基于多重分形谱的木材高光谱图像纹理分类算法

唐艳慧; 赵鹏; 王承琨

doi:10.3788/YJYXS20193412.1182

您当前的位置：

首页 >

文章列表页 >

基于多重分形谱的木材高光谱图像纹理分类算法

图像处理 | 更新时间：2020-07-16

- 基于多重分形谱的木材高光谱图像纹理分类算法
- Texture classification algorithm of wood hyper-spectral image based on multi-fractal spectra
- 液晶与显示 2019年34卷第12期页码：1182-1190
- 作者机构：
  
  东北林业大学信息与计算机工程学院, 黑龙江哈尔滨 150040
- 作者简介：
  
  [ "唐艳慧(1994—), 女, 黑龙江省佳木斯人, 硕士研究生, 2017年于东北林业大学获得学士学位, 主要从事图像处理、模式识别研究方向。E-mall:1421412131@qq.com" ]
  [ "赵鹏(1972—), 男, 黑龙江阿城人, 博士, 教授, 2006年于哈尔滨工业大学获得博士学位, 研究方向是林业信息工程和农业信息化的学科交叉研究。E-mail:impanefu@aliyun.com" ]
- 基金信息：
  
  国家自然科学基金面上项目资助(31670717)
- DOI：10.3788/YJYXS20193412.1182
  中图分类号： TP391
- 收稿日期：2019-08-28，
  
  录用日期：2019-9-19，
  
  纸质出版日期：2019-12-05
- 稿件说明：
移动端阅览
唐艳慧, 赵鹏, 王承琨. 基于多重分形谱的木材高光谱图像纹理分类算法[J]. 液晶与显示, 2019,34(12):1182-1190.

Yan-hui TANG, Peng ZHAO, Cheng-kun WANG. Texture classification algorithm of wood hyper-spectral image based on multi-fractal spectra[J]. Chinese journal of liquid crystals and displays, 2019, 34(12): 1182-1190.
唐艳慧, 赵鹏, 王承琨. 基于多重分形谱的木材高光谱图像纹理分类算法[J]. 液晶与显示, 2019,34(12):1182-1190. DOI： 10.3788/YJYXS20193412.1182.

Yan-hui TANG, Peng ZHAO, Cheng-kun WANG. Texture classification algorithm of wood hyper-spectral image based on multi-fractal spectra[J]. Chinese journal of liquid crystals and displays, 2019, 34(12): 1182-1190. DOI： 10.3788/YJYXS20193412.1182.

摘要

为了过滤木材高光谱图像中大量的冗余信息，提升应用图像纹理进行分类的准确率，本文采用基于多重分形理论的木材高光谱图像分类算法。首先利用不同的特征选择算法选取最具代表性的10个波段；随后根据不同的函数密度图像对所选取波段的图像求解其多重分形曲线，将选择出的多个波段所对应的多重分形曲线取平均，得到表示样本纹理特征的多重分形曲线；最后使用支持向量机和BP神经网络分类器对多重分形曲线进行分类。实验表明，相对熵（K-L散度）要好于自适应波段选择（ABS）提取的波段，多重分形算法提取的高光谱图像纹理特征要好于灰度共生矩阵，支持向量机算法的分类准确率和速度要优于BP神经网络，融合K-L散度、多重分形和支持向量机算法能够有效地提高木材高光谱图像的识别准确率，最高识别准确率达到了97.91%。

Abstract

In order to increase the accuracy classified by image texture to remove plenty of useless information in wood hyper-spectral images

the texture classification algorithms based on the multifractal theory were used in this paper. Firstly

the most representative ten bands were screened out using different Feature selection algorithms

and then the multi-fractal curves of the selected bands were obtained according to different function density images. The multi-fractal curves were averaged

which could represent the texture feature of certain sample. Finally

the curves were classified by the Support Vector Machine (SVM) and BP neural network classifier. The result shows that the bands screened by K-L divergence are superior to that screened by adaptive band selection (ABS)

the image's texture features extracted by multi-fractal algorithm are better than that extracted by the gray level co-occurrence matrix(GLCM)

and the classification accuracy and classification speed of SVM have an advantage over that used BP neural network. It can be concluded that the integrating K-L divergence

multi-fractal with SVM algorithm can dramatically increase the recognition classification

which can reach 97.91% in our work.

