局部熵驱动区域主动轮廓的局部化框架

Localizing Framework of Region-based Active Contours Driven by Local Entropy

提出一种将任意基于区域主动轮廓线模型进行局部化推广的框架。该框架的能量泛涵包含一个惩罚区域弧长的几何正则项和一个局部区域数据拟合项。根据图像像素空间排列的相关性,采用一个滑动窗函数提取图像局部熵,将图像从灰度空间转化到相应局部熵特征空间。在局部熵特征空间,采用另外的窗函数进行局部区域信息提取,从而推导出区域主动轮廓线模型的局部化框架。以CV模型为例推导局部化过程,并对2种常用的窗函数进行分析比较。实验结果表明,该方法可以成功分割一类包含有杂乱特征的图像。

This paper proposes a framework which allows any region-based active contours can be re-formulated in a local way.The energy function of this framework consists of a geometric regularization term that penalizes the length of region boundaries and a data fitting term in a local region.It uses a slide window function to extract the local entropy according to the relationship of spatial arrangements of image pixel,which can map intensity space of image to local entropy space.Another window function can be used to extract local region information so that getting the localizing region-based active contours framework.It takes CV model as an example to demonstrate it.The analysis and comparison of the two familiar window functions also can be done.Experimental results for images illustrate that this model can segment the cluttered images.