摘要
传统分水岭图像分割算法主要基于梯度模值图像,寻找集水盆地,易产生过分割现象。本文提出了基于MIL改进的分水岭图像分割算法,借助MIL软件开发性强、函数库功能强大等特点,对粘连目标图像进行了分割。实验证明,该方法具有较强的有效性和实用性。
The traditional watershed image segmentation algorithm acting on gradient modulus value image and looking for catchment basin,easyly brings over segmentation phenomenon.This paper proposes an improved watershed image segmentation algorithm based on MIL software,using Mil software's strong development and powerful function library,the object images of adhesion have good segmentation.The method is demonstrated it's validity and practicability by the experiments.
出处
《中原工学院学报》
CAS
2016年第6期-,共4页
Journal of Zhongyuan University of Technology
基金
河南省基础与前沿研究项目(142300410042)
关键词
分水岭图像分割算法
梯度模值
集水盆地
过分割
粘连目标
watershed image segmentation algorithm
gradient modulus value
catchment basin
over segmentation
object images of adhesion
