摘要
基于数学形态学的基本变换，采用多结构元素，构造了一类多刻度广义形态滤波器并证明了滤波器具有递增性、幂等性和阈值叠加性等重要性质计算机仿真结果证实了这类滤波器不仅可以有效地抑制图象中的噪声。
Based on the basic transformations in mathematical morphology,we construct a class of multiscale generalized morphological filters by using multiple structural elements .Some of their important properties,such as increase,idempotence and threshold superposition,are testified.The results of computer simulation show that these filters can not only effectively suppress noise in images but also preserve the geometrical structure features of the images.
出处
《哈尔滨工程大学学报》
EI
CAS
CSCD
1997年第4期84-90,共7页
Journal of Harbin Engineering University
基金
国家自然科学基金
关键词
形态滤波器
非线性滤波
图象处理
噪声
图象信号
morphological filter
structural element
nonlinear filtering
image processing
