Shape-based object segmentation with simultaneous intensity adjustment

Most segmentation algorithms are based on the assumption of intensity homogeneity within an object. However, in many applications, the object of interest contains more than one homogenous region. Even when the object's shape is known, such object is not effectively extracted. In this paper, we...

Full description

Saved in:
Bibliographic Details
Main Authors: Sarawut Tae-O-Sot, Supatana Auethavekiat, Somchai Jitapunkul
Other Authors: Chulalongkorn University
Format: Conference or Workshop Item
Published: 2018
Subjects:
Online Access:https://repository.li.mahidol.ac.th/handle/123456789/23229
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Mahidol University
id th-mahidol.23229
record_format dspace
spelling th-mahidol.232292018-08-20T13:58:12Z Shape-based object segmentation with simultaneous intensity adjustment Sarawut Tae-O-Sot Supatana Auethavekiat Somchai Jitapunkul Chulalongkorn University Mahidol University Engineering Most segmentation algorithms are based on the assumption of intensity homogeneity within an object. However, in many applications, the object of interest contains more than one homogenous region. Even when the object's shape is known, such object is not effectively extracted. In this paper, we propose a segmentation process for the objects containing 2 homogenous regions. Our method is based on the level set method. We construct the shape model from the set of manually extracted objects. The parameters that represent the shape model are coefficients of PCA basis. Instead of defining a new cost-function based on heterogeneity assumption, we repeatedly form a homogenous region inside the evolving curve and evolve the curve by the level set method. Our experiment on medical images indicated that our method effectively segmented object with one and two homogenous regions. © 2006 IEEE. 2018-08-20T06:58:12Z 2018-08-20T06:58:12Z 2006-12-14 Conference Paper Third Canadian Conference on Computer and Robot Vision, CRV 2006. Vol.2006, (2006) 10.1109/CRV.2006.64 2-s2.0-33845370680 https://repository.li.mahidol.ac.th/handle/123456789/23229 Mahidol University SCOPUS https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=33845370680&origin=inward
institution Mahidol University
building Mahidol University Library
continent Asia
country Thailand
Thailand
content_provider Mahidol University Library
collection Mahidol University Institutional Repository
topic Engineering
spellingShingle Engineering
Sarawut Tae-O-Sot
Supatana Auethavekiat
Somchai Jitapunkul
Shape-based object segmentation with simultaneous intensity adjustment
description Most segmentation algorithms are based on the assumption of intensity homogeneity within an object. However, in many applications, the object of interest contains more than one homogenous region. Even when the object's shape is known, such object is not effectively extracted. In this paper, we propose a segmentation process for the objects containing 2 homogenous regions. Our method is based on the level set method. We construct the shape model from the set of manually extracted objects. The parameters that represent the shape model are coefficients of PCA basis. Instead of defining a new cost-function based on heterogeneity assumption, we repeatedly form a homogenous region inside the evolving curve and evolve the curve by the level set method. Our experiment on medical images indicated that our method effectively segmented object with one and two homogenous regions. © 2006 IEEE.
author2 Chulalongkorn University
author_facet Chulalongkorn University
Sarawut Tae-O-Sot
Supatana Auethavekiat
Somchai Jitapunkul
format Conference or Workshop Item
author Sarawut Tae-O-Sot
Supatana Auethavekiat
Somchai Jitapunkul
author_sort Sarawut Tae-O-Sot
title Shape-based object segmentation with simultaneous intensity adjustment
title_short Shape-based object segmentation with simultaneous intensity adjustment
title_full Shape-based object segmentation with simultaneous intensity adjustment
title_fullStr Shape-based object segmentation with simultaneous intensity adjustment
title_full_unstemmed Shape-based object segmentation with simultaneous intensity adjustment
title_sort shape-based object segmentation with simultaneous intensity adjustment
publishDate 2018
url https://repository.li.mahidol.ac.th/handle/123456789/23229
_version_ 1763494258471337984