一种改进的基于图的图像分割方法

摘要

An improved segmentation method is proposed. The definitions of metric functions including weight function of edges and determination function are given firstly. The determination function is used to find out the borderline between regions, and then the segmentation is performed based on the borderline. By redefining the metric function and combining global features with local features,the improved method has better measurement of interior difference and exterior difference, and has higher speed as well. The experimental results show that the improved method is more efficient than existing one.%提出一种改进的基于图的分割方法.该方法重新定义了边权重函数、判定函数等度量函数,然后利用判定函数来判别区域间的边界,从而完成分割.该方法能兼顾全局和局部特征,从而更好的度量区域内部的差别和区域之间的差别,具有了更快的分割速度.实验表明,改进的方法具有更好的效率.