EXTRACTING PRINTED DESIGNS AND WOVEN PATTERNS FROM TEXTILE IMAGES

Jia Wei, Stephen J. McKenna, Annette A. Ward

2009

Abstract

The extraction of printed designs and woven patterns from textiles is formulated as a pixel labelling problem. Algorithms based on Markov random field (MRF) optimisation and reestimation are described and evaluated on images from an historical fabric archive. A method for quantitative evaluation is presented and used to compare the performance of MRF models optimised using $\alpha-$expansion and iterated conditional modes, both with and without parameter reestimation. Results are promising for potential application to content-based indexing and browsing.

References

  1. Besag, J. (1986). On the statistical analysis of dirty picutures. Journal of Royal Statistical Sociely, Series B, 48(3):259-302.
  2. Boykov, Y. and Kolmogorov, V. (2004). An experimental comparison of min-cut / max-flow algorithms for energy minimization in vision. IEEE Transactions on Pattern Analysis and Machine Intelligence, 26:1124- 1137.
  3. Boykov, Y., Veksler, O., and Zabih, R. (November 2001). Fast aproximate energy minimization via graph cut. IEEE Transactions on Pattern Analysis and Machine Intelligence, 23, no. 11:1222-1239.
  4. Deng, Y. and Manjunath, B. (2001). Unsupervised segmentation of color-texture regions in images and video. IEEE Transactions on Pattern Analysis and Machine Intelligence, 23:800-810.
  5. Gupta, L. and Sortrakul, T. (1998). A Gaussian mixture based image segmentation algorithm. Pattern Recognition, 31(3):315-325.
  6. Kato, Z. and Pong, T. C. (2006). A Markov random field image segmentation model for color texture images. Image and Vison Computing, 24:1103-1114.
  7. Li, S. Z. (1995). Markov Random Field Modeling in Computer Vision. Springer-Verlag.
  8. Permuter, H., Francos, J., and Jermyn, I. H. (2003). Gaussian mixture models of texture and color for image database retrieval. Acoustics, Speech and Signal Processing, 3:569-572.
  9. Potts, R. (1952). Some generalized order-disorder transformation. Proc. Cambridge Philosophical Soc., 48:106- 109.
  10. Roberts, S. J., Husmeier, D., Rezek, I., and Penny, W. (1998). Bayesian approaches to Gaussian mixture modeling. IEEE Transactions on Pattern Analysis and Machine Intelligence, 20(11):1133-1142.
  11. Szeliski, R., Zabih, R., Scharstein, D., Veksler, O., Kolmogorov, V., Agarwala, A., Tappen, M., and Rother, C. (2008). A comparative study of energy minimization methods for Markov random fields with smoothness-based priors. IEEE Transactions on Pattern Analysis and Machine Intelligence, 30:1068- 1080.
  12. Valiente, J. M., Carretero, M. C., Gmis, J. M., and Albert, F. (2001). Image processing tool for the purpose of textile fabric modeling. In 12th International Conference on Designs Tools and Methods.
  13. Wu, Y., Yang, X., and Chan, K. L. (2003). Unsupervised colour image segmentation based on Gaussian mixture model. Information, Communications and Signal Processing, 1:541-544.
  14. Zabih, R. and Kolmogorov, V. (2004). Spatially coherent clustering using graph cuts. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2:473-444.
  15. Table 6: Segmentation results on a 996×608 textile image ( c Liberty Fabric). Ground truth BIC
Download


Paper Citation


in Harvard Style

Wei J., J. McKenna S. and A. Ward A. (2009). EXTRACTING PRINTED DESIGNS AND WOVEN PATTERNS FROM TEXTILE IMAGES . In Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2009) ISBN 978-989-8111-69-2, pages 201-208. DOI: 10.5220/0001800702010208


in Bibtex Style

@conference{visapp09,
author={Jia Wei and Stephen J. McKenna and Annette A. Ward},
title={EXTRACTING PRINTED DESIGNS AND WOVEN PATTERNS FROM TEXTILE IMAGES},
booktitle={Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2009)},
year={2009},
pages={201-208},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001800702010208},
isbn={978-989-8111-69-2},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Fourth International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2009)
TI - EXTRACTING PRINTED DESIGNS AND WOVEN PATTERNS FROM TEXTILE IMAGES
SN - 978-989-8111-69-2
AU - Wei J.
AU - J. McKenna S.
AU - A. Ward A.
PY - 2009
SP - 201
EP - 208
DO - 10.5220/0001800702010208