基于Otsu方法的钢轨图像分割

袁小翠; 吴禄慎; 陈华伟

doi:10.3788/OPE.20162407.1772

您当前的位置：

首页 >

文章列表页 >

基于Otsu方法的钢轨图像分割

信息科学 | 更新时间：2020-08-13

- 基于Otsu方法的钢轨图像分割
- Rail image segmentation based on Otsu threshold method
- 光学精密工程 2016年24卷第7期页码：1772-1781
- 作者机构：
  
  1.南昌工程学院江西省精密驱动与控制重点实验室, 江西南昌 330099
  2.南昌大学机电工程学院, 江西南昌 330031
- 作者简介：
  
  [ "袁小翠(1988-),女,江西抚州人,博士,主要研究方向为图像处理与逆向工程。E-mail:yuanxc2012@163.com" ]
  吴禄慎(1953-),男,江西乐平人,硕士,教授,博士生导师,1978年于北京航空航天大学获得学士学位,1990年于清华大学获得硕士学位,主要从事面外"moire"法、三维光学图像测量与逆向工程的研究。E-mail:wulushen@163.com E-mail:wulushen@163.com
- 基金信息：
  
  国家自然科学基金资助项目(51365037);国家自然科学基金资助项目(51065021)
- DOI：10.3788/OPE.20162407.1772
  中图分类号： TP391.4;U213.43
- 收稿日期：2015-08-18，
  
  录用日期：2015-11-12，
  
  纸质出版日期：2016-07
- 稿件说明：
移动端阅览
袁小翠, 吴禄慎, 陈华伟. 基于Otsu方法的钢轨图像分割[J]. 光学精密工程, 2016,24(7):1772-1781.

Xiao-cui YUAN, Lu-shen WU, Hua-wei CHEN. Rail image segmentation based on Otsu threshold method[J]. Optics and precision engineering, 2016, 24(7): 1772-1781.
袁小翠, 吴禄慎, 陈华伟. 基于Otsu方法的钢轨图像分割[J]. 光学精密工程, 2016,24(7):1772-1781. DOI： 10.3788/OPE.20162407.1772.

Xiao-cui YUAN, Lu-shen WU, Hua-wei CHEN. Rail image segmentation based on Otsu threshold method[J]. Optics and precision engineering, 2016, 24(7): 1772-1781. DOI： 10.3788/OPE.20162407.1772.

摘要

由于钢轨图像灰度分布不均，一般的图像分割法难以将目标从背景中分割出来，故本文提出了目标方差加权的类间方差阈值分割法对钢轨图像进行阈值分割。分析了钢轨图像的特点，总结了加权的目标方差(Otsu)方法及其它全局阈值分割法对钢轨图像分割存在的问题。然后，对Otsu方法进行改进，以目标出现的概率为权重，对类间方差的目标方差加权，使分割阈值靠近单模直方图的左边缘和双模直方图的谷底。最后，计算图像的错误分类误差、钢轨图像的缺陷检测率和误检率来验证算法的有效性。实验结果表明，改进的Otsu方法能有效地分割钢轨图像，错误分类误差接近0。与其它阈值分割法如Otsu法、其它改进的Otsu法、最大熵阈值分割法相比，本文方法对钢轨图像的分割效果更优，缺陷检测率和误检率分别为93%和6.4%，适合机器视觉缺陷检测的实时应用。

Abstract

As rail images show uneven gray distribution

general image segmenting methods can not accurately segment rail images. To address this issue

this paper presents an improved Otsu method using weighted object variance (WOV) for rail image segmentation to separate the defect from its background. Firstly

the property of a rail image was analyzed and the problems of the Otsu method and other global threshold methods for segmenting rail images were summarized. Then

the Otsu method was improved. By taking the cumulative probability of defect occurrence for the weighting

the object variance of between-class variance was weighted

and the threshold will always be a value that locates at two peaks or at the left bottom rim of a single peak histogram. Finally

the misclassification error (MCE)

the detection rate and false alarm rate of the defect image were calculated to validate the effectiveness of proposed method. The experimental results demonstrate that the improved Otsu method accurately segments various kinds of rail images and the MCE value is close to 0. As comparing to the Otsu method

other improved Otsu method and maximum entropy threshold method

the proposed method provides better segmentation results

the detection rate and false alarm rate for the rail defected image are 93% and 6.4% respectively. It is suitable for the applications in machine vision defect detection in real time.

