Vector field convolution (VFC) provides a successful external force for an active contour model. However, it fails to extract the complex geometries, especially the deep concavity when the initial contour is set outside the object or the concave region. In this letter, dynamically constrained vector field convolution (DCVFC) external force is proposed to solve this problem. In DCVFC, the indicator function with respect to the evolving contour is introduced to restrain the correlation of external forces generated by different edges, and the forces dynamically generated by complex concave edges gradually make the contour move to the object. On the other hand, traditional vector field, a component of the proposed DCVFC, makes the evolving contour stop at the object boundary. The connections between VFC and DCVFC are also analyzed. DCVFC maintains desirable properties of VFC, such as robustness to initialization. Experimental results demonstrate that DCVFC snake provides a much better segmentation than VFC snake.
Guoqi LIU
South China University of Technology
Zhiheng ZHOU
South China University of Technology
Shengli XIE
South China University of Technology
Dongcheng WU
South China University of Technology
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
Guoqi LIU, Zhiheng ZHOU, Shengli XIE, Dongcheng WU, "Dynamically Constrained Vector Field Convolution for Active Contour Model" in IEICE TRANSACTIONS on Information,
vol. E96-D, no. 11, pp. 2500-2503, November 2013, doi: 10.1587/transinf.E96.D.2500.
Abstract: Vector field convolution (VFC) provides a successful external force for an active contour model. However, it fails to extract the complex geometries, especially the deep concavity when the initial contour is set outside the object or the concave region. In this letter, dynamically constrained vector field convolution (DCVFC) external force is proposed to solve this problem. In DCVFC, the indicator function with respect to the evolving contour is introduced to restrain the correlation of external forces generated by different edges, and the forces dynamically generated by complex concave edges gradually make the contour move to the object. On the other hand, traditional vector field, a component of the proposed DCVFC, makes the evolving contour stop at the object boundary. The connections between VFC and DCVFC are also analyzed. DCVFC maintains desirable properties of VFC, such as robustness to initialization. Experimental results demonstrate that DCVFC snake provides a much better segmentation than VFC snake.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E96.D.2500/_p
Copy
@ARTICLE{e96-d_11_2500,
author={Guoqi LIU, Zhiheng ZHOU, Shengli XIE, Dongcheng WU, },
journal={IEICE TRANSACTIONS on Information},
title={Dynamically Constrained Vector Field Convolution for Active Contour Model},
year={2013},
volume={E96-D},
number={11},
pages={2500-2503},
abstract={Vector field convolution (VFC) provides a successful external force for an active contour model. However, it fails to extract the complex geometries, especially the deep concavity when the initial contour is set outside the object or the concave region. In this letter, dynamically constrained vector field convolution (DCVFC) external force is proposed to solve this problem. In DCVFC, the indicator function with respect to the evolving contour is introduced to restrain the correlation of external forces generated by different edges, and the forces dynamically generated by complex concave edges gradually make the contour move to the object. On the other hand, traditional vector field, a component of the proposed DCVFC, makes the evolving contour stop at the object boundary. The connections between VFC and DCVFC are also analyzed. DCVFC maintains desirable properties of VFC, such as robustness to initialization. Experimental results demonstrate that DCVFC snake provides a much better segmentation than VFC snake.},
keywords={},
doi={10.1587/transinf.E96.D.2500},
ISSN={1745-1361},
month={November},}
Copy
TY - JOUR
TI - Dynamically Constrained Vector Field Convolution for Active Contour Model
T2 - IEICE TRANSACTIONS on Information
SP - 2500
EP - 2503
AU - Guoqi LIU
AU - Zhiheng ZHOU
AU - Shengli XIE
AU - Dongcheng WU
PY - 2013
DO - 10.1587/transinf.E96.D.2500
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E96-D
IS - 11
JA - IEICE TRANSACTIONS on Information
Y1 - November 2013
AB - Vector field convolution (VFC) provides a successful external force for an active contour model. However, it fails to extract the complex geometries, especially the deep concavity when the initial contour is set outside the object or the concave region. In this letter, dynamically constrained vector field convolution (DCVFC) external force is proposed to solve this problem. In DCVFC, the indicator function with respect to the evolving contour is introduced to restrain the correlation of external forces generated by different edges, and the forces dynamically generated by complex concave edges gradually make the contour move to the object. On the other hand, traditional vector field, a component of the proposed DCVFC, makes the evolving contour stop at the object boundary. The connections between VFC and DCVFC are also analyzed. DCVFC maintains desirable properties of VFC, such as robustness to initialization. Experimental results demonstrate that DCVFC snake provides a much better segmentation than VFC snake.
ER -