Journal
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
Volume 71, Issue -, Pages -Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIM.2022.3196133
Keywords
Inspection; Decoding; Training; Image segmentation; Image reconstruction; Feature extraction; Generative adversarial networks; Adversarial learning; anomaly detection; deep learning; defect generation; texture defect inspection
Funding
- National Defense Science and Technology Innovation Special Zone Project [193-A14-202-0123]
- National Natural Science Foundation of China [51875228]
- Project of Foshan Science and Technology Bureau [2020001006509]
Ask authors/readers for more resources
Texture defect inspection remains challenging due to extreme variations in textures and defects. In this study, a novel anomaly composition and decomposition network (ACDN) is proposed for accurate inspection of various texture defects.
Texture defect inspection remains challenging due to the extreme variations in various textures and defects. Current unsupervised-learning-based texture defect inspection methods cannot simultaneously inspect a wide variety of texture defects because they lack an explicit mechanism to encourage the model to create large anomaly scores for defects. In this study, we propose a novel anomaly composition and decomposition network (ACDN) for accurate inspection of various texture defects. In the proposed ACDN, a Gaussian-sampling-based anomaly composition (GSAC) method is proposed to perform the anomaly composition procedure, which composites a large number of defective images for training. Then, a novel anomaly decomposition network (ADN) is proposed to perform the anomaly decomposition procedure, which decomposes the defective images into texture background images and anomaly images by forcing the intrinsic texture features of abnormal images to share a common distribution with those of defect-free images. Through the GSAC and ADN, ACDN learns not only to accurately reconstruct texture background images to cause large reconstruction errors for defect regions but also accurately segment defects. In the testing phase, a defective image is decomposed into a texture background image and an anomaly image through the trained ADN. The residual image between the defective image and the texture background image is then fused with the anomaly image to obtain the defect inspection result. Extensive experimental results on mainstream texture defect datasets demonstrate that ACDN achieves the state-of-the-art texture defect inspection accuracy.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available