A Multi-Source Circular Geodesic Voting Model for Image Segmentation

Image segmentation is a crucial task in artificial intelligence fields such as computer vision and medical imaging. While convolutional neural networks (CNNs) have achieved notable success by learning representative features from large datasets, they often lack geometric priors and global object inf...

Full description

Saved in:
Bibliographic Details
Main Authors: Shuwang Zhou, Minglei Shu, Chong Di
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Entropy
Subjects:
Online Access:https://www.mdpi.com/1099-4300/26/12/1123
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850036309725282304
author Shuwang Zhou
Minglei Shu
Chong Di
author_facet Shuwang Zhou
Minglei Shu
Chong Di
author_sort Shuwang Zhou
collection DOAJ
description Image segmentation is a crucial task in artificial intelligence fields such as computer vision and medical imaging. While convolutional neural networks (CNNs) have achieved notable success by learning representative features from large datasets, they often lack geometric priors and global object information, limiting their accuracy in complex scenarios. Variational methods like active contours provide geometric priors and theoretical interpretability but require manual initialization and are sensitive to hyper-parameters. To overcome these challenges, we propose a novel segmentation approach, named PolarVoting, which combines the minimal path encoding rich geometric features and CNNs which can provide efficient initialization. The introduced model involves two main steps: firstly, we leverage the PolarMask model to extract multiple source points for initialization, and secondly, we construct a voting score map which implicitly contains the segmentation mask via a modified circular geometric voting (CGV) scheme. This map embeds global geometric information for finding accurate segmentation. By integrating neural network representation with geometric priors, the PolarVoting model enhances segmentation accuracy and robustness. Extensive experiments on various datasets demonstrate that the proposed PolarVoting method outperforms both PolarMask and traditional single-source CGV models. It excels in challenging imaging scenarios characterized by intensity inhomogeneity, noise, and complex backgrounds, accurately delineating object boundaries and advancing the state of image segmentation.
format Article
id doaj-art-697a730e42ae464ca00b30da454b0054
institution DOAJ
issn 1099-4300
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Entropy
spelling doaj-art-697a730e42ae464ca00b30da454b00542025-08-20T02:57:13ZengMDPI AGEntropy1099-43002024-12-012612112310.3390/e26121123A Multi-Source Circular Geodesic Voting Model for Image SegmentationShuwang Zhou0Minglei Shu1Chong Di2College of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao 266590, ChinaShandong Artificial Intelligence Institute, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250014, ChinaShandong Artificial Intelligence Institute, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250014, ChinaImage segmentation is a crucial task in artificial intelligence fields such as computer vision and medical imaging. While convolutional neural networks (CNNs) have achieved notable success by learning representative features from large datasets, they often lack geometric priors and global object information, limiting their accuracy in complex scenarios. Variational methods like active contours provide geometric priors and theoretical interpretability but require manual initialization and are sensitive to hyper-parameters. To overcome these challenges, we propose a novel segmentation approach, named PolarVoting, which combines the minimal path encoding rich geometric features and CNNs which can provide efficient initialization. The introduced model involves two main steps: firstly, we leverage the PolarMask model to extract multiple source points for initialization, and secondly, we construct a voting score map which implicitly contains the segmentation mask via a modified circular geometric voting (CGV) scheme. This map embeds global geometric information for finding accurate segmentation. By integrating neural network representation with geometric priors, the PolarVoting model enhances segmentation accuracy and robustness. Extensive experiments on various datasets demonstrate that the proposed PolarVoting method outperforms both PolarMask and traditional single-source CGV models. It excels in challenging imaging scenarios characterized by intensity inhomogeneity, noise, and complex backgrounds, accurately delineating object boundaries and advancing the state of image segmentation.https://www.mdpi.com/1099-4300/26/12/1123geodesic votingimage segmentationmulti-sourcepolar representationgeodesic model
spellingShingle Shuwang Zhou
Minglei Shu
Chong Di
A Multi-Source Circular Geodesic Voting Model for Image Segmentation
Entropy
geodesic voting
image segmentation
multi-source
polar representation
geodesic model
title A Multi-Source Circular Geodesic Voting Model for Image Segmentation
title_full A Multi-Source Circular Geodesic Voting Model for Image Segmentation
title_fullStr A Multi-Source Circular Geodesic Voting Model for Image Segmentation
title_full_unstemmed A Multi-Source Circular Geodesic Voting Model for Image Segmentation
title_short A Multi-Source Circular Geodesic Voting Model for Image Segmentation
title_sort multi source circular geodesic voting model for image segmentation
topic geodesic voting
image segmentation
multi-source
polar representation
geodesic model
url https://www.mdpi.com/1099-4300/26/12/1123
work_keys_str_mv AT shuwangzhou amultisourcecirculargeodesicvotingmodelforimagesegmentation
AT mingleishu amultisourcecirculargeodesicvotingmodelforimagesegmentation
AT chongdi amultisourcecirculargeodesicvotingmodelforimagesegmentation
AT shuwangzhou multisourcecirculargeodesicvotingmodelforimagesegmentation
AT mingleishu multisourcecirculargeodesicvotingmodelforimagesegmentation
AT chongdi multisourcecirculargeodesicvotingmodelforimagesegmentation