摘要
多阈值图像分割中经常出现所选阈值数量不能事先确定的情况。为解决这一问题,提出一种基于聚类技术的多阈值图像分割方法,通过Mean Shift技术找出模式中心,通过迭代选择确定相邻模式中心的不同阈值,最后用多阈值完成对图像的分割。仿真实验结果表明,这一方法可有效应用于图像分割,并取得较好的效果。
The selected threshold quantity often cannot be determined in advance in image segmentation based on multi-threshold. A multi-threshold segmentation method is proposed based on clustering to solve the problem. The pattern centers are found through Mean Shift technology,various thresholds of adjacent pattern centers are determined by iterative selection method, and image segmentation is completed by the method of multi-threshold. The experimental results show that the proposed method is effective and can obtain good effect.
作者
陈强
CHEN Qiang(Department of Science and Technology,Ankang University,Ankang Shaanxi 725000,China)
出处
《太赫兹科学与电子信息学报》
北大核心
2018年第4期715-718,共4页
Journal of Terahertz Science and Electronic Information Technology
基金
安康市科技局计划基金资助项目(2017AK01-09)
安康学院青年基金资助项目(2017AYQN08)
关键词
多阈值
图像分割
聚类方法
迭代
multi-threshold
image segmentation
clustering method
iteration
