Engraved Character Recognition of Train Wheelset Based on the Total Least Square Method

  • Shuang Zhang
  • Hua WangEmail author
  • Jin-gang Gao
  • Chun-qi Xing
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 503)


According to the characteristics of depth information of the engraved characters and the lack of color difference to the background, a line structured light sensor was applied to acquire train wheelset engraved character point cloud information. The total least square method was proposed for a 3D character point cloud processing method, in which the observation vector error and the coefficient matrix error are taken into account. According to the standard deviation of the point cloud data, abnormal points and engraved character points can be eliminated for plane fitting. A high-quality outline of the character information can be extracted from the character point cloud depth data.


Engraved character recognition Total least square method Train wheelset Line structured light 



This work was supported by the Jilin province science and technology development-funding project. The title of the research project is Online Inspection Key Technology Research for the Train Wheelset Manufacture Quality, and the project serial number is: 20160204005GX.


  1. 1.
    Berchmans D,Kumar SS (2014) Optical character recognition:an overview and an insight. In: International Conference on Control,Instrumentation,Communication and Computational Technologies (ICCICCT)Google Scholar
  2. 2.
    kaur Amritpal, Arora Madhavi (2013) Neural network based Numerical digits recognization using NNT in Matlab. Int J Comput Sci Eng Surv 4(5):47–59CrossRefGoogle Scholar
  3. 3.
    Matei O, Pop PC, Vǎlean H et al (2013) Optical character recognition in real environments using neural networks and k-nearest neighbor. Appl Intell Int J Artif Intell Neural Netw Comp Prob-Solv Technol 39(4):739–748Google Scholar
  4. 4.
    Vikramdeep Singh R, Randhawa N (2014) Automobile number plate recognition and extraction using optical character recognition. Int J Sci Technol Res 3(10):37–39Google Scholar
  5. 5.
    Lu J, Ye, Z, Zou Y et al (2013) Huber fractal image coding based on a fitting plane. IEEE Trans Image Process 22(1):134–145Google Scholar
  6. 6.
    Men Y, Zhang G, Men C, Li Xiang, Ning MA (2015) A Stereo matching algorithm based on four-moded census and relative confidence plane fitting. Chin J Electron 04:807–812CrossRefGoogle Scholar
  7. 7.
    Zlokazov VB, Morozov VA (2014) Robust fitting for the estimation of hidden parameters in experimental distributions on the plane. Phys Part Nucl Lett 11(4):483–485CrossRefGoogle Scholar
  8. 8.
    Hulik R, Spanel M, Smrz P et al (2014) Continuous plane detection in point-cloud data based on 3D Hough transform. J Vis Commun Image Represent 25(1):86–97CrossRefGoogle Scholar
  9. 9.
    Li X, Li W, Jiang H et al (2013) Automatic evaluation of machining allowance of precision castings based on plane features from 3D point cloud. Comput Ind 64(9):1129–1137CrossRefGoogle Scholar
  10. 10.
    Xiao J, Zhang J, Adler B et al (2013) Three-dimensional point cloud plane segmentation in both structured and unstructured environments. Robot Auton Syst 61(12):1641–1652CrossRefGoogle Scholar
  11. 11.
    Aydar U, Altan MO (2015) Total least squares registration of 3D surfaces. Int J Environ Geoinf 2(2):27–38CrossRefGoogle Scholar
  12. 12.
    Petrášl Ivo, Bednárová D (2010) Total least squares approach to modeling: a matlab toolbox. Acta Montan Slovaca Ročník 15(2):158–170Google Scholar
  13. 13.
    Muñoz LR, Villanueva MG, Suárez CG (2014) A tutorial on the total least squares method for fitting a straight line and a plane. In: International congress on mechanical and electric engineering, 1 al 4 de Diciembre del 2014. Coatzacoalcos, Veracruz, MexicoGoogle Scholar
  14. 14.
    Markovsky I, Sima DM, Van Huffel S (2009) Total least squares methods, Wiley Inc. WIREs Comp Stat 2010, 2:212–217Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  • Shuang Zhang
    • 1
    • 2
  • Hua Wang
    • 1
    Email author
  • Jin-gang Gao
    • 1
  • Chun-qi Xing
    • 3
  1. 1.School of Mechatronic EngineeringChangchun Institute of TechnologyChangchunChina
  2. 2.School of Mechanical Science and EngineeringJilin UniversityChangchunChina
  3. 3.School of Mechatronic EngineeringChangchun University of TechnologyChangchunChina

Personalised recommendations