DocumentCode
786878
Title
Disentangling chromosome overlaps by combining trainable shape models with classification evidence
Author
Graham, James
Volume
50
Issue
8
fYear
2002
fDate
8/1/2002 12:00:00 AM
Firstpage
2080
Lastpage
2085
Abstract
Resolving chromosome overlaps is an unsolved problem in automated chromosome analysis. We propose a method that combines evidence from classification and shape, based on trainable shape models. In evaluation using synthesized overlaps, certain cases are resolvable using shape evidence alone, but where this is misleading, classification evidence improves performance
Keywords
cellular biophysics; image classification; image segmentation; medical image processing; automated chromosome analysis; biological cells; chromosome overlaps disentangling; classification evidence; image classification; image segmentation; shape evidence; synthesized overlaps; trainable shape models; Automation; Biological cells; Biomedical engineering; Biomedical imaging; Image segmentation; Machine vision; Pattern analysis; Pattern recognition; Shape measurement; Solid modeling;
fLanguage
English
Journal_Title
Signal Processing, IEEE Transactions on
Publisher
ieee
ISSN
1053-587X
Type
jour
DOI
10.1109/TSP.2002.800421
Filename
1018802
Link To Document