Advertisement

A Suitable Neural Network to Detect Textile Defects

  • Md. Atiqul Islam
  • Shamim Akhter
  • Tamnun E. Mursalin
  • M. Ashraful Amin
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4233)

Abstract

25% of the total revenue earning is achieved from Textile exports for some countries like Bangladesh. It is thus important to produce defect free high quality garment products. Inspection processes done on fabric industries are mostly manual hence time consuming. To reduce error on identifying fabric defects requires automotive and accurate inspection process. Considering this lacking, this research implements a Textile Defect detector. A multi-layer neural network is determined that best classifies the specific problems. To feed neural network the digital fabric images taken by a digital camera and converts the RGB images are first converted into binary images by restoration process and local threshold techniques, then three different features are determined for the actual input to the neural network, which are the area of the defects, number of the objects in a image and finally the shape factor. The develop system is able to identify two very commonly defects such as Holes and Scratches and other types of minor defects. The developed system is very suitable for Least Developed Countries, identifies the fabric defects within economical cost and produces less error prone inspection system in real time.

Keywords

Textile defects threshold decision tree multi-layer neural networks resilient back propagation cross validation 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Ralló, M., Millán, M.S., Escofet, J.: Wavelet based techniques for textile inspection. Opt. Eng. 26(2), 838–844 (2003)Google Scholar
  2. 2.
    Meier, R.: Uster Fabriscan, The Intelligent Fabric Inspection, Online document (cited April 20, 2005), available HTTP: http://www.kotonline.com/english_pages/ana_basliklar/uster.asp
  3. 3.
    Stojanovic, R., Mitropulos, P., Koulamas, C., Karayiannis, Y.A., Koubias, S., Papadopoulos, G.: Real-time Vision based System for Textile Fabric Inspection. Real-Time Imaging 7(6), 507–518 (2001)zbMATHCrossRefGoogle Scholar
  4. 4.
    Gonzalez, R.C., Woods, R.E., Eddins, S.L.: Digital Image Processing using MATLAB, pp. 76–104, 142–166, 404–407 (2005), ISBN 81-297-0515-XGoogle Scholar
  5. 5.
    Hagan, M.T., Demuth, H.B., Beale, M.: Neural Network Design, part 2.5, 10.8 (2002), ISBN 981-240-376-0Google Scholar
  6. 6.
    Riedmiller, M., Braun, H.: A direct adaptive method for faster backpropagation learning: The RPROP algorithm. In: Proceedings of the IEEE International Conference on Neural Networks (1993)Google Scholar
  7. 7.
    Neural Network Toolbox, MATLAB –The Language of Technical Conputing (CD Document), Version 7.0.0.19920(R14) (2004)Google Scholar
  8. 8.
    Batchelor, B.G., Whelan, P.F.: Selected Papers on Industrial Machine Vision Systems. SPIE Milestone Series (1994)Google Scholar
  9. 9.
    Newman, T.S., Jain, A.K.: A Survey of Automated Visual Inspection. Computer Vision and Image Understanding 61, 231–262 (1995)CrossRefGoogle Scholar
  10. 10.
    Zhang, H., Guan, J., Sun, G.C.: Artificial Neural Network-Based Image Pattern Recognition. In: ACM 30th Annual Southeast Conference (1992)Google Scholar
  11. 11.
    Ciamberlini, C., Francini, F., Longobardi, G., Sansoni, P., Tiribilli, B.: Defect detection in textured materials by optical filtering with structured detectors and selfadaptable masks. Opt. Eng. 35(3), 838–844 (1996)CrossRefGoogle Scholar
  12. 12.
    Kang, T.J., et al.: Automatic Recognition of Fabric Weave Patterns by Digital Image Analysis. Textile Res. J. 69(2), 77–83 (1999)CrossRefGoogle Scholar
  13. 13.
    Kang, T.J., et al.: Automatic Structure Analysis and Objective Evaluation of Woven Fabric Using Image Analysis. Textile Res. J. 71(3), 261–270 (2001)Google Scholar
  14. 14.
    Jasper, W.J., Garnier, S.J., Potlapalli, H.: Texture characterization and defect detection using adaptive wavelets. Opt. Eng. 35(11), 3140–3149 (1996)CrossRefGoogle Scholar
  15. 15.
    Jasper, W.J., Potlapalli, H.: Image analysis of mispicks in woven fabric. Text. Res.J. 65(1), 683–692 (1995)CrossRefGoogle Scholar
  16. 16.
    Escofet, J., Navarro, R., Millán, M.S., Pladellorens, J.: Detection of local defects in textile webs using Gabor filters. In: Réfrégier, P. (ed.) Vision Systems: New Image Processing Techniques. Proceedings SPIE, vol. 2785, pp. 163–170 (1996)Google Scholar
  17. 17.
    Escofet, J., Navarro, R., Millán, M.S., Pladellorens, J.: Detection of local defects in textile webs using Gabor filters. Opt. Eng. 37(8), 2297–2307 (1998)CrossRefGoogle Scholar
  18. 18.
    Millán, M.S., Escofet, J.: Fourier domain based angular correlation for quasiperiodic pattern recognition. Applications to web inspection. Appl. Opt. 35(31), 6253–6260 (1996)CrossRefGoogle Scholar
  19. 19.
    Martin, T., Jones, M., Edmison, J., Sheikh, T., Nakad, Z.: Modeling and Simulating Electronic Textile Applications, LCTES, USA (2004)Google Scholar
  20. 20.
    Dockery, A.: Automatic Fabric Inspection: Assessing the Current State of the Art, Online document (2001) (cited April 29, 2005)Google Scholar
  21. 21.
    Ji, Y., Chang, K.H., Hung, C.: Efficient Edge Detection and Object Segmentation Using Gabor Filters, ACMSE, USA (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Md. Atiqul Islam
    • 1
  • Shamim Akhter
    • 1
  • Tamnun E. Mursalin
    • 1
  • M. Ashraful Amin
    • 2
  1. 1.Department of Computer ScienceAmerican International University- BangladeshDhakaBangladesh
  2. 2.Department of Electronic EngineeringCity University of Hong KongKowloon, Hong Kong

Personalised recommendations