DocumentCode
1820301
Title
Shape and appearance modeling with feature distributions for image segmentation
Author
Litvin, Andrew ; Karl, William C. ; Shah, Jayant
Author_Institution
Dept. of Electr. & Comput. Eng., Boston Univ., MA
fYear
2006
fDate
6-9 April 2006
Firstpage
1128
Lastpage
1131
Abstract
This paper presents a new approach to prior shape and appearance modeling for use in curve evolution-based segmentation. The new method is based on the unified use of feature distributions and allows the incorporation of coupled prior information about shape and appearance into the curve evolution segmentation process. Examples show the accurate placement of boundaries in challenging situations; for example, in cases where an intensity boundary does not exist
Keywords
biomedical MRI; image segmentation; medical image processing; MRI; appearance modeling; curve evolution-based segmentation; feature distributions; image segmentation; shape modeling; Active appearance model; Biomedical imaging; Drives; Higher order statistics; Hospitals; Image segmentation; Mathematical model; Mathematics; Shape; Topology;
fLanguage
English
Publisher
ieee
Conference_Titel
Biomedical Imaging: Nano to Macro, 2006. 3rd IEEE International Symposium on
Conference_Location
Arlington, VA
Print_ISBN
0-7803-9576-X
Type
conf
DOI
10.1109/ISBI.2006.1625121
Filename
1625121
Link To Document