[1]崔红霞,黄科涵.基于混合纹理的计算机自动分类方法[J].计算机技术与发展,2018,28(02):158-162.[doi:10．3969/j．issn．1673－629X．2018．02．034]
　CUI Hong-xia,HUANG Ke-han.Computer Automatic Classification Method Based on Mixed Texture[J].,2018,28(02):158-162.[doi:10．3969/j．issn．1673－629X．2018．02．034]
点击复制

基于混合纹理的计算机自动分类方法()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
28
期数:
2018年02期
页码:
158-162
栏目:
应用开发研究
出版日期:
2018-02-10

文章信息/Info

Title:
Computer Automatic Classification Method Based on Mixed Texture
文章编号:
1673－629X(2018)02－0158－05
作者:
崔红霞; 黄科涵
渤海大学 信息科学与技术学院，辽宁 锦州 121000
Author(s):
CUI Hong-xia; HUANG Ke-han
School of Information Science and Technology，Bohai University，Jinzhou 121000，China
关键词:
计算机分类; 纹理特征; 灰度共生矩阵; 聚类; 非监督分类
Keywords:
computer classification; texture feature; grey level co－occurrence matrix; clustering; unsupervised classification
分类号:
TP751
DOI:
10．3969/j．issn．1673－629X．2018．02．034
文献标志码:
A
摘要:
针对高分辨率光学图像光谱信息单一，纹理信息丰富的特点，设计了一种基于粗、细纹理两种特征相结合的计算机自动分类方法。通过提出一种基于 Tamura 的局部纹理特征和灰度共生矩阵的细小纹理特征混合的 7 维特征向量，实现图像基于 k－means 聚类的 7 维特征空间的计算机自动分类。针对耕地、森林、裸露地、水域四类典型地物，通过对 1 600 张样本影像(每类 400 张)的分类探测，自动确定 Tamura 特征和灰度共生矩阵特征移动窗口的最佳尺寸。模拟地物合成影像自动分类和低空高分辨率光学影像的典型地物自动分类的实验结果表明，该方法的自动分类精度优于单种纹理特征的分类精度，采用混合纹理对遥感图像进行地物分类是计算机自动分类的研究方向之一。
Abstract:
According to the characteristics of high resolution optical image with single spectral information and rich texture information，we design a computer automatic classification method based on the combination of two features of coarse and fine texture．By presenting a new 7 dimensional feature vector based on Tamura texture feature and gray level co－occurrence matrix，automatic classification of 7 dimensional feature space based on k－means clustering is achieved．According to four kinds of typical objects like the cultivated land，forest and bare
land，waters，through the image of 1600 samples (each 400) classification detection，the optimal size of Tamura features and gray level co-occurrence matrix features moving window is determined automatically．The experiments on automatic classification of simulation object synthetic image and that of typical objects for the low optical image with high resolution show that the classification accuracy of the proposed method is better than that of single texture features．Texture features using the mixture of remote sensing image classification is one of the re-
search directions of computer automatic classification．

相似文献/References:

[1]赵福君 李景文 陈大克 刘卉卉.数学形态学的纹理图像分割方法[J].计算机技术与发展,2008,(05):112.
　ZHAO Fu-jun,LI Jing-wen,CHEN Da-ke,et al.Image Segmentation Method about Mathematical Morphology Based on Textural Features[J].,2008,(02):112.
[2]焦蓬蓬 郭依正 刘丽娟 卫星.灰度共生矩阵纹理特征提取的Matlab实现[J].计算机技术与发展,2012,(11):169.
　JIAO Peng-peng,GUO Yi-zheng,LIU Li-juan,et al.Implementation of Gray Level Co-occurrence Matrix Texture Feature Extraction Using Matlab[J].,2012,(02):169.
[3]肖秦琨,刘米娜,高嵩.基于颜色和纹理特征的遥感图像检索[J].计算机技术与发展,2013,(04):107.
　XIAO Qin-kun,LIU Mi-na,GAO Song.Remote Sensing Image Retrieval Based on Color and Texture[J].,2013,(02):107.
[4]王职军[],梁光明[],刘任任[],等. 共生矩阵纹理特征的DSP优化实现[J].计算机技术与发展,2014,24(11):13.
　WANG Zhi-jun[],LIANG Guang-ming[],LIU Ren-ren[],et al. DSP Optimized Implementation of Co-occurrence Matrix Texture Feature[J].,2014,24(02):13.
[5]王树梅,张文斌. 小波变换在数字图像边缘探测中的应用[J].计算机技术与发展,2015,25(06):16.
　WANG Shu-mei,ZHANG Wen-bin. Application of Wavelet Transform in Edge Detection for Digital Image[J].,2015,25(02):16.
[6]黎粤华,单磊,田仲富,等. 基于多特征融合的视频烟雾检测[J].计算机技术与发展,2016,26(01):129.
　LI Yue-hua,SHAN Lei,TIAN Zhong-fu,et al. Video Smoke Detection Based on Multi Feature Fusion Technology[J].,2016,26(02):129.
[7]刘少林,朱文球,孙文静,等.基于联合直方图的自适应粒子滤波跟踪算法[J].计算机技术与发展,2018,28(06):106.[doi:10.3969/ j. issn.1673-629X.2018.06.024]
　LIU Shao-lin,ZHU Wen-qiu,SUN Wen-jing,et al.An Adaptive Particle Filtering and Tracking Algorithm Based on Joint Histogram[J].,2018,28(02):106.[doi:10.3969/ j. issn.1673-629X.2018.06.024]
[8]闫文耀,郭铭涛,王志晓,等.面向汉字书写质量评价的 Gabor 特征提取方法[J].计算机技术与发展,2020,30(10):92.[doi:10. 3969 / j. issn. 1673-629X. 2020. 10. 017]
　YAN Wen-yao,GUO Ming-tao,WANG Zhi-xiao,et al.Gabor-based Feature Extraction towards Chinese Character Writing Quality Evaluation[J].,2020,30(02):92.[doi:10. 3969 / j. issn. 1673-629X. 2020. 10. 017]
[9]韩昕昊,孙进保,李 威.基于 Gabor 的多尺度纹理特征融合的黑烟识别[J].计算机技术与发展,2022,32(S2):41.[doi:10. 3969 / j. issn. 1673-629X. 2022. S2. 007]
　HAN Xin-hao,SUN Jin-bao,LI Wei.Black Smoke Recognition Based on Gabor Multi-scale Texture Feature Fusion[J].,2022,32(02):41.[doi:10. 3969 / j. issn. 1673-629X. 2022. S2. 007]

更新日期/Last Update: 2018-03-29