A variational based smart segmentation model for speckled images
A variational based smart segmentation model for speckled images
复制标题
一种基于变分的斑点图像智能分割模型
DOI：
10.1016/j.neucom.2015.07.115
复制
发表时间：
2016
期刊：
影响因子：
6
通讯作者：
Baciu George
中科院分区：
文献类型：
--
作者：
Han Yu;Xu Chen;Baciu George
本文提出了一种新的模糊变分模型来实现合成孔径雷达（SAR）图像等斑点图像的分割任务。该模型的一部分是通过使用所谓的最大化后验概率（MAP）估计方法。该模型的创新之处在于：（1）用Gamma分布代替了经典的高斯分布来模拟图像各均匀区域的灰度值;（2）设计了一个关于模糊隶属度函数的智能正则化项。新设计的正则化项相当于一个自适应加权全变差正则化子。与经典的TV正则化算子相比，该正则化算子不仅具有更稀疏的性质，而且还能防止分割结果退化（过平滑）。此外，提出了一种基于交替方向迭代算法的新算法来求解该模型。该算法综合了分裂Bregman法和Chambolle投影法，提高了算法的效率.数值算例验证了该模型的有效性。
In this paper, we propose a new variational model in the fuzzy framework to achieve the task of partitioning speckled images, such as the synthetic aperture radar (SAR) images. The model is partly derived by using the so-called maximizing a posteriori (MAP) estimation method. The novelties of the model are that (1) the Gamma distribution rather than the classical Gaussian distribution is used to simulate the gray intensities in each homogeneous region of the images; (2) a smart regularization term with respect to fuzzy membership functions is designed. The newly designed regularization term equals to an adaptive weighted total variation (TV) regularizer. Compared with the classical TV regularizer, the proposed regularization term not only has a sparser property, but also protects the segmentation results from degeneration (being over-smoothed). In addition, a new algorithm based on the alternative direction iteration algorithm is proposed to solve the model. The algorithm is efficient since it integrates the split Bregman method and Chambolle׳s projection method. Numerical examples are given to verify the promising efficiency of our model.