Region segmentation via deformable model-guided split and merge

Author

Liu, Lifeng ; Sclaroff, Stan

Author_Institution

Dept. of Comput. Sci., Boston Univ., MA, USA

Volume

1

fYear

2001

fDate

2001

Firstpage

98

Abstract

An improved method for deformable shape-based image segmentation is described. Image regions are merged together and/or split apart, based on their agreement with an a priori distribution on the global deformation parameters for a shape template. Perceptually-motivated criteria are used to determine where/how to split regions, based on the local shape properties of the region group´s bounding contour. A globally consistent interpretation is determined in part by the minimum description length principle. Experiments show that model-guided split and merge yields a significant improvement in segmention over a method that uses merging alone

Keywords

computational geometry; image segmentation; merging; a priori distribution; bounding contour; deformable model-guided split and merge; deformable shape-based image segmentation; global deformation parameters; image regions; local shape properties; minimum description length principle; region segmentation; shape template; Computer science; Content based retrieval; Deformable models; Humans; Image retrieval; Image segmentation; Indexing; Merging; Object detection; Shape;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer Vision, 2001. ICCV 2001. Proceedings. Eighth IEEE International Conference on

Conference_Location

Vancouver, BC

Print_ISBN

0-7695-1143-0

Type

conf

DOI

10.1109/ICCV.2001.937504

Filename

937504