关键词

Keywords

references

MOUSTAKIDIS S, KAPPATOS V, KARLSSON P, et al.. An Intelligent methodology for railways monitoring using ultrasonic guided waves[J]. Journal of Nondestructive Evaluation, 2014, 33(4):694-710.

SONG Z, YAMADA T, SHITARA H, et al.. Detection of damage and crack in railhead by using eddy current testing[J]. Journal of Electromagnetic Analysis and Applications, 2011, 3:546-550.

LI Q, REN S. A real-time visual inspection system for discrete surface defects of rail heads[J]. IEEE Transactions on Instrumentation and Measurement, 2012, 61(8):2189-2199.

BEAUCHEMIN M. Image thresholding based on semivariance[J]. Pattern Recognition Letters, 2013, 34(5):456-462.

SEZGIN M. Survey over image thresholding techniques and quantitative performance evaluation[J]. Journal of Electronic Imaging, 2004, 13(1):146-168.

OTSU N. A threshold selection method from gray-level histograms[J]. IEEE Transactions on Systrems, Man, and Cybernetics, 1979, 9:62-66.

KAPUR J, SAHOO P K, WONG A. A new method for gray-level picture thresholding using the entropy of the histogram[J]. Computer Vision, Graphics, and Image Processing, 1985, 29(3):273-285.

NACEREDDINE N, HAMAMI L, TRIDIM. Non-parametric histogram-based thresholding methods for weld defect detection in radiography[J]. Proceedings of World Academy of Science, Engineering and Technology, 2005, 9:213-217.

KITTLER J, ILLINGWORTH J. Minimum error thresholding[J]. Pattern Recognition, 1986, 19(1):41-47.

TSAI W H. Moment-preserving thresolding:A new approach[J]. Computer Vision, Graphics, and Image Processing, 1985, 29(3):377-393.

HU Q, HOU Z, NOWINSKI W L. Supervised range constrained thresholding[J]. IEEE Transactions on Image Processing, 2006, 15(1):228-240.

NG H F. Automatic thresholding for defect detection[J]. Pattern Recognition Letters, 2006, 27(14):1644-1649.

FAN J L, LEI B. A modified valley-emphasis method for automatic thresholding[J]. Pattern Recognition Letters, 2012, 33(6):703-708.

景晓军, 李剑峰, 刘郁林. 一种基于三维最大类间方差的图像分割算法[J]. 电子学报, 2003, 31(9):1281-1285.

JING X J, LI J F, LIU Y L. Image segmentation based on 3-D maximum between-cluster variance[J]. Acta Electronica Sinica, 2003, 31(9):1281-1285.(in Chinese)

申铉京, 龙建武, 陈海鹏, 等. 三维直方图重建和降维的Otsu阈值分割算法[J]. 电子学报, 2011, 39(5):1108-1114.

SHEN Y J, LONG J W, CHEN H P, et al.. Otsu thresholding algorithm based on rebuilding and dimension reduction of the 3-dimensional histogram[J]. Acta Electronica Sinica, 2011, 39(5):1108-1114.(in Chinese)

XU X, XU S, JIN L, et al.. Characteristic analysis of Otsu threshold and its applications[J]. Pattern Recognition Letters, 2011, 32(7):956-961.

YASNOFF W A, MUI J K, BACUS J W. Error measures for scene segmentation[J]. Pattern Recognition, 1977, 9(4):217-231.

NGAN H Y T, PANG G KH, YUNG N H C. Automated fabric defect detection-a review[J]. Image and Vision Computing, 2011, 29(7):442-458.

浏览量

504

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

电力巡检中的偏振图像特征融合

基于机器视觉的透明软管内微量液体体积测量

融合条形注意力机制的电芯极片计算机断层图像分割

基于圆卷积神经网络的粘连导电粒子检测

融合多尺度特征的蜗杆表面缺陷检测