Wang Yuanquan, Zhu Ce, Zhang Jiawan, Jian Yuden
School of Computer Science, Tianjin University of Technology, Tianjin, China.
School of Electronic Engineering, University of Electronic Science and Technology of China, Chengdu, China.
PLoS One. 2014 Oct 31;9(10):e110032. doi: 10.1371/journal.pone.0110032. eCollection 2014.
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.
梯度向量流（GVF）是一种用于主动轮廓的有效外力；然而，它存在计算量过大的问题。虚拟电场（VEF）模型后来被提出作为GVF模型的一种改进，它可以使用快速傅里叶变换（FFT）实时实现。在这项工作中，我们提出了VEF模型的一种扩展，简称为卷积虚拟电场（CONVEF）。这个提出的CONVEF模型将VEF模型视为一种卷积操作，并在卷积核中采用了一种修改后的距离。CONVEF模型也与向量场卷积（VFC）模型密切相关。与GVF、VEF和VFC模型相比，CONVEF模型不仅具有这些模型的一些理想特性，如扩大捕获范围、U形凹度收敛、目标轮廓收敛和初始化不敏感，还具有一些其他有趣的特性，如G形凹度收敛、相邻物体分离、噪声抑制以及同时保持弱边缘。同时，CONVEF模型也可以通过使用FFT实时实现。实验结果说明了CONVEF模型在合成图像和自然图像上的这些优势。
