Fourier-domain-based angular correlation for quasiperiodic pattern recognition Applications to web inspection

Abstract

A Fourier-domain-based recognition technique is proposed for periodic and quasiperiodic pattern recognition. It is based on the angular correlation of the moduli of the sample and the reference Fourier spectra centered at the maximum central point. As in other correlation techniques, recognition is achieved when a high correlation peak is obtained, and this result occurs when the two spectra coincide. The angular correlation is a one-dimensional function of the rotation angle. The position of the correlation peak indicates the rotation angle between two similar patterns in the original images. Some optimizations for the discrete calculation of the Fourier-domain-based angular correlation are also proposed. Some applications of this technique to web inspection tasks, such as pattern recognition and classification, damaged web evaluation, and detection of defects, are presented and discussed.

Stochastic simulation of woven composites forming

“…This fact has been used in image analysis of woven textiles to estimate the direction of tows by integrating ( ) v , u F along radial directions and identifying the warp and weft direction as the directions of maximum accumulated radial energies [22]. Furthermore, the number of tows per unit length is related to the distance between the dc term, i.e.…”

Optoelectronic Techniques for Surface Characterization of Fabrics

“…Nevertheless most methods used to characterize textile textures are based on surface pictures. After the acquisition, images are processed with Fourier Transform (Haggerty and Young, 1989;Wood, 1990;Wood, 1996;Millan and Escofet, 1996;Tsai and Hsieh, 1999), wavelet Transform (Kreißl et al, 1997;Tsai and Hsiao, 2001;Shakher et al, 2002;Tsai and Chiang, 2003;Shakher et al, 2004), other filters (Ciamberlini et al, 1996;Escofet et al, 1998),…”

<title>Image segmentation based on a Gaussian model applied to pilling evaluation in fabrics</title>

“…The total area of pilling A can be estimated using the formula np A= (5) i=1,T>t where T is the area in pixels of the i-pill, n is the number of current pills in the binarized image of degree of pillingp, t is the biggest size of the object considered as noise and St is the number of pills of the smallest size t with selected shape.…”

“…Besides, the standard photographs offer an useful reference to experts for visual comparisons with samples affected by pilling. Intense fluffiness and evident pilling (severe pilling) 5 Intense fluffiness and dense pilling throughout the sample (very severe pilling)…”