[1]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,(04):41-46.[doi:10.13890/j.issn.1000-128x.2020.04.100]
　HUANG Mengying,LUO Jiangping,WANG Wenxing,et al.Research on Classification of Rail Defects Based on Image Processing Algorithm[J].Electric Drive for Locomotives,2020,(04):41-46.[doi:10.13890/j.issn.1000-128x.2020.04.100]
点击复制

基于图像处理的钢轨伤损分类算法研究()
分享到：

机车电传动[ISSN:1000-128X/CN:43-1125/U]

卷:
期数:
2020年04期
页码:
41-46
栏目:
试验检测技术
出版日期:
2020-07-10

文章信息/Info

Title:
Research on Classification of Rail Defects Based on Image Processing Algorithm
文章编号:
1000-128X(2020)04-0041-06
作者:
黄梦莹; 罗江平; 王文星; 曹经纬
（株洲时代电子技术有限公司，湖南 株洲 412007）
Author(s):
HUANG Mengying;  LUO Jiangping;  WANG Wenxing;  CAO Jingwei
( Zhuzhou Times Electronic Technology Co., Ltd., Zhuzhou, Hunan 412007, China )
关键词:
钢轨; Tamura纹理特征; LBP; 特征提取; SVM; 钢轨伤损分类
Keywords:
rail;  Tamura texture feature;  LBP;  feature extraction;  SVM;  rail defect classification
分类号:
U213.4+2
DOI:
10.13890/j.issn.1000-128x.2020.04.100
文献标志码:
A
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.

参考文献/References:

[1] 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.

[2] 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.
[3] 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.
[4] HOWARTH P, R?GER 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_40.
[5] OJALA T, PIETIK?INENM, HARWOOD D. A comparative study of texture measures with classificationbased on featured distributions[J]. Pattern Recog- nition, 1996, 29(1): 51-59.
[6] 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.
[7] 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.
[8] 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.
[9] BURGES J C C. A tutorial on support vector machines for pattern recognition[J]. Data Mining and Knowledge Discovery, 1998, 2(2):121-167.
[10] 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.

相似文献/References:

[1]龚继军,郭猛刚,侯 博,等.钢轨打磨技术发展现状及打磨策略探讨[J].机车电传动,2020,(03):23.[doi:10.13890/j.issn.1000-128x.2020.03.005]
　GONG Jijun,GUO Menggang,HOU Bo,et al.Discussion on Rail Grinding Technology Development Situation and Grind Strategies[J].Electric Drive for Locomotives,2020,(04):23.[doi:10.13890/j.issn.1000-128x.2020.03.005]
[2]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,(04):1.[doi:10.13890/j.issn.1000-128x.2020.04.100]
　HUANG Mengying,LUO Jiangping,WANG Wenxing,et al. Research on Classification of Rail Defects based on Image Processing Algorithm[J].Electric Drive for Locomotives,2020,(04):1.[doi:10.13890/j.issn.1000-128x.2020.04.100]
[3]陈经纬,崔 涛,孙建锋,等.基于高速列车异常晃动的钢轨廓形打磨管理[J].机车电传动,2020,(05):128.[doi:10.13890/j.issn.1000-128x.2020.05.104]
　CHEN Jingwei,CUI Tao,SUN Jianfeng,et al.Grinding Management of Rail Profile Based on AbnormalHunting of High-speed Train[J].Electric Drive for Locomotives,2020,(04):128.[doi:10.13890/j.issn.1000-128x.2020.05.104]

备注/Memo

备注/Memo:
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。
更新日期/Last Update: 2020-07-10