摘要
本文对基于形态学分水岭算法进行了深入的研究,并针对其存在的过分割问题对分水岭算法提出改进:使用区域合并方法限制允许出现的区域的数目,这种改进的方法不仅可以很好地抑制过分割问题,还能有效分割出图像中的感兴趣区域,以达到提取图像有效边缘信息的目的。将此方法在OpenCV下进行实验,结果表明这种方法可以有效清除干扰噪声及局部极小值,从而得到精确的分割结果。
In this paper,we carried out in-depth research on the watershed algorithm based on morphology,and put forward an improved method in view of the existing problem of over segmentation.The method of region merging was used to limit the number of allowable regions,and the improved method can not only inhibit over segmentation phenomenon,but also segment the region of interest in the image,in order to achieve the purpose of extracting the effective edge information of image.The method was experimented under OpenCV,and the result showed that the method can effectively eliminate local minimum value and noise,so as to achieve the accurate segmentation results.
基金
吉林省科技发展计划项目青年科研基金(201201112)
