Optimization of automated online fabric inspection by fast Fourier transform (FFT) and cross-correlation

Abstract

Fabric inspection has an importance to prevent the risk of delivering inferior quality product. Until recently, the process was still undertaken offline and manually by humans, which has many drawbacks. The continuous development in computer technology introduces the automated fabric inspection as an effective alternative. In our work, Fast Fourier Transform and Cross-correlation techniques, i.e. linear operations, are first implemented to examine the structure regularity features of the fabric image in the spatial domain. To improve the efficiency of the technique and overcome the problem of detection errors, further thresholding operation is implemented using a level selection filter. Through this filter, the technique is able to detect only the actual or real defects and highlight its exact dimensions. A software package such as Matlab or Scilab is used for this procedure. It is implemented firstly on a simulated plain fabric to determine the most important parameters during the process of defect detection and then to optimize each of them even considering noise. To verify the success of the technique, it is implemented on real plain fabric samples with different colors containing various defects. Several results of the proposed technique for the simulated and real plain fabric structures with the most common defects are presented. Finally, a vision-based fabric inspection prototype that could be accomplished on-loom to inspect the fabric under construction with 100% coverage is proposed.

Fast and Parallel Summed Area Table for Fabric Defect Detection

“…Consequently, within the limits of the hardware resources o®ered by the GPU, the input image should be large as possible to fully utilize the computation power of the GPU. Moreover, Malek et al 33 developed an online fabric inspection by Fast Fourier Transformer (FFT) and cross-correlation that was able to detect defects on image of 500 Â 500 pixels in 700 ms. However, the experiments conducted in our work detected the defects for the same size image in 140.0 and 43.5 ms using PFDD-NCC and PFDD-SAT algorithms consequently as shown in Table 2.…”

A Fast Fabric Defect Detection Framework for Multi-Layer Convolutional Neural Network Based on Histogram Back-Projection

“…Spectral methods include Fourier Manuscript transform [9], Gabor filter [10], [11] and wavelet transform [12]. Model methods include autoregressive models and Markov fields [13].…”

A High-Precision Fusion Algorithm for Fabric Quality Inspection

“…Malek A S et al [5] used fast Fourier transform and cross correlation techniques to analyze the fabric image in the spatial domain, and obtain the fabric structure characteristics to detect the defects. Alper Selver M. et al [6] proposed a texture detection based on texture statistics and gradient search, combined with differential histogram and cooccurrence matrix for fabric texture analysis, so as to speed up the processing speed of detection.…”