Unsupervised defect segmentation of patterned materials under NIR illumination

An unsupervised detection method for automatic flaw segmentation in patterned materials (textile, non-woven, paper) that has no need of any defect-free references or a training stage is presented in this paper. Printed materials having a pattern of colored squares, bands, etc. superimposed to the background texture can be advantageously analyzed using NIR illumination and a camera with enough sensitivity to this region of the spectrum. The contrast reduction of the pattern in the NIR image facilitates material inspection and defect segmentation. Underdetection and misdetection errors can be reduced in comparison with the inspection performed under visible illumination. For woven fabrics, with periodic structure, 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. For nonwoven and random textured materials, the algorithm combines the multiresolution Gabor analysis of the sample image with a statistical analysis of the wavelet coefficients corresponding to each detail. The information of all the channels is merged in a single binary output image where the defect appears segmented from the background. The method is applicable to random, non-periodic, and periodic textures. Since all the information to inspect a sample is obtained from the sample itself, the method is proof against heterogeneities between different samples of the material, in-plane positioning errors, scale variations and lack of homogeneous illumination. Experimental results are presented for a variety of materials and defects.