关键词

Keywords

references

YADAV A R, ANAND R S, DEWAL M L, et al . Multiresolution local binary pattern variants based texture feature extraction techniques for efficient classification of microscopic images of hardwood species[J]. Applied Soft Computing , 2015, 32:101-112.

YADAV A R, ANAND R S, DEWAL M L, et al . Gaussian image pyramid based texture features for classification of microscopic images of hardwood species[J]. Optik , 2015, 126(24):5570-5578.

BARMPOUTIS P, DIMITROPOULOS K, BARBOUTIS I, et al . Wood species recognition through multidimensional texture analysis[J]. Computers and Electronics in Agriculture , 2018, 144:241-248.

刘春红, 赵春晖, 张凌雁.一种新的高光谱遥感图像降维方法[J].中国图象图形学报, 2005, 10(2):218-222.

LIU C H, ZHAO C H, ZHANG L Y. A new method of hyperspectral remote sensing image dimensional reduction[J]. Journal of Image and Graphics , 2005, 10(2):218-222. (in Chinese)

徐进永, 张子达, 陆爽.基于K-L变换和支持向量机的滚动轴承故障模式的识别[J].吉林大学学报:工学版, 2005, 35(5):500-504.

XU J Y, ZHANG Z D, LU S. Fault pattern recognition of rolling bearing based on K-L transform and support vector machine[J]. Journal of Jilin University:Engineering and Technology Edition , 2005, 35(5):500-504. (in Chinese)

权龙哲, 祝荣欣, 雷溥, 等.基于K-L变换与LS-SVM的玉米品种识别方法[J].农业机械学报, 2010, 41(4):168-172.

QUAN L Z, ZHU R X, LEI P, et al . Recognition method of maize cultivars based on K-L transform and LS-SVM[J]. Transactions of the Chinese Society for Agricultural Machinery , 2010, 41(4):168-172. (in Chinese)

赵慧洁, 李明康, 李娜, 等.一种基于改进子空间划分的波段选择方法[J].红外与激光工程, 2015, 44(10):3155-3160.

ZHAO H J, LI M K, LI N, et al . A band selection method based on improved subspace partition[J]. Infrared and Laser Engineering , 2015, 44(10):3155-3160. (in Chinese)

刘雪松, 葛亮, 王斌, 等.基于最大信息量的高光谱遥感图像无监督波段选择方法[J].红外与毫米波学报, 2012, 31(2):166-170, 176.

LIU X S, GE L, WANG B, et al . An unsupervised band selection algorithm for hyperspectral imagery based on maximal information[J]. Journal of Infrared and Millimeter Waves , 2012, 31(2):166-170, 176. (in Chinese)

FOWLER A D. The fractal geometry of nature[J]. Computers & Geosciences , 1991, 17(7):1065-1066.

杨冬风, 马秀莲.基于分形纹理分析的蛋壳裂纹识别[J].吉林大学学报:工学版, 2011, 41(S1):348-352.

YANG D F, MA X L. Identification of egg shell crack based on fractal texture analysis[J]. Journal of Jilin University (Engineering and Technology Edition) , 2011, 41(S1):348-352. (in Chinese)

孙翘楚, 肖创柏, 郭犇, 等.食用油红外光谱的分形维数特征[J].哈尔滨工业大学学报, 2010, 42(11):1814-1817.

SUN Q C, XIAO C B, GUO B, et al . Fractal geometry feature of edible oil FTIR[J]. Journal of Harbin Institute of Technology , 2010, 42(11):1814-1817. (in Chinese)

王晓乔, 王访, 廖桂平, 等.油菜光谱的多重分形分析及叶绿素诊断建模[J].光谱学与光谱分析, 2016, 36(11):3657-3663.

WANG X Q, WANG F, LIAO G P, et al . Multifractal analysis of rapeseed spectrum for chlorophyll diagnosis modeling[J]. Spectroscopy and Spectral Analysis , 2016, 36(11):3657-3663. (in Chinese)

张艳诚, 毛罕平, 胡波, 等.数字图像中作物病斑形状分形特征提取[J].微计算机信息, 2007, 23(33):295-297.

ZHANG Y C, MAO H P, HU B, et al . Extracting fractal feature of spot morphology of plant diseases in digital image[J]. Microcomputer Information , 2007, 23(33):295-297. (in Chinese)

XU Y, JI H, FERMVLLER C. Viewpoint invariant texture description using fractal analysis[J]. International Journal of Computer Vision , 2009, 83(1):85-100.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

暂无数据