full
search.png

Search

close.png

Cancel

arrow
Volume 26, Issue 1
Advection-Enhanced Gradient Vector Flow for Active-Contour Image Segmentation

Po-Wen Hsieh, Pei-Chiang Shao & Suh-Yuh Yang

DOI: 10.4208/cicp.OA-2018-0068

Commun. Comput. Phys., 26 (2019), pp. 206-232.

Published online: 2019-02

Preview Full PDF 3890 36666

Cited by

google scholar semantic scholar
Export citation
  • Abstract

In this paper, we propose a new gradient vector flow model with advection enhancement, called advection-enhanced gradient vector flow, for calculating the external force employed in the active-contour image segmentation. The proposed model is mainly inspired by the functional derivative of an adaptive total variation regularizer whose minimizer is expected to be able to effectively preserve the desired object boundary. More specifically, by incorporating an additional advection term into the usual gradient vector flow model, the resulting external force can much better help the active contour to recover missing edges, to converge to a narrow and deep concavity, and to preserve weak edges. Numerical experiments are performed to demonstrate the high performance of the newly proposed model.

  • Keywords

Image segmentation, active contour, gradient vector flow, external force.

  • AMS Subject Headings

68U10, 65K10

  • Copyright

COPYRIGHT: © Global Science Press

  • Email address
  • BibTex
  • RIS
  • TXT
@Article{CiCP-26-206, author = {Po-Wen Hsieh, Pei-Chiang Shao and Suh-Yuh Yang}, title = {Advection-Enhanced Gradient Vector Flow for Active-Contour Image Segmentation}, journal = {Communications in Computational Physics}, year = {2019}, volume = {26}, number = {1}, pages = {206--232}, abstract = {

In this paper, we propose a new gradient vector flow model with advection enhancement, called advection-enhanced gradient vector flow, for calculating the external force employed in the active-contour image segmentation. The proposed model is mainly inspired by the functional derivative of an adaptive total variation regularizer whose minimizer is expected to be able to effectively preserve the desired object boundary. More specifically, by incorporating an additional advection term into the usual gradient vector flow model, the resulting external force can much better help the active contour to recover missing edges, to converge to a narrow and deep concavity, and to preserve weak edges. Numerical experiments are performed to demonstrate the high performance of the newly proposed model.

}, issn = {1991-7120}, doi = {https://doi.org/10.4208/cicp.OA-2018-0068}, url = {http://global-sci.org/intro/article_detail/cicp/13032.html} }
TY - JOUR T1 - Advection-Enhanced Gradient Vector Flow for Active-Contour Image Segmentation AU - Po-Wen Hsieh, Pei-Chiang Shao & Suh-Yuh Yang JO - Communications in Computational Physics VL - 1 SP - 206 EP - 232 PY - 2019 DA - 2019/02 SN - 26 DO - http://doi.org/10.4208/cicp.OA-2018-0068 UR - https://global-sci.org/intro/article_detail/cicp/13032.html KW - Image segmentation, active contour, gradient vector flow, external force. AB -

In this paper, we propose a new gradient vector flow model with advection enhancement, called advection-enhanced gradient vector flow, for calculating the external force employed in the active-contour image segmentation. The proposed model is mainly inspired by the functional derivative of an adaptive total variation regularizer whose minimizer is expected to be able to effectively preserve the desired object boundary. More specifically, by incorporating an additional advection term into the usual gradient vector flow model, the resulting external force can much better help the active contour to recover missing edges, to converge to a narrow and deep concavity, and to preserve weak edges. Numerical experiments are performed to demonstrate the high performance of the newly proposed model.

Po-Wen Hsieh, Pei-Chiang Shao and Suh-Yuh Yang. (2019). Advection-Enhanced Gradient Vector Flow for Active-Contour Image Segmentation. Communications in Computational Physics. 26 (1). 206-232. doi:10.4208/cicp.OA-2018-0068
Copy to clipboard
BibteX RIS TXT
The citation has been copied to your clipboard