A Selective Attention Computational Model for Perceiving Textures

  • Woobeom Lee
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5264)

Abstract

This paper presents a biologically-inspired method of perceiving textures from various texture images. Our approach is motivated by a computational model of neuron cells found in the cerebral visual cortex. An unsupervised learning schemes of SOM(: Self-Organizing Map) is used for the block-based textures clustering, plus a selective attention computational model tuning to the response frequency properties of texture is used for perceiving any texture from the clustered texture. To evaluate the effectiveness of the proposed method, various texture images were built, and the quality of the perceived TROI(: Texture Region Of Interest) was measured according to the discrepancies. Our experimental results demonstrated a very successful performance.

Keywords

A selective attention Cerebral visual cortex Texture peception Self-organizing net Gabor scheme 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Manthalkar, R., et al.: Rotation invarient texture classification using even symmetric Gabor filters. Pattern Recognition Letters 24, 2061–2068 (2003)CrossRefGoogle Scholar
  2. 2.
    Idrissa, M., Acheroy, M.: Texture classification using Gabor filters. Pattern Recognition Letters 23, 1095–1102 (2002)MATHCrossRefGoogle Scholar
  3. 3.
    Tsai, D., et al.: Optimal Gabor filter design for texture segmentation using stochastic optimazation. Image and Vision Computing 19, 299–316 (2001)CrossRefGoogle Scholar
  4. 4.
    Clausi, D.A., Jernigan, M.: Designing Gabor filters for optimal texture seperability. Pattern Recognition 33, 1835–1849 (2000)CrossRefGoogle Scholar
  5. 5.
    Lee, W.B., Kim, W.H.: Texture Segmentation by Unsupervised Learning and Histogram Analysis using Boundary Tracing. In: Yue, H., et al. (eds.) CIS 2005. LNCS (LNAI), vol. 3801, pp. 25–32. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  6. 6.
    Bovik, A.C., Clark, M., Geisler, W.S.: Multichannel texuture analysis using localized spatial filter. IEEE Trans. PAMI 12 (1), 55–73 (1990)Google Scholar
  7. 7.
    Marr, D.: Vision: A computational investigation into the human representation and processing of visual information. W. H. Freedom & Company (1982)Google Scholar
  8. 8.
    Kohonen, T.: The self-organizing map. Proc. IEEE 78 (9), 1464–1480 (1990)CrossRefGoogle Scholar
  9. 9.
    Lippmann, R.P.: An introduction to computing with neural nets. IEEE ASSP Magagine 4, 4–22 (1987)CrossRefGoogle Scholar
  10. 10.
    Brodatz, P.: Texture: A photographic album for artists and designer. Dover Publication (1966)Google Scholar
  11. 11.
    Zhang, Y.J.: A survey on evaluation methods for image segmentation. Pattern Recognition 29 (8), 1335–1346 (1996)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Woobeom Lee
    • 1
  1. 1.School of Computer&Information EngineeringSangji UniversityRepublic of Korea

Personalised recommendations