Department of Mathematics
This paper analyzes the cartoon and texture structures to inspect and visualize defective objects in a patterned fabric image. It presents a method of an image decomposition (ID) and solves it by a convex optimization algorithm. Our experimental results on benchmark fabric images are superior to those by other methods.
Classification, convex optimization, image decomposition, operator splitting method, patterned fabric inspection
Source Publication Title
IEEE Transactions on Automation Science and Engineering
Institute of Electrical and Electronics Engineers
1545-5955 © 2014 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See http://www.ieee.org/publications_standards/publications/rights/index.html for more information.
The work of M. K. Ng is supported by RGC Grants and HKBU FRG Grants. The work of H. Y. T. Ngan is supported by HKBU FRG Grant FRG1/12-13/075. The work of X. M. Yuan is supported by the General Research Fund of Hong Kong 203712. The work of W. X. Zhang is supported by NNSFC 11301055.
Link to Publisher's Edition
Ng, M., Ngan, H., Yuan, X., & Zhang, W. (2014). Patterned fabric inspection and visualization by the method of image decomposition. IEEE Transactions on Automation Science and Engineering, 11 (3), 943-947. https://doi.org/10.1109/TASE.2014.2314240