Metal Defect Detection Based on Yolov5
Abstrak
Metal surface defect detection has been a challenge in the industrial field. The current metal surface defect algorithms target only at a few types of defects and fail to perform well on defects with different scales. In this paper, a large number of metal surface defects are studied based on GC10-DET data set. An improved yolov5 detection network is designed targeting defects of various scales, especially of small-scaled objects, using a specific data enhancement method to regularize and an effective loss function to address data imbalance caused by small-scaled object defects. Finally, the comparative experiment on GC10-DET data set proves the major improvements on accuracy superiority of the proposed method.
Topik & Kata Kunci
Penulis (3)
Kung-Jeng Wang
Zixuan Teng
Tengyue Zou
Akses Cepat
- Tahun Terbit
- 2022
- Bahasa
- en
- Total Sitasi
- 19×
- Sumber Database
- Semantic Scholar
- DOI
- 10.1088/1742-6596/2218/1/012050
- Akses
- Open Access ✓