Morphological Image Analysis for Automated Surface Quality Inspection of Moving Steel Plates
Automated surface inspection of steel plates plays important part in quality control of steel production. purpose of the inspection is to detect and classify surface defects. The work presented herein describes the algorithms and implementation of morphological image analysis based surface inspection of hot rolled steel plates. We consider the surface quality inspection problem of image segmentation, shape description and defect classification. A number of shape descriptors are investigated and a set of measures are defined to characterize the defects. An automated solution for the defect detection and categorization is proposed. The proposed solution is assessed with samples from a hot rolling plant, and experimental results show that the defects can be detected and classified with high performance.
Dadong Wang Ke Xu Jinwu Xu
CSIRO Mathematics, Informatics and Statistics, Locked Bag 17, North Ryde,Sydney, NSW 1670, Australia National Engineering Research Centre of Advanced Rolling,University of Science and Technology Beijin National Engineering Research Centre of Advanced Rolling, University of Science and Technology Beiji
国际会议
The 31st International Congress on Imaging Science(第31届国际影像科学大会 ICIS2010)
北京
英文
42-45
2010-05-12（万方平台首次上网日期，不代表论文的发表时间）