• Opto-Electronic Engineering
  • Vol. 41, Issue 2, 40 (2014)
ZHANG Huaixiang1、*, LIU Huaiguang2, YANG Maolin1, and WANG Xingdong2
Author Affiliations
  • 1[in Chinese]
  • 2[in Chinese]
  • show less
    DOI: 10.3969/j.issn.1003-501x.2014.02.007 Cite this Article
    ZHANG Huaixiang, LIU Huaiguang, YANG Maolin, WANG Xingdong. A Self-adaptive Segmentation Method of Wire Defects under Complex Illumination[J]. Opto-Electronic Engineering, 2014, 41(2): 40 Copy Citation Text show less

    Abstract

    For the technical difficulties of defect detection on high-speed wire surface, the segmentation technology of wire defects under complex illumination is researched. As the gradient histogram has multi-peak, a peak selection standard is described and then a piecewise self-adaptive fuzzy threshold method is provided based on the fuzzy threshold with double humps. Using this method, the wire can be segmented from the complex background. In order to extract the defect edges ahead, a contraposition traversal method is provided. The final test results shows that the methods provided can deal with the continuous gray problem caused by uneven illumination and extract the defect accurately, and thereby lay a foundation for the further study on the vision recognition of wire defects.
    ZHANG Huaixiang, LIU Huaiguang, YANG Maolin, WANG Xingdong. A Self-adaptive Segmentation Method of Wire Defects under Complex Illumination[J]. Opto-Electronic Engineering, 2014, 41(2): 40
    Download Citation