摘要
根据数学形态学和边缘检测算子以及木材腐朽图像的特征,选择多尺度多结构的形态学算法,首先对图像进行交替顺序多尺度结构元素的膨胀、腐蚀滤波;再用多结构元素对图像进行开闭运算达到去除噪声,保留图像细节的目的;最后利用Canny算子提取图像的边缘特征。实验结果表明该方法抗噪能力强,能有效提取图像的边缘特征。
According to the theory of mathematical morphology,edge detection operators and characteristics of rotten wood image,a multi-structure element with multi-scale edge detection algorithm based on mathematical morphology was proposed.In order to remove noise and preserve image details,the image was filtered by an alternative-order morphological corrosion-expansion filter with multi-scale element,and the edge information was obtained using multi-structure elements open-close operation.Canny operator was used to extract the edge of the rotten image.Experimental results show that the proposed algorithm is insensitive to noise and is efficient in edge detection.
出处
《森林工程》
2011年第2期28-30,87,共4页
Forest Engineering
基金
中央高校基本科研业务费专项资金项目
关键词
数学形态学
多尺度多结构元素
边缘检测
木材检测
mathematical morphology
multi-scale multi-structure element
edge detection
wood detection
