Research on computer-aided analysis and reverse reconstruction for the weave pattern of fabric

This paper proposes a method to realize computer-aided analysis and reverse reconstruction for the weave pattern of fabric. Firstly, a double-face imaging system is designed to get the redundant image information used to correct node classification, and then the image gridding processing is realized by using the projection algorithm in the warp and weft directions. The grid node color was determined by the color clustering method. Then the attributes and classification of the grid nodes are determined by the analysis of the edge strength information. The correction of node classification is realized with the information of adjacent nodes and the color of the double surface image of the corresponding fabric region. After that, the acquired nodes were encoded with 0 and 1, and then converted into a digital matrix; the basic weave structure matrix of the fabric was derived by matrix transformations. In the meantime, two one-dimensional row and column matrices and a color mapping table are adopted to represent the warp and weft yarn color array. On the basis of the above, the digital files of the woven pattern of sample fabric are established. Finally, the model of the fabric weave pattern can be obtained by the reverse reconstruction method and the automatic recognition of the fabric weave pattern is realized. Through comparison of the original fabric sample image with the reconstructed weave pattern model, it is proved that the proposed method is effective.

[1]  Maziar Palhang,et al.  Identification of printed pattern repeat and its dimensions by image analysis , 2006 .

[2]  Jinho Jang,et al.  Applying image analysis to automatic inspection of fabric density for woven fabrics , 2005 .

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

[4]  T. Kang,et al.  Automatic Recognition of Fabric Weave Patterns by Digital Image Analysis , 1999 .

[5]  Jaume Escofet,et al.  Weave-repeat identification by structural analysis of fabric images. , 2003, Applied optics.

[6]  R. Benslimane,et al.  A system for textile design patterns retrieval. Part I: Design patterns extraction by adaptive and efficient color image segmentation method , 2006 .

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

[8]  J Escofet,et al.  Fourier-domain-based angular correlation for quasiperiodic pattern recognition. Applications to web inspection. , 1996, Applied optics.

[9]  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).

[10]  Daoliang Li,et al.  A new approach for image processing in foreign fiber detection , 2009 .

[11]  Chung-Yang Shih,et al.  Automatic Recognition of Fabric Weave Patterns by a Fuzzy C-Means Clustering Method , 2004 .

[12]  Chang-Chiun Huang,et al.  Woven Fabric Analysis by Image Processing , 2000 .

[13]  Masoud Latifi,et al.  Computer Vision-Aided Fabric Inspection System for On-Circular Knitting Machine , 2005 .

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

[15]  Aleš Linka,et al.  Automatic assessing and monitoring of weaving density , 2009 .

[16]  Bugao Xu,et al.  Identifying Fabric Structures with Fast Fourier Transform Techniques , 1996 .

[17]  J Escofet,et al.  Modeling of woven fabric structures based on fourier image analysis. , 2001, Applied optics.

[18]  Chung-Feng Jeffrey Kuo,et al.  Color and Pattern Analysis of Printed Fabric by an Unsupervised Clustering Method , 2005 .