In this paper, we propose a hybrid fuzzy geometric active contour method, which embeds the spatial fuzzy clustering into the evolution of geometric active contour. In every iteration, the evolving curve works as a spatial constraint on the fuzzy clustering, and the clustering result is utilized to construct the fuzzy region force. On one hand, the fuzzy region force provides a powerful capability to avoid the leakages at weak boundaries and enhances the robustness to various noises. On the other hand, the local information obtained from the gradient feature map contributes to locating the object boundaries accurately and improves the performance on the images with heterogeneous foreground or background. Experimental results on synthetic and real images have shown that our model can precisely extract object boundaries and perform better than the existing representative hybrid active contour approaches.
Danyi LI
Tsinghua University
Weifeng LI
Tsinghua University
Qingmin LIAO
Tsinghua University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Danyi LI, Weifeng LI, Qingmin LIAO, "A Fuzzy Geometric Active Contour Method for Image Segmentation" in IEICE TRANSACTIONS on Information,
vol. E96-D, no. 9, pp. 2107-2114, September 2013, doi: 10.1587/transinf.E96.D.2107.
Abstract: In this paper, we propose a hybrid fuzzy geometric active contour method, which embeds the spatial fuzzy clustering into the evolution of geometric active contour. In every iteration, the evolving curve works as a spatial constraint on the fuzzy clustering, and the clustering result is utilized to construct the fuzzy region force. On one hand, the fuzzy region force provides a powerful capability to avoid the leakages at weak boundaries and enhances the robustness to various noises. On the other hand, the local information obtained from the gradient feature map contributes to locating the object boundaries accurately and improves the performance on the images with heterogeneous foreground or background. Experimental results on synthetic and real images have shown that our model can precisely extract object boundaries and perform better than the existing representative hybrid active contour approaches.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E96.D.2107/_p
Copy
@ARTICLE{e96-d_9_2107,
author={Danyi LI, Weifeng LI, Qingmin LIAO, },
journal={IEICE TRANSACTIONS on Information},
title={A Fuzzy Geometric Active Contour Method for Image Segmentation},
year={2013},
volume={E96-D},
number={9},
pages={2107-2114},
abstract={In this paper, we propose a hybrid fuzzy geometric active contour method, which embeds the spatial fuzzy clustering into the evolution of geometric active contour. In every iteration, the evolving curve works as a spatial constraint on the fuzzy clustering, and the clustering result is utilized to construct the fuzzy region force. On one hand, the fuzzy region force provides a powerful capability to avoid the leakages at weak boundaries and enhances the robustness to various noises. On the other hand, the local information obtained from the gradient feature map contributes to locating the object boundaries accurately and improves the performance on the images with heterogeneous foreground or background. Experimental results on synthetic and real images have shown that our model can precisely extract object boundaries and perform better than the existing representative hybrid active contour approaches.},
keywords={},
doi={10.1587/transinf.E96.D.2107},
ISSN={1745-1361},
month={September},}
Copy
TY - JOUR
TI - A Fuzzy Geometric Active Contour Method for Image Segmentation
T2 - IEICE TRANSACTIONS on Information
SP - 2107
EP - 2114
AU - Danyi LI
AU - Weifeng LI
AU - Qingmin LIAO
PY - 2013
DO - 10.1587/transinf.E96.D.2107
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E96-D
IS - 9
JA - IEICE TRANSACTIONS on Information
Y1 - September 2013
AB - In this paper, we propose a hybrid fuzzy geometric active contour method, which embeds the spatial fuzzy clustering into the evolution of geometric active contour. In every iteration, the evolving curve works as a spatial constraint on the fuzzy clustering, and the clustering result is utilized to construct the fuzzy region force. On one hand, the fuzzy region force provides a powerful capability to avoid the leakages at weak boundaries and enhances the robustness to various noises. On the other hand, the local information obtained from the gradient feature map contributes to locating the object boundaries accurately and improves the performance on the images with heterogeneous foreground or background. Experimental results on synthetic and real images have shown that our model can precisely extract object boundaries and perform better than the existing representative hybrid active contour approaches.
ER -