摘要
基于数学形态学的边缘检测过程中,不同形状、不同尺度的结构元素在滤除噪声和保持边缘细节方面的作用是不同的,为此提出了一种基于多形状多尺度结构元素的自适应边缘检测算法,分别使用不同方向和大小的结构元素提取图像边缘,通过计算信息熵自适应确定权重系数,对多形状结构元素和多尺度结构元素检测的边缘做融合处理.实验结果表明,该算法与几种经典边缘检测算子相比,有效抑制了噪声影响,提高了检测精度,对各种不同图像具有很好的鲁棒性.
In the process of edge detection based on mathematical morphology,the structural elements of different shapes/scales play different roles in noise filtering and keeping edge details intact.An adaptive edge detection algorithm based on multi-shape/scale structural elements was therefore proposed,where the image edge was extracted using different directions/sizes structural elements.Then,the weight factors were determined adaptively by computing the information entropy so as to integrate the edges detected by multi-shape and multi-scale structural elements.Experimental results showed that the proposed algorithm can suppress the interference of noise more effectively in comparison with several classical edge detection algorithm,thus improving the detection accuracy and robustness of different images.
出处
《东北大学学报（自然科学版）》
EI
CAS
CSCD
北大核心
2010年第10期1483-1486,共4页
Journal of Northeastern University(Natural Science)
基金
国家自然科学基金资助项目(50435040)
关键词
数学形态学
边缘检测
信息熵
融合
鲁棒性
mathematical morphology
edge detection
information entropy
integration
robustness
作者简介
黄海龙（1982－），男，辽宁锦州人，东北大学博士研究生；
Correspondent： WANG Hong, E-mail： hongwang @ mail. neu. edu. cn王宏（1960－），女，辽宁沈阳人，东北大学教授，博士生导师．
