基于MSP-ROA边缘检测和区域合并的图像组合分割方法

Image Segmentation Based on MSP-ROA Edge Detection and Region Merging

提出一种基于MSP-ROA边缘检测和区域合并的图像组合分割算法,算法中对边缘检测的结果做种子生长、标注和区域填充,并根据相似性准则对填充的初始分割结果进行相邻区域的合并处理,最终得到同质性和连通性都较好的图像分割结果。

This paper firstly introduces the concept of image segmentation. A new method of image segmentation which based on MSPROA edge detection and region merging is proposed. After edge detecting, the algorithms including seed growing, region signing and region filling are used to have a good image segmentation in which the segments have good connectivity and homogeneity. Finally, the real image data is applied to validate the above algorithm.