基于相似性和统计性的超像素的图像分割

Image segmentation based on super-pixel similarity and statistical

为了解决超像素图像分割的过分割问题,提出了一种基于超像素区域颜色直方图相似性和统计特性的合并判断准则,用来合并超像素图像分割的区域。该合并准则将超像素分割结果作为区域合并的基本单元,利用基本单元的颜色相似性、空间距离大小和统计特性进行区域合并,以解决超像素图像分割中存在的过分割问题。仿真实验结果表明,该方法能有效地改善超像素过分割问题,并且用于评价分割算法的概率Rand指数和信息变化指数都有所提高。

In order to solve the over-segmentation problem of super-pixel image segmentation, a merging criterion based on color histogram similarity and statistical characteristics of super-pixel to merge super-pixel image segmentation region is proposed. The merging criterion uses the super-pixel regional segmentation results as the basic units, using the color similarity, the size of the space distance, and statistical characteristics of basic units for region merging, to solve the over-segmentation problem of super-pixel image segmentation. Simulation results show that the algorithm can solve the problem of super-pixel over-segmentation, and the index PRI and VoI for evaluating segmentation algorithms are improved.