摘要
根据木材表面缺陷图像的特点,提出了基于灰度-梯度共生矩阵模型和最大熵原理的木材缺陷图像自动阀值化技术。并且利用形态学运算对分割后的二值图像进行后期处理。经实验验证,该方法提取的木材表面缺陷图像效果良好。
According to the characteristics of the timber surface defect, we present an automatic technique for thresholding of timber surface defect images based on gray level-gradient co-occurrence matrix and the maximum entropy principle. Post-treatment to the segmented binary images by morphology operation was also implemented. The algorithm was tested on some timber surface defect images. The results are satisfied.
出处
《森林工程》
2007年第2期16-18,共3页
Forest Engineering
基金
哈尔滨市自然科学基金项目(2004ADX X J O 20)
黑龙江省自然科学基金项目(C2004-03)
关键词
木材表面缺陷
图像分割
灰度-梯度共生矩阵
最大熵
形态学
timber surface defect
image segmentation
gray level-gradient co-occurrence matrix
maximum entropy
mor-phology
