基于熵的两区域图像分割

图像分割在多媒体,图像处理,计算机视觉领域扮演着重要角色。提出了基于图像分割熵的二区域图像分割方法。 首先,根据熵的特性:单个随机变量所对应的熵越大,所包含的信息量越大,图像是单一区域时,所含的信息量(熵)较小,引入图像分割熵(ISE)测度,用于度量两区域图像分割准确程度,将两区域图像分割问题转化成ISE最小值问题。然后,采用迭代图切(graph cut)算法给出ISE最小值问题的近似解,实现二区域图像分割。实验结果表明,基于图像分割熵的二区域图像分割方法是可行有效的。

Entropy based bi-region image segmentation

Image segmentation plays an important part in the areas of multimedia, image processing and computer vision. In the paper, the authors propose an image segmentation approach based on an entropy measurer. Specifically, the image segmentation entropy (ISE) is defined to describe the information of an image region. We further prove that the image after segmentation have the minimum ISE, if the image is correctly partitioned. Then, the image segmentation problem is cast into an optimization problem which minimizes ISE. Finally, we use the iterative graph cut approach (IGCA) to solve the optimization problem. The experiments provided in the paper show that our ISE based segmentation approach works well.