The C-V model with motion factor
加移动因子的C-V模型

One advantage of C-V model among the variational level set methods is that it can detect image boundaries which were not defined by gradient. However, when detecting these type boundaries, the C-V model only consider the mean value of each region without local information, so though the C-V model can get non-gradient defined image boundary, its segmentation result contains errors. The above problem is solved by importing the motion factor to the C-V model in this paper. Where, the motion factor is defined as a function of local convexities of image. By adjusting parameters of the motion factor, the novel model can adjust the height of its 0-level set, i.e., can make the 0-level set get close to the plane which the target belongs to, so can eliminate the partition errors. We present the partial differential model, and experiments validate the quality of the segmentations obtained.