This dataset aims to set a benchmark suit for vision based fabric defect detection, including image dataset, evaluation protocol, baseline experiments.
Please refer to our website for more information.
https://github.com/nico-zck/ZJU-Leaper-Dataset/tree/master/dataset_api
https://github.com/nico-zck/ZJU-Leaper-Dataset/tree/master/baselines
The paper titled "ZJU-Leaper: A Benchmark Dataset for Fabric Defect Detection and a Comparative Study" was accepted by IEEE Transactions on Artificial Intelligence.
@article{zju-leaper,
author={Zhang, Chenkai and Feng, Shaozhe and Wang, Xulongqi and Wang, Yueming},
journal={IEEE Transactions on Artificial Intelligence},
title={ZJU-Leaper: A Benchmark Dataset for Fabric Defect Detection and a Comparative Study},
year={2020},
volume={1},
number={3},
pages={219-232},
doi={10.1109/TAI.2021.3057027}
issn={2691-4581},
publisher={IEEE},
}
- codes for dataset API
- documentation for dataset API
- codes for baseline experiments
- download link for the dataset