期刊
出版社
IEEE
DOI: 10.1109/ddcls49620.2020.9275154
关键词
yam-dyed fabric; fabric defect detection; de-noising auto-encoder; convolutional auto-encoder; Unet
资金
- National Natural Science Foundation of China [61803292]
- Young Science and Technology Star Project of the Shaanxi Innovation Talent Promotion Plan [2018KJXX-038]
- Natural Science Basic Research Plan In Shaanxi Province of China [2019JM-263]
- Open Subject of Key Laboratory of Advanced Control of Light Industry Process of Education Ministry [APCLI1806]
- Graduate Scientific Innovation Fund for Xi'an Polytechnic University [chx2020017]
Practical factors such as high labor cost of labelling defect samples and scarcity of defect samples make it difficult for supervised machine learning models to solve the problem of yam-dyed fabric defect detection. To solve this problem, this paper proposes an unsupervised yam-dyed fabric defect detection method based on U-shaped de-noising convolutional auto-encoder (UDCAE). Firstly, for tested samples of yam-dyed fabric, the training dataset was constructed by collecting the non-defect yarn-dyed fabric samples. Then, the non-defect dataset is utilized to model and train the proposed UDCAE model. Finally, the defective area can be quickly detected by calculating the residual between the original tested yarn-dyed fabric image and its reconstructed item correspondingly. The experiment results show that the proposed method can accurately detect defects of yarn-dyed fabrics with different patterns.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据