NEU-DET-and-GC10-DET-with-YOLO-fromat
收藏Zenodo2025-08-27 更新2026-05-26 收录
下载链接：
https://zenodo.org/doi/10.5281/zenodo.16882077
下载链接
链接失效反馈官方服务：
资源简介：
The raw data of this dataset originates from NEU-DET (K. Song and Y. Yan, “A noise robust method based on completed local binary patterns for hot-rolled steel strip surface defects,” Applied Surface Science, vol. 285, pp. 858-864, Nov. 2013) and GC10-DET (Lv, X.; Duan, F.; Jiang, J.-j.; Fu, X. and Gan, L. “Deep Metallic Surface Defect Detection: The New Benchmark and Detection Network.” Sensors 2020, 20, 1562.).
The following preprocessing steps were applied to the original data in this dataset:
Format conversion: The data formats of both NEU-DET and GC10-DET were converted into YOLO format.
Noise addition: Random noise at 15 dB to 30 dB was added to the images of both NEU-DET and GC10-DET.
Data splitting: The data in both NEU-DET and GC10-DET were divided into training and validation sets in an 8:2 ratio.
提供机构：
Zenodo创建时间：
2025-08-15
