Research Article
Open Access
Total Variation Diffusion-Guided Fuzzy Active Contour Model for Noisy Image Segmentation
1
SKLSVMS, Xi’an Jiaotong University, Xi’an 710049, China
2
School of Aerospace Engineering, Xi’an Jiaotong University, Xi’an 710049, China
3
School of Automation Science and Engineering, Xi’an Jiaotong University, Xi’an 710049, China
* Corresponding Author:
Yi Yang,
[email protected]
Volume 3, Issue 2
2026
Received: 12 September 2025
Accepted: 11 May 2026
Published: 29 May 2026
Article Information
Published in
Chinese Journal of Information Fusion
Volume/Issue
Volume 3, Issue 2, 2026
Pages
93-124
Abstract
Image segmentation is an important task in computer vision and plays a critical role in many fields. Fuzzy Active Contour Model (FACM) has been widely applied in image segmentation because it can handle complex shape changes. However, it is difficult for current FACMs to obtain ideal performance when segmenting noisy images. Therefore, this paper proposes a Total Variation Diffusion-Guided Fuzzy Active Contour Model (TVDGFACM), which formulates noisy image segmentation as a hierarchical fusion process. Specifically, this model introduces total variation and adaptively fuses anisotropic and isotropic diffusion mechanisms to suppress noise interference while preserving image edges. Moreover, TVDGFACM fuses local intensity evidence according to regional dependencies and noise-aware pixel reliability, which helps adjust pixel memberships to generate a smooth and coherent segmentation result. Furthermore, a balance factor is constructed based on noise density, which is used to fuse global and local intensity information, thereby ensuring segmentation efficiency and stability. Experiments on synthetic, natural, remote sensing images, and large-scale benchmark dataset show that TVDGFACM is rational and effective.
Graphical Abstract
Keywords
image segmentation
fuzzy active contour model
noisy images
total variation
regional dependencies
Data Availability Statement
Data will be made available on request.
Funding
This work was supported by the National Natural Science Foundation of China under Grant 62473304 and Grant U22A2045.
Conflicts of Interest
The authors declare no conflicts of interest.
AI Use Statement
The authors declare that no generative AI was used in the preparation of this manuscript.
Ethical Approval and Consent to Participate
Not applicable.
References
- Jiang, X., Feng, C., Han, T., Wu, B., & Yang, Y. (2025). Active contour model combining frequency domain information for noisy vessel image segmentation. Pattern Recognition, 112126.
[CrossRef] [Google Scholar] - Li, Z., Zhang, F., Wang, G., Weng, G., & Chen, Y. (2026). An active contour model based on Kullback–Leibler divergence and morphology for image segmentation with edge leakage. Signal Processing, 238, 110143.
[CrossRef] [Google Scholar] - Li, Z., Tang, S., Zeng, Y., Chai, S., Ye, W., Yang, F., & Huang, K. (2024). A level-set method with a multiplicative–additive constraint model for image segmentation and bias correction. Knowledge-Based Systems, 297, 111972.
[CrossRef] [Google Scholar] - Vijai, A., Padmavathi, S., & Venkataraman, D. (2025). Artificial intelligence based semantic segmentation on aerial images with variational mode decomposition. Engineering Applications of Artificial Intelligence, 156, 111140.
[CrossRef] [Google Scholar] - Ge, P., Wan, M., Xu, Y., Kong, X., Kang, Y., Weng, G., ... & Chen, Q. (2025). A hybrid active contour model using local region-based K-medoids for infrared image segmentation. Expert Systems with Applications, 290, 128325.
[CrossRef] [Google Scholar] - Zhao, W., Sang, J., Shu, Y., & Li, D. (2024). Robust image segmentation and bias field correction model based on image structural prior constraint. Expert Systems with Applications, 251, 123961.
[CrossRef] [Google Scholar] - Dickson, A. J., Linsely, J. A., Daniel, V. A. A., & Rahul, K. (2024). Sparse deep belief network coupled with extended local fuzzy active contour model-based liver cancer segmentation from abdomen CT images. Medical & Biological Engineering & Computing, 62(5), 1361-1374.
[CrossRef] [Google Scholar] - Krinidis, S., & Chatzis, V. (2009). Fuzzy energy-based active contours. IEEE Transactions on Image Processing, 18(12), 2747-2755.
