Advertisement

Genetic Paint: A Search for Salient Paintings

  • J. P. Collomosse
  • P. M. Hall
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3449)

Abstract

The contribution of this paper is a novel non-photorealistic rendering (NPR) algorithm for rendering real images in an impasto painterly style. We argue that figurative artworks are salience maps, and develop a novel painting algorithm that uses a genetic algorithm (GA) to search the space of possible paintings for a given image, so approaching an “optimal” artwork in which salient detail is conserved and non-salient detail is attenuated. We demonstrate the results of our technique on a wide range of images, illustrating both the improved control over level of detail due to our salience adaptive painting approach, and the benefits gained by subsequent relaxation of the painting using the GA.

Keywords

Mean Square Error Source Image Salient Region Brush Stroke Salience Measure 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Gombrich, E.H.: Art and Illusion. Phaidon Press Ltd., Oxford (1960)Google Scholar
  2. 2.
    Hall, P.M., Owen, M., Collomosse, J.P.: A trainable low-level feature detector. In: Proc. Intl. Conf. on Pattern Recognition (ICPR), vol. 1, pp. 708–711 (2004)Google Scholar
  3. 3.
    Hall, P., Owen, M., Collomosse, J.P.: Learning to detect low-level features. In: Proc. 15th British Machine Vision Conf. (BMVC), vol. 1, pp. 337–346 (2004)Google Scholar
  4. 4.
    Sziranyi, T., Tath, Z.: Random paintbrush transformation. In: Proc. 15th Intl. Conf. on Pattern Recognition (ICPR), Barcelona, vol. 3, pp. 155–158 (2000)Google Scholar
  5. 5.
    Hertzmann, A.: Paint by relaxation. In: Proc. Comp. Graph. Intl., pp. 47–54 (2001)Google Scholar
  6. 6.
    Haeberli, P.: Paint by numbers: abstract image representations. In: Proc. ACM SIGGRAPH, vol. 4, pp. 207–214 (1990)Google Scholar
  7. 7.
    Litwinowicz, P.: Processing images and video for an impressionist effect. In: Proc. ACM SIGGRAPH, Los Angeles, USA, pp. 407–414 (1997)Google Scholar
  8. 8.
    Treavett, S., Chen, M.: Statistical techniques for the automated synthesis of non-photorealistic images. In: Proc. 15th Eurographics UK Conf., pp. 201–210 (1997)Google Scholar
  9. 9.
    Shiraishi, M., Yamaguchi, Y.: An algorithm for automatic painterly rendering based on local source image approximation. In: Proc. ACM NPAR, pp. 53–58 (2000)Google Scholar
  10. 10.
    Hertzmann, A.: Painterly rendering with curved brush strokes of multiple sizes. In: Proc. ACM SIGGRAPH, pp. 453–460 (1998)Google Scholar
  11. 11.
    Gooch, B., Coombe, G., Shirley, P.: Artistic vision: Painterly rendering using computer vision techniques. In: Proc. ACM NPAR, pp. 83–90 (2002)Google Scholar
  12. 12.
    DeCarlo, D., Santella, A.: Abstracted painterly renderings using eye-tracking data. In: Proc. ACM SIGGRAPH, pp. 769–776 (2002)Google Scholar
  13. 13.
    Hertzmann, A., Jacobs, C.E., Oliver, N., Curless, B., Salesin, D.H.: Image analogies. In: Proc. ACM SIGGRAPH, pp. 327–340 (2001)Google Scholar
  14. 14.
    Walker, K.N., Cootes, T.F., Taylor, C.J.: Locating salient object features. In: Proc. 9th British Machine Vision Conf (BMVC), vol. 2, pp. 557–567 (1998)Google Scholar
  15. 15.
    Holland, J.: Adaptation in Natural and Artificial Systems. U. Michigan (1975)Google Scholar
  16. 16.
    de Jong, K.: Learning with genetic algorithms. Machine Learning 3, 121–138 (1988)CrossRefGoogle Scholar
  17. 17.
    Goldberg, D.: GAs in Search, Optimization, and Machine Learning. Add. W., Reading (1989)Google Scholar
  18. 18.
    Collomosse, J.P.: Higher Level Techniques for the Artistic Rendering of Images and Video. PhD thesis, University of Bath, U.K. (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • J. P. Collomosse
    • 1
  • P. M. Hall
    • 1
  1. 1.Department of Computer ScienceUniversity of BathBathU.K.

Personalised recommendations