PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
Image inpaintnig in textile manufacturing is a new emerging research topic in preprocessing for jacquard CAD systems. One of the most important aspects of a jacquard CAD system is the simulation of the appearance of a jacquard texture during inference. Jacquard image inpainting has become an indispensable process for the Jacquard CAD system. Jacquard image reconstruction is designed to restore a damaged image with missing information, so it is necessary to determine which parts of the image need to be repaired. Thus, this task includes two processing stages: the detection of defects and their recovery. This article presents a two-stage approach that combines new and traditional algorithms for detecting defects and repairing damaged areas. The first stage is a defect detection method based on a convolutional autoencoder (U-Net). The second stage is image inpainting based on exemplar-based concepts and the anisotropic gradient. Our system quantitatively outperforms state-of-the-art methods regarding reconstruction accuracy in the benchmark.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
The alert did not successfully save. Please try again later.
N. Gapon, V. Voronin, M. Zhdanova, R. Sizyakin, E. Semenishchev, Yu Ilyukhin, "Deep learning-based image defect detection and removal in manufacturing," Proc. SPIE 12624, Digital Optical Technologies 2023, 126241Q (7 August 2023); https://doi.org/10.1117/12.2682045