Defect Data Augmentation Method for Robust Image-based Product Inspection
##plugins.themes.bootstrap3.article.main##
##plugins.themes.bootstrap3.article.sidebar##
Abstract
In this paper, we develop a model for detecting defects in fabric products based on an object segmentation algorithm, including a novel image data augmentation method to enhance the robustness. First, a vision-based inspection system is established to collect image data of the fabric products. The three types of fabric defects, such as a hole, a stain, and a dyeing defect, are considered. To enhance defect detection accuracy and robustness, a novel image data augmentation method, referred to as the defect-area cut-mix, is proposed. In this method, the shapes that are the same as each defect are extracted using the masks, and then they are added to non-defective fabric images. Second, an ensemble process is implemented by combining the results of two models, one with high sensitivity in defect diagnosis and the other with lower sensitivity. The results demonstrated that the model trained on the augmented dataset exhibits improved metrics such as intersection over union and classification accuracy in defect detection on the test dataset.
How to Cite
##plugins.themes.bootstrap3.article.details##
Data augmentation, Image segmentation, Product inspection
Israel, I. M., Israel, S. A., & Irvine, J. M. (2021, October). Factors influencing CNN performance. In 2021 IEEE Applied Imagery Pattern Recognition Workshop (AIPR) (pp. 1-4). IEEE. DOI 10.1109/AIPR52630.2021.9762112 Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). You only look once: Unified, real-time object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 779-788). Cho, J., Lee, K., Shin, E., Choy, G., & Do, S. (2015). How much data is needed to train a medical image deep learning system to achieve necessary high accuracy? arXiv preprint arXiv:1511.06348. https://arxiv.org/abs/1511.06348 DOI 10.48550/arXiv.1511.06348 Yun, S., Han, D., Oh, S. J., Chun, S., Choe, J., & Yoo, Y. (2019). Cutmix: Regularization strategy to train strong classifiers with localizable features. In Proceedings of the IEEE/CVF international conference on computer vision (pp. 6023-6032).
This work is licensed under a Creative Commons Attribution 3.0 Unported License.
The Prognostic and Health Management Society advocates open-access to scientific data and uses a Creative Commons license for publishing and distributing any papers. A Creative Commons license does not relinquish the author’s copyright; rather it allows them to share some of their rights with any member of the public under certain conditions whilst enjoying full legal protection. By submitting an article to the International Conference of the Prognostics and Health Management Society, the authors agree to be bound by the associated terms and conditions including the following:
As the author, you retain the copyright to your Work. By submitting your Work, you are granting anybody the right to copy, distribute and transmit your Work and to adapt your Work with proper attribution under the terms of the Creative Commons Attribution 3.0 United States license. You assign rights to the Prognostics and Health Management Society to publish and disseminate your Work through electronic and print media if it is accepted for publication. A license note citing the Creative Commons Attribution 3.0 United States License as shown below needs to be placed in the footnote on the first page of the article.
First Author et al. This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 United States License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.