摘要
为提高现有模糊C均值聚类算法(FCM)对噪声图像分割的效果和稳定性,提出一种基于FCM的图像分割算法。利用非局部空间信息构建和图像,根据和图像的直方图,自动选择初始化聚类中心,通过求取目标函数极小值完成图像分割。理论分析和实验结果表明,该算法比现有算法更加有效和稳定,对噪声图像有更强的鲁棒性。
To improve the validity and stability of the existing fuzzy C-means clustering algorithm(FCM) for noise image segmentation,a segmentation algorithm based on FCM was presented.A sum image was set up using non-local information.Initial clustering center was chosen automatically in accordance with histogram of the sum image.The segmentation result was determined by minimizing the object function.Both theoretical analysis and experimental results show that the proposed algorithm is more efficient and stable than the existing algorithms,and has stronger robustness to the noise image.
出处
《计算机工程与设计》
北大核心
2018年第1期159-164,共6页
Computer Engineering and Design
基金
国家自然科学基金项目(61571071)
关键词
图像分割
模糊C均值
非局部信息
和图像
直方图
image segmentation
fuzzy C-means
non-local information
sum image
histogram