DCC-CenterNet: A rapid detection method for steel surface defects

In recent years, surface defect detection methods based on deep learning have been widely used. A conflict between speed and accuracy, however, still exists. In this paper, a steel surface defect detector, DCC-CenterNet, is proposed to achieve the best speed-accuracy trade-off. This detector uses keypoint estimation to locate center points and regresses all other defect properties. Firstly, a dilated feature enhancement model is proposed to enlarge the receptive field of the detector. Secondly, a new centerness function center-weight is proposed to make the keypoint estimation more accurate. Then, the CIoU loss that considers the overlap area and aspect ratio of the defect is adopted in the size regression. Finally, the results of experiments show that the accuracy of DCCCenterNet can reach 79.41 mAP, and the running speed FPS is 71.37 with input size 224 x 224 on the NEU-DET steel defect dataset. And it reaches 61.93 mAP on the GC10-DET steel sheet surface defect dataset at a running speed of 31.47 FPS with input size 512 x 512. It demonstrates that the developed detector can detect steel surface defects efficiently and effectively.

Automated summary

This paper introduces a steel surface defect detector, DCC-CenterNet, utilizing deep learning and keypoint estimation techniques to achieve a balance between speed and accuracy. Experimental results demonstrate that the detector efficiently detects steel surface defects on different datasets.