Design of Strip Surface Defect Detection System Based on Machine Vision

In order to address the practical application issues of surface defect detection in steel strips, this paper designs a surface defect detection system based on machine vision. The detection algorithm was developed, and defect images of the steel strip surface were captured by an image acquisition device. The accuracy of detection and system stability were studied. First, an improved Faster R-CNN algorithm was adopted and trained using the NEU-DET dataset to learn the feature information of surface defects in steel strips. Then, a hardware and software platform for the detection system was built, and the defect detection performance was verified. The study shows that the detection system operates smoothly and achieves high detection accuracy.