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

An example of the line-drawing image with N = 128 used for computational cost comparison.It is clear that the GVF field in (b) is unmatured at iteration , so, the runtime reported in Table 1 for GVF is underestimated.
© Copyright Policy
Related In: Results  -  Collection

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

pone-0110032-g004: An example of the line-drawing image with N = 128 used for computational cost comparison.It is clear that the GVF field in (b) is unmatured at iteration , so, the runtime reported in Table 1 for GVF is underestimated.

Mentions: In order to demonstrate the computation efficiency of the CONVEF model, we coined line-drawing images of dimension to calculate the CONVEF and GVF fields. Since the VEF, VFC and CONVEF models can all be calculated using FFT, their computational costs depend mainly on the size of the convolution kernel. Therefore, we just compare the runtime of the CONVEF model with that of the GVF model. The convolution kernel size for CONVEF is , and the iteration number for GVF is . The results with different N are reported in Table 1, from which one can see that the CONVEF is about 10 to 400 times faster than the GVF since there are two partial differential equations for the GVF to be solved iteratively on the entire image. Fig. 4 shows an example of the line-drawing image with N = 128. It is clear that the GVF field in Fig. 4(b) is unmatured at iteration , so, the runtime reported in Table 1 for GVF is underestimated. This experiment was conducted using MATLAB 2010 on a Thinkpad T60 notebook with 1.83 GHz CPU, 2.5 GB RAM.


Convolutional virtual electric field for image segmentation using active contours.

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

An example of the line-drawing image with N = 128 used for computational cost comparison.It is clear that the GVF field in (b) is unmatured at iteration , so, the runtime reported in Table 1 for GVF is underestimated.
© Copyright Policy
Related In: Results  -  Collection

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

pone-0110032-g004: An example of the line-drawing image with N = 128 used for computational cost comparison.It is clear that the GVF field in (b) is unmatured at iteration , so, the runtime reported in Table 1 for GVF is underestimated.
Mentions: In order to demonstrate the computation efficiency of the CONVEF model, we coined line-drawing images of dimension to calculate the CONVEF and GVF fields. Since the VEF, VFC and CONVEF models can all be calculated using FFT, their computational costs depend mainly on the size of the convolution kernel. Therefore, we just compare the runtime of the CONVEF model with that of the GVF model. The convolution kernel size for CONVEF is , and the iteration number for GVF is . The results with different N are reported in Table 1, from which one can see that the CONVEF is about 10 to 400 times faster than the GVF since there are two partial differential equations for the GVF to be solved iteratively on the entire image. Fig. 4 shows an example of the line-drawing image with N = 128. It is clear that the GVF field in Fig. 4(b) is unmatured at iteration , so, the runtime reported in Table 1 for GVF is underestimated. This experiment was conducted using MATLAB 2010 on a Thinkpad T60 notebook with 1.83 GHz CPU, 2.5 GB RAM.

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