Image and Volume Segmentation by Water Flow
Image and Volume Segmentation by Water Flow
A general framework for image segmentation is presented in this paper, based on the paradigm of water flow. The major water flow attributes like water pressure, surface tension and capillary force are defined in the context of force field generation and make the model adaptable to topological and geometrical changes. A flow-stopping image functional combining edge- and region-based forces is introduced to produce capability for both range and accuracy. The method is assessed qualitatively and quantitatively on synthetic and natural images. It is shown that the new approach can segment objects with complex shapes or weak-contrasted boundaries, and has good immunity to noise. The operator is also extended to 3-D, and is successfully applied to medical volume segmentation.
62-74
Liu, Xin U.
dbdb088d-dabe-4e87-95bb-e57e81fc78da
Nixon, Mark S.
2b5b9804-5a81-462a-82e6-92ee5fa74e12
2007
Liu, Xin U.
dbdb088d-dabe-4e87-95bb-e57e81fc78da
Nixon, Mark S.
2b5b9804-5a81-462a-82e6-92ee5fa74e12
Liu, Xin U. and Nixon, Mark S.
(2007)
Image and Volume Segmentation by Water Flow.
Proc USVC 2007/ LNCS, Nevada, United States.
.
Record type:
Conference or Workshop Item
(Other)
Abstract
A general framework for image segmentation is presented in this paper, based on the paradigm of water flow. The major water flow attributes like water pressure, surface tension and capillary force are defined in the context of force field generation and make the model adaptable to topological and geometrical changes. A flow-stopping image functional combining edge- and region-based forces is introduced to produce capability for both range and accuracy. The method is assessed qualitatively and quantitatively on synthetic and natural images. It is shown that the new approach can segment objects with complex shapes or weak-contrasted boundaries, and has good immunity to noise. The operator is also extended to 3-D, and is successfully applied to medical volume segmentation.
More information
Published date: 2007
Venue - Dates:
Proc USVC 2007/ LNCS, Nevada, United States, 2007-01-01
Organisations:
Southampton Wireless Group
Identifiers
Local EPrints ID: 265673
URI: http://eprints.soton.ac.uk/id/eprint/265673
PURE UUID: 946a5cf9-8dff-4ac8-9367-216b381115fc
Catalogue record
Date deposited: 07 May 2008 10:36
Last modified: 15 Mar 2024 02:35
Export record
Contributors
Author:
Xin U. Liu
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics
