Detecting fabric density and weft distortion in woven fabrics using the discrete fourier transform

Abstract

Fabric density and distortion offer important information on fabric attributes and quality during the manufacturing process. However, most current procedures require human effort, which is often inefficient, time-consuming, and imprecise. In this paper, we propose to use an automatic method using the 2D Fast Fourier Transform (2D-FFT) to count the number of yarns and determine the angle rotation of weft yarns in fabric images. First, we explain the mathematical background of Fourier Transform and 2D-FFT. Then, we use a customized and optimized software package to apply a 2D-FFT to extract image magnitude, phase, and power spectrum. We apply the inverse 2D Fast Fourier Transform (2D-iFFT) on selected frequencies corresponding to periodic structures - basic weave patterns - to reconstruct the original image and extract warp and weft yarns separately. Finally, we use a local adaptive threshold process to convert reconstructed images into binary images for the counting and calculating process. For the weft rotation, we apply a mathematical calculation on the frequency domain to collect the angular distribution and then figure out the major rotation of weft yarns. Our experiments show that the proposed method is highly accurate and capable of inspecting different patterns of fabric. We also observe that the processing time of our proposal method is practical and time-efficient.