local Pyramids for More Robust Object Delineation
British Library Conference Proceedings | 1996
|Initializing snakes [object delineation]
IEEE | 1994
|Fast Multi-Feature Pyramids for Scale-Adaptive Object Tracking
British Library Online Contents | 2016
|Video tracking using morphological pyramids
British Library Online Contents | 1999
|British Library Conference Proceedings | 2006
|