摘要
通过对赞比亚产三种木材花纹的采集与分类,基于MATLAB软件,以自相关函数的粗糙度为导向,结合灰度共生矩阵特征参数估计,建立木材花纹图像学模型。结果表明:灰度共生矩阵特征信息分析从对纹理构成的角度上定量地代表了对应的纹理特征,木材花纹间的对比度差异比较明显,同质性(0.70~0.80)上差异较小。基于木材基本构造特征辅助计算机参数,实现对木材不同特征纹理的识别和对木材花纹的分类运用,具有一定可行性与准确性。
Through the acquisition and classification of three wood patterns produced in Zambia,based on MATLAB,guided by the roughness of the auto correlation function and estimated through combination with the feature parameters of the gray-level co-occurrence matrix,a wood pattern image model was established.The results show that the feature information analysis of gray-level co-occurrence matrix quantitatively represents the corresponding texture characteristics from the perspective of texture composition,with obvious contrast difference between wood patterns and small difference in homogeneity(0.70-0.80).Based on the basic structural characteristics of wood,accompanied by computer aided parameters,it is feasible and accurate to realize the identification of different characteristic textures of wood and the classification and application of wood patterns.
作者
蒋彤(Banda Charity)
田朔
黄璇
余辉龙
李文珠
JIANG Tong(Banda Charity);TIAN Shuo;HUANG Xuan;YU Hui-long;LI Wen-zhu(School of Chemistry and Materials Engineering,Zhejiang A&F University,Hangzhou Zhejiang 311300,China;Dongyang Forest Resources Comprehensive Service Center,Dongyang Zhejiang 322100,China;Furniture Product Quality Supervision and Inspection Center of Jiangxi Province,Ganzhou Jiangxi 341400,China)
出处
《林业机械与木工设备》
2022年第8期89-96,共8页
Forestry Machinery & Woodworking Equipment
基金
浙江省科技厅浙江省基础公益研发计划项目(编号:LGC20C160001)。
关键词
木材花纹
MATLAB
图像处理
自相关函数
灰度共生矩阵
wood pattern
MATLAB
image Processing
auto correlation function
gray-level co-occurrence matrix
