Advanced search
1 file | 1.91 MB

Noise-robust method for image segmentation

Ivana Despotovic (UGent) , Vedran Jelača (UGent) , Ewout Vansteenkiste (UGent) and Wilfried Philips (UGent)
Author
Organization
Abstract
Segmentation of noisy images is one of the most challenging problems in image analysis and any improvement of segmentation methods can highly influence the performance of many image processing applications. In automated image segmentation, the fuzzy c-means (FCM) clustering has been widely used because of its ability to model uncertainty within the data, applicability to multi-modal data and fairly robust behaviour. However, the standard FCM algorithm does not consider any information about the spatial linage context and is highly sensitive to noise and other imaging artefacts. Considering above mentioned problems, we developed a new FCM-based approach for the noise-robust fuzzy clustering and we present it in this paper. In this new iterative algorithm we incorporated both spatial and feature space information into the similarity measure and the membership function. We considered that spatial information depends on the relative location and features of the neighbouring pixels. The performance of the proposed algorithm is tested on synthetic image with different noise levels and real images. Experimental quantitative and qualitative segmentation results show that our method efficiently preserves the homogeneity of the regions and is more robust to noise than other FCM-based methods.
Keywords
Fuzzy C-Means, Spatial information, Fuzzy clustering, Noise, Image segmentation

Downloads

  • paper246.pdf
    • full text
    • |
    • open access
    • |
    • PDF
    • |
    • 1.91 MB

Citation

Please use this url to cite or link to this publication:

Chicago
Despotovic, Ivana, Vedran Jelača, Ewout Vansteenkiste, and Wilfried Philips. 2010. “Noise-robust Method for Image Segmentation.” In Lecture Notes in Computer Science, ed. Jacques Blanc-Talon , Don Bone, Wilfried Philips, Dan Popescu, and Paul Scheunders, 6474:153–162. Berlin, Germany: Springer.
APA
Despotovic, I., Jelača, V., Vansteenkiste, E., & Philips, W. (2010). Noise-robust method for image segmentation. In J. Blanc-Talon , D. Bone, W. Philips, D. Popescu, & P. Scheunders (Eds.), LECTURE NOTES IN COMPUTER SCIENCE (Vol. 6474, pp. 153–162). Presented at the 12th International conference on Advanced Concepts for Intelligent Vision Systems (ACIVS 2010), Berlin, Germany: Springer.
Vancouver
1.
Despotovic I, Jelača V, Vansteenkiste E, Philips W. Noise-robust method for image segmentation. In: Blanc-Talon J, Bone D, Philips W, Popescu D, Scheunders P, editors. LECTURE NOTES IN COMPUTER SCIENCE. Berlin, Germany: Springer; 2010. p. 153–62.
MLA
Despotovic, Ivana, Vedran Jelača, Ewout Vansteenkiste, et al. “Noise-robust Method for Image Segmentation.” Lecture Notes in Computer Science. Ed. Jacques Blanc-Talon et al. Vol. 6474. Berlin, Germany: Springer, 2010. 153–162. Print.
@inproceedings{1080046,
  abstract     = {Segmentation of noisy images is one of the most challenging problems in image analysis and any improvement of segmentation methods can highly influence the performance of many image processing applications. In automated image segmentation, the fuzzy c-means (FCM) clustering has been widely used because of its ability to model uncertainty within the data, applicability to multi-modal data and fairly robust behaviour. However, the standard FCM algorithm does not consider any information about the spatial linage context and is highly sensitive to noise and other imaging artefacts. Considering above mentioned problems, we developed a new FCM-based approach for the noise-robust fuzzy clustering and we present it in this paper. In this new iterative algorithm we incorporated both spatial and feature space information into the similarity measure and the membership function. We considered that spatial information depends on the relative location and features of the neighbouring pixels. The performance of the proposed algorithm is tested on synthetic image with different noise levels and real images. Experimental quantitative and qualitative segmentation results show that our method efficiently preserves the homogeneity of the regions and is more robust to noise than other FCM-based methods.},
  author       = {Despotovic, Ivana and Jela\v{c}a, Vedran and Vansteenkiste, Ewout and Philips, Wilfried},
  booktitle    = {LECTURE NOTES IN COMPUTER SCIENCE},
  editor       = { Blanc-Talon , Jacques and Bone, Don and Philips, Wilfried and Popescu, Dan and Scheunders, Paul},
  isbn         = {9783642176876},
  issn         = {0302-9743},
  language     = {eng},
  location     = {Sydney, Australia},
  pages        = {153--162},
  publisher    = {Springer},
  title        = {Noise-robust method for image segmentation},
  url          = {http://dx.doi.org/10.1007/978-3-642-17688-3\_16},
  volume       = {6474},
  year         = {2010},
}

Altmetric
View in Altmetric
Web of Science
Times cited: