Adaptive detection of weft‐knitted fabric defects based on machine vision system

This paper describes a machine vision system for the detection of weft‐knitted fabric defects based on an adaptive pulse‐coupled neural network (PCNN) and Ridgelet transform. In order to classify defects according to their different texture features, two methods are implemented: an improved PCNN method to segment the defects such as hole and dropped stitch from background image and a Ridgelet transform method based on wavelet analysis to identify the defect such as course mark. In implementing the PCNN model, necessary parameters of PCNN model such as linking coefficient, connection weight, and iteration number are automatically calculated in accordance with the spatial distance of neurons, mean, and variance value of whole image, and the cross‐entropy criterion. The function of Ridgelet transform is to identify the straight line marks and fit the regression equation for simulating the course mark in the image. The Ridgelet transform model can be simplified as the combination of Radon and wavelet transforms. The parameters of detected line are acquired by wavelet analysis in Fourier semicircle region. The experiment materials were several plain and interlocked weft‐knitted fabrics with hole, dropped stitch, and course mark defects. The fabric images were captured by an area‐scan camera with a resolution of 600 × 800 pixels, and signal processing was controlled by a digital signal processing multiprocessor on the inspection machine. The validation tests proved that the system performed well.

[1]  C. J. Kuo,et al.  A Back-Propagation Neural Network for Recognizing Fabric Defects , 2003 .

[2]  Aysin Ertüzün,et al.  Using perceptual relation of regularity and anisotropy in the texture with independent component model for defect detection , 2007, Pattern Recognit..

[3]  John L. Johnson,et al.  PCNN models and applications , 1999, IEEE Trans. Neural Networks.

[4]  Liu Qing,et al.  Automated image segmentation using improved PCNN model based on cross-entropy , 2004, Proceedings of 2004 International Symposium on Intelligent Multimedia, Video and Speech Processing, 2004..

[5]  Arivazhagan Selvaraj,et al.  Texture classification using ridgelet transform , 2005, Sixth International Conference on Computational Intelligence and Multimedia Applications (ICCIMA'05).

[6]  Jeffrey A. Joines,et al.  Fabric defect detection using a genetic algorithm tuned wavelet filter , 2005 .

[7]  Eric Andres,et al.  Discrete analytical Ridgelet transform , 2004, Signal Process..

[8]  I. Tsai,et al.  Fabric Inspection Based on Best Wavelet Packet Bases , 2000 .

[9]  Michael K. Ng,et al.  Wavelet based methods on patterned fabric defect detection , 2005, Pattern Recognit..

[10]  N. Guo,et al.  Automatic Defect Characterization using Artificial Neural Networks and Deconvolution Techniques , 2006 .

[11]  O.G. Sezer,et al.  Automated inspection of textile defects using independent component analysis , 2004, Proceedings of the IEEE 12th Signal Processing and Communications Applications Conference, 2004..

[12]  Chang Yao,et al.  Automated retinal blood vessels segmentation based on simplified PCNN and fast 2D-Otsu algorithm , 2009 .

[13]  A. Tilocca,et al.  Detecting Fabric Defects with a Neural Network Using Two Kinds of Optical Patterns , 2002 .

[14]  Shih-hsuan Chiu,et al.  Textural Defect Segmentation Using a Fourier-Domain Maximum Likelihood Estimation Method , 2002 .

[15]  Vijay K. Madisetti.  VLSI Digital Signal Processors: An Introduction to Rapid Prototyping and Design Synthesis , 1995 .

[16]  Randall R. Bresee,et al.  Fabric Defect Detection and Classification Using Image Analysis , 1995 .

[17]  Kare L. Jensen,et al.  Fuzz and Pills Evaluated on Knitted Textiles by Image Analysis , 2002 .

[18]  Chung-Feng Jeffrey Kuo,et al.  Using a Neural Network to Identify Fabric Defects in Dynamic Cloth Inspection , 2003 .

[19]  Allan Hanbury,et al.  Finding defects in texture using regularity and local orientation , 2002, Pattern Recognit..

[20]  K. Choi,et al.  Slub Extraction in Woven Fabric Images Using Gabor Filters , 2008 .

[21]  Jason M. Kinser,et al.  Image Processing using Pulse-Coupled Neural Networks , 1998, Perspectives in Neural Computing.

[22]  Zuo Bao-qi,et al.  Identification of fabric defects based on discrete wavelet transform and back-propagation neural network , 2007 .

[23]  E. Shady,et al.  Detection and Classification of Defects in Knitted Fabric Structures , 2006 .

[24]  Cheng Chen,et al.  A two-level scheduling method: an effective parallelizing technique for uniform nested loops on a DSP multiprocessor , 2005, J. Syst. Softw..

[25]  Yu-Chin Hsu,et al.  Pipeline scheduling techniques in high-level synthesis , 1993, Sixth Annual IEEE International ASIC Conference and Exhibit.

[26]  Bugao Xu,et al.  A Simplified pulse-coupled neural network for adaptive segmentation of fabric defects , 2009, Machine Vision and Applications.

[27]  Chi-Ho Chan,et al.  Fabric defect detection by Fourier analysis , 1999, Conference Record of the 1999 IEEE Industry Applications Conference. Thirty-Forth IAS Annual Meeting (Cat. No.99CH36370).