Weakly-Supervised Defect Segmentation on Periodic Textures Using CycleGAN

• Published in: IEEE access Vol. 8; pp. 176202 - 176216
• Main Authors: Kim, Minsu, Jo, Hoon, Ra, Moonsoo, Kim, Whoi-Yul
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Automated defect inspection; Data augmentation; Defects; Fabrics; Generative adversarial networks; Image quality; Image segmentation; Inspection; Labels; Manufacturing industries; periodic textures; Semantic segmentation; Semantics; Surface texture; Task analysis; visual inspection system; weakly-supervised learning
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2020.3024554

The importance of an automated defect inspection system has been increasing in the manufacturing industries. Various products to be examined have periodic textures. Among image-based inspection systems, it is common that supervised defect segmentation requires a great number of defect images with their own region-level labels; however, it is difficult to prepare sufficient training data. Because most products are of normal quality, it is difficult to obtain images of product defects. Pixel-wise annotation for semantic segmentation tasks is an exhausting and time-consuming process. To solve these problems, we propose a weakly-supervised defect segmentation framework for defect images with periodic textures and a data augmentation process using generative adversarial networks. With only image-level labeling, the proposed segmentation framework translates a defect image into its defect-free version, called a golden template, using CycleGAN and then segments the defects by comparing the two images. The proposed augmentation process creates whole new synthetic defect images from real defect images to obtain sufficient data. Furthermore, synthetic non-defect images are generated even from real defect images through the augmentation process. The experimental results demonstrate that the proposed framework with data augmentation outperforms an existing weakly-supervised method and shows remarkable results comparable to those of supervised segmentation methods.