Level Set Methods Implementation for Image Levelsets and Image Contour
Level Set Methods Implementation for Image Levelsets and Image Contour
复制标题
图像水平集和图像轮廓的水平集方法实现
DOI：
--
复制
发表时间：
2009
期刊：
影响因子：
--
通讯作者：
N. Salman
中科院分区：
文献类型：
--
作者：
N. Salman
概述在水平集(平均曲率流)的曲率下平滑图像，创建图像数据的等高线曲线图。为此，使用了一个高级函数(Volve2D)，它可以利用以下任意组合：1)曲线法线方向的力，2)基于曲率的力，以及3)在外部矢量场影响下的演化。此函数接受一个输入，对其进行N次迭代并返回结果。因此，本文在基于曲率的作用力下对图像的所有水平集进行平滑处理，并计算出原始图像的水平集。然后经过25-50次的平滑迭代对图像进行平滑处理，然后计算其相应的水平集。本文还利用MatLab函数IMCONTOUR(IMG)绘制了强度图像(IMG)的等高线图。该方法准确地给出了平滑前后图像的水平集。计算了不同处理图像的处理时间。最后将结果与活动轮廓法和不需要重新初始化的水平集方法进行了比较。
Summary Smoothing an image under the curvature of its level sets (Mean curvature flow), create contour plot of image data were used. To do that, a high level function (evolve2D) was used that can utilize any combination of: 1) a force in the normal direction to the curve, 2) a curvature-based force, and 3) evolution under the influence of an external vector field. This function takes an input, evolves it N iterations and returns the result. So; in this paper, all level sets of the image are smoothed under curvature-based forces and the level sets of the original image are calculated. Then the image was smoothed after 25-50 iterations of smoothing, and then we calculated its corresponding level sets. Also in this paper the Matlab function IMCONTOUR (img) was used to draw a contour plot of the intensity image ( img). The method gives us accurately the level sets of our image before and after smoothing. The processing time for different processed images was calculated. Finally the results were compared with active contour method and levelset without re-initialization method.