[CrossRef] [Google Scholar] - Wu, Y., Ma, W., Gong, M., Li, H., & Jiao, L. (2015). Novel fuzzy active contour model with kernel metric for image segmentation. Applied Soft Computing, 34, 301-311.
[CrossRef] [Google Scholar] - Krinidis, S., & Krinidis, M. (2012, September). Fuzzy energy-based active contours exploiting local information. In IFIP International Conference on Artificial Intelligence Applications and Innovations (pp. 175-184). Berlin, Heidelberg: Springer Berlin Heidelberg.
[CrossRef] [Google Scholar] - Mondal, A., Ghosh, S., & Ghosh, A. (2016). Robust global and local fuzzy energy based active contour for image segmentation. Applied Soft Computing, 47, 191-215.
[CrossRef] [Google Scholar] - Fang, J., Liu, H., Zhang, L., Liu, J., & Liu, H. (2021). Region-edge-based active contours driven by hybrid and local fuzzy region-based energy for image segmentation. Information Sciences, 546, 397-419.
[CrossRef] [Google Scholar] - Zhang, H., Tang, L., & He, C. (2019). A variational level set model for multiscale image segmentation. Information Sciences, 493, 152-175.
[CrossRef] [Google Scholar] - Rabelo, R. A. L., Ribeiro, P. H. A., Santos, W. M. S., Silva, R. C. C., & Souza, J. C. O. (2025). A non-monotone proximal point method for image reconstruction using non-convex total variation models. Computers and Electrical Engineering, 126, 110491.
[CrossRef] [Google Scholar] - Liu, X. (2025). Hyperspectral mixed noise removal using nonconvex low-rank and total generalized variation. Signal Processing: Image Communication, 138, 117344.
[CrossRef] [Google Scholar] - Abualigah, L., Almomani, M. H., Alomari, S. A., Zitar, R. A., Snasel, V., Saleem, K., ... & Ezugwu, A. E. (2025). A control-driven transition strategy for enhanced multi-level threshold image segmentation optimization. Egyptian Informatics Journal, 30, 100646.
[CrossRef] [Google Scholar] - Ren, J., Shang, R., Chen, J., Zhang, W., Feng, J., Liu, M., ... & Stolkin, R. (2024). Sar image segmentation based on complicated region-sensitive adaptive superpixel generation and hybrid edge correction. IEEE Transactions on Geoscience and Remote Sensing, 62, 1-17.
[CrossRef] [Google Scholar] - Cui, H., Xie, Z., Zeng, W., Ma, R., Zhang, Y., Yin, Q., & Xu, Z. (2024). Intuitionistic fuzzy local information C-means algorithm for image segmentation. Information Sciences, 681, 121205.
[CrossRef] [Google Scholar] - Song, B., & Chan, T. (2002). A fast algorithm for level set based optimization. UCLA Cam Report, 2(68). https://ww3.math.ucla.edu/camreport/cam02-68.pdf
[Google Scholar] - Huang, K., Ouyang, J., & Weng, G. (2025). Active contour model based on fuzzy C-means and local pre-fitting energy for image segmentation. Signal, Image and Video Processing, 19(2), 193.
[CrossRef] [Google Scholar] - Dong, B., Bu, Q., Zhu, Z., & Ni, J. (2025). An active contour model with adaptive weighted mean filtering and anisotropic diffusion filtering. Signal Processing, 237, 110071.
[CrossRef] [Google Scholar] - Zhang, F., Bi, X., Wang, G., Weng, G., & Chen, Y. (2025). Anisotropic edge-enhanced active contour model with Gaussian difference for robust multi-category image segmentation. The Visual Computer, 41(12), 10153-10170.
[CrossRef] [Google Scholar] - Rossetti, S., & Pirri, F. (2024). Hierarchy-agnostic unsupervised segmentation: parsing semantic image structure. Advances in Neural Information Processing Systems, 37, 98898-98935.
[Google Scholar] - Benfenati, A., Catozzi, A., Franchini, G., & Porta, F. (2025). Unsupervised noisy image segmentation using Deep Image Prior. Mathematics and Computers in Simulation.
[CrossRef] [Google Scholar] - Zhang, L., Yang, F., Zhang, Y. D., & Zhu, Y. J. (2016, September). Road crack detection using deep convolutional neural network. In 2016 IEEE international conference on image processing (ICIP) (pp. 3708-3712). IEEE.
