基于灰度共生矩阵的木材表面缺陷图像的纹理分割方法  

Approach to Texture Segmentation of Wood Surface Defects Based on Gray Level Co-occurrence Matrix

作　　者：白雪冰 王科俊 邹丽晖[2] 

机构地区：[1]哈尔滨工程大学,哈尔滨150001 [2]北京理工大学

出　　处：《东北林业大学学报》2008年第12期23-25,27,共4页Journal of Northeast Forestry University

基　　金：黑龙江省博士后基金项目(LBH-Z06032)

摘　　要：针对木材缺陷这一自然纹理型事物,提出了一种基于灰度共生矩阵并结合模糊C均值聚类算法的纹理分割方法。对比了该方法与基于灰度-梯度共生矩阵二维阈值分割算法的分割结果,实验表明:对于木材表面缺陷这类自然纹理图像的分割,纹理分割是行之有效的方法。For the natural texture wood defect, a texture segmentation method based on gray level co-occurrence matrix and combined with Fuzzy C-Means cluster algorithm is presented. And compared with the segmentation method of two-dimensional threshold algorithm based on gray level-gradient co-occurrence matrix, the experiment shows that the texture segmentation is an effective way to segment the natural texture images of wood surface defects.

关 键 词：木材表面缺陷 纹理分割 灰度共生矩阵 模糊C均值聚类 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] S781.1[自动化与计算机技术—计算机科学与技术]