On using an analogy to heat flow for shape extraction
On using an analogy to heat flow for shape extraction
We introduce a novel evolution-based segmentation algorithm which uses the heat flow analogy to gain practical advantage. The proposed algorithm consists
of two parts. In the first part, we represent a particular heat conduction problem in the image domain to roughly segment the region of interest. Then we use geometric heat flow to complete the segmentation, by smoothing extracted boundaries and removing noise inside the prior segmented region. The proposed algorithm is compared with active contour models and is tested on synthetic and medical images. Experimental results indicate that our approach works well in noisy conditions without pre-processing. It can detect multiple objects simultaneously. It is also computationally more efficient and easier to control and implement in comparison with active contour models.
125-139
Direkoglu, Cem
b793e59b-4188-44b2-99c5-b4dedc46cfda
Nixon, Mark S.
2b5b9804-5a81-462a-82e6-92ee5fa74e12
2013
Direkoglu, Cem
b793e59b-4188-44b2-99c5-b4dedc46cfda
Nixon, Mark S.
2b5b9804-5a81-462a-82e6-92ee5fa74e12
Direkoglu, Cem and Nixon, Mark S.
(2013)
On using an analogy to heat flow for shape extraction.
Pattern Analysis and Applications, 16, .
(doi:10.1007/s10044-011-0223-0).
Abstract
We introduce a novel evolution-based segmentation algorithm which uses the heat flow analogy to gain practical advantage. The proposed algorithm consists
of two parts. In the first part, we represent a particular heat conduction problem in the image domain to roughly segment the region of interest. Then we use geometric heat flow to complete the segmentation, by smoothing extracted boundaries and removing noise inside the prior segmented region. The proposed algorithm is compared with active contour models and is tested on synthetic and medical images. Experimental results indicate that our approach works well in noisy conditions without pre-processing. It can detect multiple objects simultaneously. It is also computationally more efficient and easier to control and implement in comparison with active contour models.
Text
direkoglu paa.pdf
- Version of Record
More information
Published date: 2013
Organisations:
Vision, Learning and Control
Identifiers
Local EPrints ID: 356733
URI: http://eprints.soton.ac.uk/id/eprint/356733
PURE UUID: 85ab8e99-bda8-49d7-8cd1-6c3e507575b0
Catalogue record
Date deposited: 01 May 2015 15:38
Last modified: 15 Mar 2024 02:35
Export record
Altmetrics
Contributors
Author:
Cem Direkoglu
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
