Research Article
Surface Defect Detection Algorithm of Aluminum Sheet Based on Improved Yolov3
@INPROCEEDINGS{10.1007/978-3-031-32443-7_9, author={Liu Yang and Guoxiong Hu and Li Huang}, title={Surface Defect Detection Algorithm of Aluminum Sheet Based on Improved Yolov3}, proceedings={Mobile Networks and Management. 12th EAI International Conference, MONAMI 2022, Virtual Event, October 29-31, 2022, Proceedings}, proceedings_a={MONAMI}, year={2023}, month={5}, keywords={Defect detection Attention Mechanism Few Shot Small Target Detection}, doi={10.1007/978-3-031-32443-7_9} }- Liu Yang
Guoxiong Hu
Li Huang
Year: 2023
Surface Defect Detection Algorithm of Aluminum Sheet Based on Improved Yolov3
MONAMI
Springer
DOI: 10.1007/978-3-031-32443-7_9
Abstract
The surface defect detection of aluminum sheet is of great significance to ensure the appearance and quality of aluminum sheet. The surface defects of aluminum sheets have the characteristics of different shapes, obvious size differences, and difficult to obtain defect samples, which make defect detection challenging. In order to solve this problem, we make the following improvements to YOLOv3: Adding attention mechanism modules after the three feature layers output by the model backbone and after neck upsampling; Freezing the model backbone and using pretrained for transfer learning. The proposed YOLOv3 + ECA model is compared with the target detection models such as YOLOv3 and Faster-RCNN. It is found that the mAP of our model reaches 96.22%, which is higher than the current conventional algorithm. The AP values for different types of defects have good detection results.
