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

Blob-like concavity convergence of the CONVEF, VFC, and GVF snakes.The results using CONVEF snake are in row (a), and those in rows (b) and (c) are the results using VFC and GVF snakes, respectively. The parameters to calculate the GVF field are , and #iteration = 200, and the other corresponding parameters are listed in the subcaption of each subfigure.
© Copyright Policy
Related In: Results  -  Collection

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

pone-0110032-g006: Blob-like concavity convergence of the CONVEF, VFC, and GVF snakes.The results using CONVEF snake are in row (a), and those in rows (b) and (c) are the results using VFC and GVF snakes, respectively. The parameters to calculate the GVF field are , and #iteration = 200, and the other corresponding parameters are listed in the subcaption of each subfigure.

Mentions: Fig. 6 shows the results of the CONVEF, VFC, and GVF snakes on S-shape, 3-shape, C-shape, as well as G-shape. The results show that the CONVEF snake evolves into the concave region progressively and steadily and locate these blob-like objects correctly. However, the GVF and VFC snakes failed. The success of the CONVEF snake is attributed to weighting more on faraway points with small n. The VFC snakes with fails to converge to these concavities although the ζ in is large enough and boundary leakage occurs. Another observation in row (c) for the GVF snake is that the initial contours are very close to the objects. The reason behind this observation is that the capture range of GVF is not large enough and there are critical points[58] which should be outside the initial contours.


Convolutional virtual electric field for image segmentation using active contours.

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

Blob-like concavity convergence of the CONVEF, VFC, and GVF snakes.The results using CONVEF snake are in row (a), and those in rows (b) and (c) are the results using VFC and GVF snakes, respectively. The parameters to calculate the GVF field are , and #iteration = 200, and the other corresponding parameters are listed in the subcaption of each subfigure.
© Copyright Policy
Related In: Results  -  Collection

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

pone-0110032-g006: Blob-like concavity convergence of the CONVEF, VFC, and GVF snakes.The results using CONVEF snake are in row (a), and those in rows (b) and (c) are the results using VFC and GVF snakes, respectively. The parameters to calculate the GVF field are , and #iteration = 200, and the other corresponding parameters are listed in the subcaption of each subfigure.
Mentions: Fig. 6 shows the results of the CONVEF, VFC, and GVF snakes on S-shape, 3-shape, C-shape, as well as G-shape. The results show that the CONVEF snake evolves into the concave region progressively and steadily and locate these blob-like objects correctly. However, the GVF and VFC snakes failed. The success of the CONVEF snake is attributed to weighting more on faraway points with small n. The VFC snakes with fails to converge to these concavities although the ζ in is large enough and boundary leakage occurs. Another observation in row (c) for the GVF snake is that the initial contours are very close to the objects. The reason behind this observation is that the capture range of GVF is not large enough and there are critical points[58] which should be outside the initial contours.

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