[CrossRef] [Google Scholar]
Cite This Article
APA Style
Zhang, M., Yang, Y., Zhang, S., Mi, P., & Han, D. (2026). Total Variation Diffusion-Guided Fuzzy Active Contour Model for Noisy Image Segmentation. Chinese Journal of Information Fusion, 3(2), 93-124. https://doi.org/10.62762/CJIF.2025.657389
Export Citation
RIS Format
Compatible with EndNote, Zotero, Mendeley, and other reference managers
TY - JOUR AU - Zhang, Meng AU - Yang, Yi AU - Zhang, Sixian AU - Mi, Pengbo AU - Han, Deqiang PY - 2026 DA - 2026/05/29 TI - Total Variation Diffusion-Guided Fuzzy Active Contour Model for Noisy Image Segmentation JO - Chinese Journal of Information Fusion T2 - Chinese Journal of Information Fusion JF - Chinese Journal of Information Fusion VL - 3 IS - 2 SP - 93 EP - 124 DO - 10.62762/CJIF.2025.657389 UR - https://www.icck.org/article/abs/CJIF.2025.657389 KW - image segmentation KW - fuzzy active contour model KW - noisy images KW - total variation KW - regional dependencies AB - Image segmentation is an important task in computer vision and plays a critical role in many fields. Fuzzy Active Contour Model (FACM) has been widely applied in image segmentation because it can handle complex shape changes. However, it is difficult for current FACMs to obtain ideal performance when segmenting noisy images. Therefore, this paper proposes a Total Variation Diffusion-Guided Fuzzy Active Contour Model (TVDGFACM), which formulates noisy image segmentation as a hierarchical fusion process. Specifically, this model introduces total variation and adaptively fuses anisotropic and isotropic diffusion mechanisms to suppress noise interference while preserving image edges. Moreover, TVDGFACM fuses local intensity evidence according to regional dependencies and noise-aware pixel reliability, which helps adjust pixel memberships to generate a smooth and coherent segmentation result. Furthermore, a balance factor is constructed based on noise density, which is used to fuse global and local intensity information, thereby ensuring segmentation efficiency and stability. Experiments on synthetic, natural, remote sensing images, and large-scale benchmark dataset show that TVDGFACM is rational and effective. SN - 2998-3371 PB - Institute of Central Computation and Knowledge LA - English ER -
BibTeX Format
Compatible with LaTeX, BibTeX, and other reference managers
@article{Zhang2026Total,
author = {Meng Zhang and Yi Yang and Sixian Zhang and Pengbo Mi and Deqiang Han},
title = {Total Variation Diffusion-Guided Fuzzy Active Contour Model for Noisy Image Segmentation},
journal = {Chinese Journal of Information Fusion},
year = {2026},
volume = {3},
number = {2},
pages = {93-124},
doi = {10.62762/CJIF.2025.657389},
url = {https://www.icck.org/article/abs/CJIF.2025.657389},
abstract = {Image segmentation is an important task in computer vision and plays a critical role in many fields. Fuzzy Active Contour Model (FACM) has been widely applied in image segmentation because it can handle complex shape changes. However, it is difficult for current FACMs to obtain ideal performance when segmenting noisy images. Therefore, this paper proposes a Total Variation Diffusion-Guided Fuzzy Active Contour Model (TVDGFACM), which formulates noisy image segmentation as a hierarchical fusion process. Specifically, this model introduces total variation and adaptively fuses anisotropic and isotropic diffusion mechanisms to suppress noise interference while preserving image edges. Moreover, TVDGFACM fuses local intensity evidence according to regional dependencies and noise-aware pixel reliability, which helps adjust pixel memberships to generate a smooth and coherent segmentation result. Furthermore, a balance factor is constructed based on noise density, which is used to fuse global and local intensity information, thereby ensuring segmentation efficiency and stability. Experiments on synthetic, natural, remote sensing images, and large-scale benchmark dataset show that TVDGFACM is rational and effective.},
keywords = {image segmentation, fuzzy active contour model, noisy images, total variation, regional dependencies},
issn = {2998-3371},
publisher = {Institute of Central Computation and Knowledge}
}
Article Metrics
Publisher's Note
ICCK stays neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and Permissions
Copyright © 2026 by the Author(s). Published by Institute of Central Computation and Knowledge. 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/), which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made.
Chinese Journal of Information Fusion
ISSN: 2998-3371 (Online)
| ISSN: 2998-3363 (Print)
Preserved at
Portico
Portico
Scan to read this article
Nantong University, China