Abstract
The gradient vector flow (GVF) is an effective external force to deform the active contours. However, it suffers from high computational cost. For efficiency, the virtual electric field (VEF) model has been proposed, which can be implemented in real time thanks to fast Fourier transform (FFT). The VEF model has large capture range and low computation cost, but it has the limitations of sensitivity to noise and leakage on weak edge. The recently proposed CONVEF (Convolutional Virtual Electric Field) model takes the VEF model as a convolutional operation and employed another convolution kernel to overcome the drawbacks of the VEF model. In this paper, we employ an edge stopping function similar to that in the anisotropic diffusion to further improve the CONVEF model, and the proposed model is referred to as MCONVEF (Modified CONVEF) model. In addition, a piecewise constant approximation algorithm is borrowed to accelerate the calculation of the MCONVEF model. The proposed MCONVEF model is compared with the GVF and VEF models, and the experimental results are presented to demonstrate its superiority in terms of noise robustness, weak edge preserving and deep concavity convergence.
Highlights
Image segmentation is a fundamental problem in computer vision [1,2] and the active contour, or snake model [3,4], dominates this community in the past thirty years
We evaluate the proposed MCONVEF snake model using the U-shape image corrupted with salt-and-pepper noise varying from 5% to 30%
Since the computational cost of both the MCONVEF and virtual electric field (VEF) model depends on the size of the convolution kernel, the convolution kernels are of size N/2 N/2, and for the gradient vector flow (GVF) model, the iteration number is N for an image of size N N
Summary
Image segmentation is a fundamental problem in computer vision [1,2] and the active contour, or snake model [3,4], dominates this community in the past thirty years. In order to overcome the drawbacks of the traditional snake model, Xu and Prince proposed the gradient vector flow (GVF) model that is one of the most successful external forces. There are two impressive works approximating the GVF, which are based on convolution and FFT and can be implemented in real-time, i.e., the virtual electric field (VEF) [29] and the gradient vector convolution [30]. The VEF model possesses some desirable properties of the GVF model such as large capture range and concavity convergence, and has low computation cost, there is room for improvement on noise robustness and weak edge preserving. The recently proposed CONVEF model extends the VEF model by using another convolution kernel and can preserve weak edges to some degree [31].
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
