基于灰度-梯度共生矩阵的木材表面缺陷分割方法  

Segmentation Method of Timber Surface Defects Based on Gray Level-Gradient Co-occurrence Matrix

作　　者：白雪冰[1] 邹丽晖[1] 

机构地区：[1]东北林业大学,哈尔滨150040

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)

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.

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 

分 类 号：S781.5[农业科学—木材科学与技术]