Cargando…

On a Variational and Convex Model of the Blake–Zisserman Type for Segmentation of Low-Contrast and Piecewise Smooth Images

This paper proposes a new variational model for segmentation of low-contrast and piecewise smooth images. The model is motivated by the two-stage image segmentation work of Cai–Chan–Zeng (2013) for the Mumford–Shah model. To deal with low-contrast images more effectively, especially in treating high...

Descripción completa

Detalles Bibliográficos
Autores principales: Burrows, Liam, Theljani, Anis, Chen, Ke
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8621176/
https://www.ncbi.nlm.nih.gov/pubmed/34821859
http://dx.doi.org/10.3390/jimaging7110228
_version_ 1784605394420629504
author Burrows, Liam
Theljani, Anis
Chen, Ke
author_facet Burrows, Liam
Theljani, Anis
Chen, Ke
author_sort Burrows, Liam
collection PubMed
description This paper proposes a new variational model for segmentation of low-contrast and piecewise smooth images. The model is motivated by the two-stage image segmentation work of Cai–Chan–Zeng (2013) for the Mumford–Shah model. To deal with low-contrast images more effectively, especially in treating higher-order discontinuities, we follow the idea of the Blake–Zisserman model instead of the Mumford–Shah. Two practical ideas are introduced here: first, a convex relaxation idea is used to derive an implementable formulation, and second, a game reformulation is proposed to reduce the strong dependence of coupling parameters. The proposed model is then analysed for existence and further solved by an ADMM solver. Numerical experiments can show that the new model outperforms the current state-of-the-art models for some challenging and low-contrast images.
format Online
Article
Text
id pubmed-8621176
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-86211762021-11-27 On a Variational and Convex Model of the Blake–Zisserman Type for Segmentation of Low-Contrast and Piecewise Smooth Images Burrows, Liam Theljani, Anis Chen, Ke J Imaging Article This paper proposes a new variational model for segmentation of low-contrast and piecewise smooth images. The model is motivated by the two-stage image segmentation work of Cai–Chan–Zeng (2013) for the Mumford–Shah model. To deal with low-contrast images more effectively, especially in treating higher-order discontinuities, we follow the idea of the Blake–Zisserman model instead of the Mumford–Shah. Two practical ideas are introduced here: first, a convex relaxation idea is used to derive an implementable formulation, and second, a game reformulation is proposed to reduce the strong dependence of coupling parameters. The proposed model is then analysed for existence and further solved by an ADMM solver. Numerical experiments can show that the new model outperforms the current state-of-the-art models for some challenging and low-contrast images. MDPI 2021-10-28 /pmc/articles/PMC8621176/ /pubmed/34821859 http://dx.doi.org/10.3390/jimaging7110228 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Burrows, Liam
Theljani, Anis
Chen, Ke
On a Variational and Convex Model of the Blake–Zisserman Type for Segmentation of Low-Contrast and Piecewise Smooth Images
title On a Variational and Convex Model of the Blake–Zisserman Type for Segmentation of Low-Contrast and Piecewise Smooth Images
title_full On a Variational and Convex Model of the Blake–Zisserman Type for Segmentation of Low-Contrast and Piecewise Smooth Images
title_fullStr On a Variational and Convex Model of the Blake–Zisserman Type for Segmentation of Low-Contrast and Piecewise Smooth Images
title_full_unstemmed On a Variational and Convex Model of the Blake–Zisserman Type for Segmentation of Low-Contrast and Piecewise Smooth Images
title_short On a Variational and Convex Model of the Blake–Zisserman Type for Segmentation of Low-Contrast and Piecewise Smooth Images
title_sort on a variational and convex model of the blake–zisserman type for segmentation of low-contrast and piecewise smooth images
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8621176/
https://www.ncbi.nlm.nih.gov/pubmed/34821859
http://dx.doi.org/10.3390/jimaging7110228
work_keys_str_mv AT burrowsliam onavariationalandconvexmodeloftheblakezissermantypeforsegmentationoflowcontrastandpiecewisesmoothimages
AT theljanianis onavariationalandconvexmodeloftheblakezissermantypeforsegmentationoflowcontrastandpiecewisesmoothimages
AT chenke onavariationalandconvexmodeloftheblakezissermantypeforsegmentationoflowcontrastandpiecewisesmoothimages