Abstract

Surface inspection is a critical step in ensuring product quality in the steel-making industry. In order to relieve inspectors of laborious work and improve the consistency of inspection, much effort has been dedicated to the automated inspection using computer vision approaches over the past decades. However, due to non-uniform illumination conditions and similarity between the surface textures and defects, the present methods are usually applicable to very specific cases. In this paper a new framework for surface inspection has been proposed to overcome these limitations. By investigating the image formation process, a quantitative model characterizing the impact of illumination on the image quality is developed, based on which the non-uniform brightness in the image can be effectively removed. Then a simple classifier is designed to identify the defects among the surface textures. The significance of this approach lies in its robustness to illumination changes and wide applicability to different inspection scenarios. The proposed approach has been successfully applied to the real-time surface inspection of round billets in real manufacturing. Implemented on a conventional industrial PC, the algorithm can proceed at 12.5 frames per second with the successful detection rate being over 90% for turned and skinned billets.

© 2017 Optical Society of America

Defect detection for corner cracks in steel billets using a wavelet reconstruction method

Yong-Ju Jeon, Doo-chul Choi, Sang Jun Lee, Jong Pil Yun, and Sang Woo Kim
J. Opt. Soc. Am. A 31(2) 227-237 (2014)

Steel-surface defect detection using a switching-lighting scheme

Yong-Ju Jeon, Doo-chul Choi, Sang Jun Lee, Jong Pil Yun, and Sang Woo Kim
Appl. Opt. 55(1) 47-57 (2016)

Automatic surface inspection for S-PVC using a composite vision-based method

Qilin Bi, Miaohui Wang, Minling Lai, Jiaxin Lin, Jialin Zhang, and Xiaoguang Liu
Appl. Opt. 59(4) 1008-1017 (2020)

Automatic optical inspection platform for real-time surface defects detection on plane optical components based on semantic segmentation

Jules Karangwa, Linghua Kong, Dingrong Yi, and Jishi Zheng
Appl. Opt. 60(19) 5496-5506 (2021)

Development of an optical defect inspection algorithm based on an active contour model for large steel roller surfaces

Jun Yang, Xuekun Li, Jirui Xu, Yuzhong Cao, Yun Zhang, Liping Wang, and Sheng Jiang
Appl. Opt. 57(10) 2490-2498 (2018)