摘要
灰度共生矩阵(GrayLevel Co-occurrence Matrix,GLCM)在图像纹理提取上应用极其广泛,但依旧存在不足。文章在GLCM纹理提取算法的基础上,引入局部二值模式(Local Binary Patterns,LBP),以此来改变GLCM在不同方向上的不一致性,解决因选取GLCM方向的不同给研究带来的误差。经实验,该文章提出的GLCM-LBP纹理特征改进方法,有效解决了方向不同带来的问题,同时计算量大幅减少。
Gray-level co-occurrence matrix(GLCM)is widely used in image texture extraction,but it still has deficiencies.Based on the GLCM texture extraction algorithm,Local Binary Patterns(LBP)to change the inconsistency of GLCM in different directions and solve the errors caused by the different GLCM directions were introducedin this paper.Through experiments,the GLCM-LBP texture feature improvement method proposed in this paper effectively solves the problems caused by different directions,and the calculation amount is greatly reduced.
作者
江玉杰
王世航
JIANG Yu-jie;WANG Shi-hang(School of Geodesy and Geomatics,AnHui University of Science and Technology,Huainan 232001,China)
出处
《电脑知识与技术》
2020年第31期13-16,共4页
Computer Knowledge and Technology
基金
国家自然科学基金(31700369)。
关键词
灰度共生矩阵
局部二值模式
遥感
图像处理
纹理提取
gray-level co-occurrence matrix
local binary patterns
remote sensing
image processing
texture extraction
