A local annular contrast based real-time inspection algorithm for steel bar surface defects

• Published in: Applied surface science 2012-06, Vol.258 (16), p.6080-6086
• Main Authors: Li, Wu-bin, Lu, Chang-hou, Zhang, Jian-chuan
• Format: Article
• Language: English
• Subjects: Condensed matter: electronic structure, electrical, magnetic, and optical properties; Condensed matter: structure, mechanical and thermal properties; Cross-disciplinary physics: materials science; rheology; Exact sciences and technology; Image processing; Local annular contrast; Physics; Surface defect detection; Vision inspection
• ISSN: 0169-4332; 1873-5584
• DOI: 10.1016/j.apsusc.2012.03.007

► A local annular contrast based real-time inspection algorithm for steel bar surface defects. ► A gray-level comparison between the detection point and its surrounding pixels at a certain distance. ► The threshold changes with the gray-level variation of local annular background. ► The algorithm has high detection success rate and need little time. A new inspection algorithm based on local annular contrast (LAC) for steel bar surface defects is presented. Because of little fluctuation of gray value inside the defects, traditional gradient detection methods could not find the defects accurately and often mistake the boundary of the bright region in center for defects. The LAC-based algorithm doesn’t have this disadvantage. Defects in images can be found due to their large contrast with local annular background (LAB). After average filter to steel bar surface image, the noise could be smoothed to a great extent but the contrast between defects and LAB changes very little. Then the LAC-based algorithm is applied to inspect defects. Experimental results show that the proposed algorithm needs only 13ms to inspect one steel bar surface image and its detection accuracy exceeds 95%.