Limits...
Convolutional virtual electric field for image segmentation using active contours.

Wang Y, Zhu C, Zhang J, Jian Y - PLoS ONE (2014)

Bottom Line: Gradient vector flow (GVF) is an effective external force for active contours; however, it suffers from heavy computation load.Meanwhile, the CONVEF model can also be implemented in real-time by using FFT.Experimental results illustrate these advantages of the CONVEF model on both synthetic and natural images.

View Article: PubMed Central - PubMed

Affiliation: School of Computer Science, Tianjin University of Technology, Tianjin, China.

ABSTRACT
Gradient vector flow (GVF) is an effective external force for active contours; however, it suffers from heavy computation load. The virtual electric field (VEF) model, which can be implemented in real time using fast Fourier transform (FFT), has been proposed later as a remedy for the GVF model. In this work, we present an extension of the VEF model, which is referred to as CONvolutional Virtual Electric Field, CONVEF for short. This proposed CONVEF model takes the VEF model as a convolution operation and employs a modified distance in the convolution kernel. The CONVEF model is also closely related to the vector field convolution (VFC) model. Compared with the GVF, VEF and VFC models, the CONVEF model possesses not only some desirable properties of these models, such as enlarged capture range, u-shape concavity convergence, subject contour convergence and initialization insensitivity, but also some other interesting properties such as G-shape concavity convergence, neighboring objects separation, and noise suppression and simultaneously weak edge preserving. Meanwhile, the CONVEF model can also be implemented in real-time by using FFT. Experimental results illustrate these advantages of the CONVEF model on both synthetic and natural images.

Show MeSH

Related in: MedlinePlus

Results on a CT image.(a) Cardiac CT image, convergence of (b) VEF snake, (c) CONVEF snake with n = 1.5, h = 2.0, and (d) CONVEF snake with n = 2.0, h = 6.0.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4216009&req=5

pone-0110032-g011: Results on a CT image.(a) Cardiac CT image, convergence of (b) VEF snake, (c) CONVEF snake with n = 1.5, h = 2.0, and (d) CONVEF snake with n = 2.0, h = 6.0.

Mentions: A third example is a cardiac CT image with inhomogeneity, shown in Fig. 11(a). We also aim at extracting the endocardium of the left ventricle (LV). The difficulty for this task is the strong edges stemming from the bones nearby the LV. Fig. 11(b) shows the evolution of the VEF snake while Figs. 11(c) and (d) show the results of the CONVEF snakes with different parameter settings. These results show that the VEF snake leaks out and moves across the endocardium boundary and sticks to the bones, whereas the CONVEF snakes converge correctly to the boundary of the endocardium.


Convolutional virtual electric field for image segmentation using active contours.

Wang Y, Zhu C, Zhang J, Jian Y - PLoS ONE (2014)

Results on a CT image.(a) Cardiac CT image, convergence of (b) VEF snake, (c) CONVEF snake with n = 1.5, h = 2.0, and (d) CONVEF snake with n = 2.0, h = 6.0.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4216009&req=5

pone-0110032-g011: Results on a CT image.(a) Cardiac CT image, convergence of (b) VEF snake, (c) CONVEF snake with n = 1.5, h = 2.0, and (d) CONVEF snake with n = 2.0, h = 6.0.
Mentions: A third example is a cardiac CT image with inhomogeneity, shown in Fig. 11(a). We also aim at extracting the endocardium of the left ventricle (LV). The difficulty for this task is the strong edges stemming from the bones nearby the LV. Fig. 11(b) shows the evolution of the VEF snake while Figs. 11(c) and (d) show the results of the CONVEF snakes with different parameter settings. These results show that the VEF snake leaks out and moves across the endocardium boundary and sticks to the bones, whereas the CONVEF snakes converge correctly to the boundary of the endocardium.

Bottom Line: Gradient vector flow (GVF) is an effective external force for active contours; however, it suffers from heavy computation load.Meanwhile, the CONVEF model can also be implemented in real-time by using FFT.Experimental results illustrate these advantages of the CONVEF model on both synthetic and natural images.

View Article: PubMed Central - PubMed

Affiliation: School of Computer Science, Tianjin University of Technology, Tianjin, China.

ABSTRACT
Gradient vector flow (GVF) is an effective external force for active contours; however, it suffers from heavy computation load. The virtual electric field (VEF) model, which can be implemented in real time using fast Fourier transform (FFT), has been proposed later as a remedy for the GVF model. In this work, we present an extension of the VEF model, which is referred to as CONvolutional Virtual Electric Field, CONVEF for short. This proposed CONVEF model takes the VEF model as a convolution operation and employs a modified distance in the convolution kernel. The CONVEF model is also closely related to the vector field convolution (VFC) model. Compared with the GVF, VEF and VFC models, the CONVEF model possesses not only some desirable properties of these models, such as enlarged capture range, u-shape concavity convergence, subject contour convergence and initialization insensitivity, but also some other interesting properties such as G-shape concavity convergence, neighboring objects separation, and noise suppression and simultaneously weak edge preserving. Meanwhile, the CONVEF model can also be implemented in real-time by using FFT. Experimental results illustrate these advantages of the CONVEF model on both synthetic and natural images.

Show MeSH
Related in: MedlinePlus