A Robust Approach for Line Scale Image Extracting
CSTR:
Author:
Affiliation:

Clc Number:

Fund Project:

  • Article
  • |
  • Figures
  • |
  • Metrics
  • |
  • Reference
  • |
  • Related
  • |
  • Cited by
  • |
  • Materials
  • |
  • Comments
    Abstract:

    In order to solve the problem of inaccurate detection and recognition of steel tape image caused by uneven illumination, rust spots, stains and other factors, a method of steel scribed line extraction based on Gabor transform is proposed. Through Gabor transformation, the line structure of characteristic direction and specific frequency is filtered and presented. Based on these line structures, the position of the line to be tested in the image is calculated, and then the double edges of the line are fitted by RANSAC algorithm, so as to accurately obtain the center position of the line. Experiments show that the algorithm can recognize the damaged and rusty scribed lines robustly when the quality of scribed lines is poor, and improve the detection accuracy and the robustness of the whole measurement system effectively, which has technical reference value.

    Reference
    Related
    Cited by
Get Citation
Related Videos

Share
Article Metrics
  • Abstract:
  • PDF:
  • HTML:
  • Cited by:
History
  • Received:
  • Revised:
  • Adopted:
  • Online: March 27,2020
  • Published:
Article QR Code