基于图像处理的钢轨伤损分类算法研究

黄梦莹; 罗江平; 王文星; 曹经纬

doi:10.13890/j.issn.1000-128x.2020.04.100

您当前的位置：

首页 >

文章列表页 >

基于图像处理的钢轨伤损分类算法研究

试验检测技术 | 更新时间：2021-12-10

- 基于图像处理的钢轨伤损分类算法研究
- Research on Classification of Rail Defects Based on Image Processing Algorithm
- 机车电传动 2020年第4期页码：41-46,53
- 作者机构：
  
  1.株洲时代电子技术有限公司，湖南　株洲　412007
- 作者简介：
  
  黄梦莹（1992—），女，硕士，从事钢轨探伤车探伤检测系统识别算法的研究工作。
- 基金信息：
- DOI：10.13890/j.issn.1000-128x.2020.04.100
  中图分类号：
扫描看全文
黄梦莹, 罗江平, 王文星, 等. 基于图像处理的钢轨伤损分类算法研究[J]. 机车电传动, 2020,(4):41-46,53.

Mengying HUANG, Jiangping LUO, Wenxing WANG, et al. Research on Classification of Rail Defects Based on Image Processing Algorithm[J]. Electric Drive for Locomotives, 2020,(4):41-46,53.
黄梦莹, 罗江平, 王文星, 等. 基于图像处理的钢轨伤损分类算法研究[J]. 机车电传动, 2020,(4):41-46,53. DOI： 10.13890/j.issn.1000-128x.2020.04.100.

Mengying HUANG, Jiangping LUO, Wenxing WANG, et al. Research on Classification of Rail Defects Based on Image Processing Algorithm[J]. Electric Drive for Locomotives, 2020,(4):41-46,53. DOI： 10.13890/j.issn.1000-128x.2020.04.100.

摘要

钢轨伤损的种类众多且形态各异，即便对于同类伤损，在超声波钢轨探伤检测软件中形成的B显图像也会存在差异，而当某类伤损的B显图像变化超出一定范围后，检测软件便无法识别该伤损的类别。因此，提出一种基于图像处理的钢轨伤损分类算法，其采用Tamura纹理特征与局部二值模式(local binary pattern, LBP)相结合的算法提取伤损B显图像的特征值并组成特征向量，使得作为分类器的支持向量机(support vector machine，SVM)能够对不同种类伤损的特征向量进行训练，从而用训练后的最优分类函数预测未训练过的待测伤损的类别。试验结果表明，所提算法在钢轨伤损图像分类方面实现了较高的分类准确率。

Abstract

There are many types and different shapes of rail defects. Even for the same type of defect, there are differences in the B-Scan images of the ultrasonic rail defect detection software. When the B-Scan image of a certain type of defect changes over a certain range, the detection software cannot identify this type of defect. Therefore, a classification for rail defects based on image processing algorithm was proposed. Firstly, the Tamura texture feature algorithm was combined with the local binary pattern algorithm to extract the feature values of the defect images, and form feature vectors. Secondly, the feature vectors of different kinds of defects were trained by support vector machine, and the optimal classification function was obtained. Finally, the category of untrained defects could be predicted by the optimal classification function. The experimental results showed that the proposed algorithm achieved high accuracy in the classification of rail defect images.

关键词

钢轨Tamura纹理特征LBP特征提取SVM钢轨伤损分类

Keywords

railTamura texture featureLBPfeature extractionSVMrail defect classification

references

株洲中车时代电气股份有限公司轨道工程机械事业部. 钢轨探伤车检测系统培训教材[Z]. 株洲: 株洲中车时代电气股份有限公司, 2017.

王雪梅. 无损检测技术及其在轨道交通中的应用[M]. 成都: 西南交通大学出版社, 2010.

TAMURA H, MORI S, YAMAWAKI T. Textural features corresponding to visual perception[J]. IEEE Transactions on Systems, Man, and Cybernetics, 1978, 8(6): 460-473.

HOWARTH P, RÜGER S. Evaluation of texture features for content-based image retrieval[J]. Lecture Notes in Computer Science, 2004, 3115: 326-334. DOI: 10.1007/978-3-540-27814-6_40http://doi.org/10.1007/978-3-540-27814-6_40.

OJALA T, PIETIKÄINENM , HARWOOD D. A comparative study of texture measures with classification based on featured distributions[J]. Pattern Recog- nition, 1996, 29(1): 51-59.

ZHU C R, WANG R S. Local multiple patterns based multiresolution gray-scale and rotation invariant texture classification[J]. Information Sciences, 2012, 187(1): 93-108.

万源, 李欢欢, 吴克风, 等. LBP和HOG的分层特征融合的人脸识别[J]. 计算机辅助设计与图形学学报, 2015, 27(4): 640-650.

LIU L, FIEGUTH P, GUO Y L, et al. Local binary features for texture classification: Taxonomy and experimental study[J]. Pattern Recognition, 2017, 62: 135-160.

BURGES J C C. A tutorial on support vector machines for pattern recognition[J]. Data Mining and Knowledge Discovery, 1998, 2(2): 121-167.

LUTS J, OJEDA F, DE PLAS R V, et al. A tutorial on support vector machine-based methods for classification problems in chemometrics[J]. Analytica Chimica Acta, 2010, 665(2): 129-145.

浏览量

下载量

CSCD

CNKI被引量

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于ICEEMDAN-MPE-RF和SVM的齿轮箱特征提取与故障诊断

基于轻量级卷积神经网络的地铁轨道线路状态检测系统

牵引电机定子绝缘局部放电试验和可靠性评估

多柔性因素下轮轨接触动态行为特性的研究

竖直牵引式打磨装置力学特性分析计算