Detection of steel defect using the image processing algorithms

Document Type : Original Article


1 Electrical and Computer Department., Isfahan University of Technology, Isfahan, Iran.

2 Engineering Department., University of Zanjan, Zanjan, Iran.

3 Electrical & Computer Eng. Dept., University of Windsor, 401 Sunset Ave, Windsor, Ontario, Canada.


In this paper, detection and classification of steel surface defects is investigated. Image
processing algorithms are applied for detecting four popular kind of steel defects, i.e.,
hole, scratch, Coil break and rust. The results show that the applied algorithms have a
good performance on steel defect detection. Numerical results indicate that the
implemented image processing algorithms have 88.4%, 78%, 90.4%, 90.3 % accuracy
respectively on the hole, scratch, Coil break and rust defect.