Translator Disclaimer
4 May 2010 Unsupervised flaw segmentation in textile materials under visible and NIR illumination
Author Affiliations +
An unsupervised novelty detection method for automatic flaw segmentation in textile materials that has no need of any defect-free references or a training stage is presented in this paper. The algorithm is based on the structural feature extraction of the weave repeat from the Fourier transform of the sample image. These features are used to define a set of multiresolution bandpass filters adapted to the fabric structure that operate in the Fourier domain. Inverse Fourier transformation, binarization and merging of the information obtained at different scales lead to the output image that contains flaws segmented from the fabric background. The whole process is fully automatic and can be implemented either optical or electronically. Fabrics having a superstructure of colored squares, bands, etc. superimposed to the basic web structure can be advantageously analyzed using NIR illumination and a camera sensitive to this region of the spectrum. The contrast reduction of the superstructure signal in the NIR image facilitates fabric structure inspection and defect segmentation. Underdetection and misdetection errors can be noticeably reduced in comparison with the inspection performed under visible illumination. Experimental results are presented and discussed for a variety of fabrics and defects.
© (2010) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
María S. Millán, Jaume Escofet, and Miquel Ralló "Unsupervised flaw segmentation in textile materials under visible and NIR illumination", Proc. SPIE 7723, Optics, Photonics, and Digital Technologies for Multimedia Applications, 77230Q (4 May 2010);

Back to Top