Basic Image Features (BIFs) Arising from Approximate Symmetry Type

  • Lewis D. Griffin
  • Martin Lillholm
  • Mike Crosier
  • Justus van Sande
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5567)

Abstract

We consider detection of local image symmetry using linear filters. We prove a simple criterion for determining if a filter is sensitive to a group of symmetries. We show that derivative-of-Gaussian (DtG) filters are excellent at detecting local image symmetry. Building on this, we propose a very simple algorithm that, based on the responses of a bank of six DtG filters, classifies each location of an image into one of seven Basic Image Features (BIFs). This effectively and efficiently realizes Marr’s proposal for an image primal sketch. We summarize results on the use of BIFs for texture classification, object category detection, and pixel classification.

Keywords

Gaussian Derivatives Hermite Transform Group Theory 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Liu, Y.X., Collins, R.T., Tsin, Y.H.: A computational model for periodic pattern perception based on frieze and wallpaper groups. IEEE Transactions on Pattern Analysis and Machine Intelligence 26(3), 354–371 (2004)CrossRefGoogle Scholar
  2. 2.
    Scognamillo, R., et al.: A feature-based model of symmetry detection. Proceedings of the Royal Society of London Series B-Biological Sciences 270(1525), 1727–1733 (2003)CrossRefGoogle Scholar
  3. 3.
    Mellor, M., Brady, M.: A new technique for local symmetry estimation. In: Kimmel, R., Sochen, N.A., Weickert, J. (eds.) Scale-Space 2005. LNCS, vol. 3459, pp. 38–49. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  4. 4.
    Bonneh, Y., Reisfeld, D., Yeshurun, Y.: Quantification of local symmetry - application to texture-discrimination. Spatial Vision 8(4), 515–530 (1994)CrossRefGoogle Scholar
  5. 5.
    Mancini, S., Sally, S.L., Gurnsey, R.: Detection of symmetry and anti-symmetry. Vision Research 45(16), 2145–2160 (2005)CrossRefGoogle Scholar
  6. 6.
    Baylis, G.C., Driver, J.: Perception of symmetry and repetition within and across visual shapes: Part-descriptions and object-based attention. Visual Cognition 8(2), 163–196 (2001)CrossRefGoogle Scholar
  7. 7.
    Marr, D.: Vision. W H Freeman & co., New York (1982)Google Scholar
  8. 8.
    Griffin, L.D.: Symmetries of 1-D Images. Journal of Mathematical Imaging and Vision 31(2-3), 157–164 (2008)MathSciNetCrossRefGoogle Scholar
  9. 9.
    Crosier, M., Griffin, L.D.: Texture classification with a dictionary of basic image features. In: CVPR 2008. IEEE, Los Alamitos (2008)Google Scholar
  10. 10.
    Lillholm, M., Griffin, L.D.: Statistics and category systems for the shape index descriptor of local image. Image and Vision Computing (in press) (2008)Google Scholar
  11. 11.
    Lillholm, M., Griffin, L.D.: Novel image feature alphabets for object recognition. In: ICPR 2008 (2008)Google Scholar
  12. 12.
    Griffin, L.D.: Symmetries of 2D images: cases without periodic translation. Journal of Mathematical Imaging and Vision (in press)Google Scholar
  13. 13.
    Griffin, L.D.: The 2nd order local-image-structure solid. IEEE Transactions on Pattern Analysis and Machine Intelligence 29(8), 1355–1366 (2007)CrossRefGoogle Scholar
  14. 14.
    Griffin, L.D., Lillholm, M.: Symmetry-sensitivity of derivative of gaussian filters. IEEE Transactions on Pattern Analysis and Machine Intelligence (in press)Google Scholar
  15. 15.
    Bieberbach, L.: Über die bewegungsgruppen der euklidischen raume I. Mathematische Annalen 70, 297 (1911)MathSciNetCrossRefMATHGoogle Scholar
  16. 16.
    Conway, J.H., et al.: On three-dimensional space groups. Contributions to Algebra and Geometry 42(2), 475–507 (2001)MathSciNetMATHGoogle Scholar
  17. 17.
    Grünbaum, B., Shephard, G.C.: Tilings and Patterns. WH Freeman & co., New York (1987)MATHGoogle Scholar
  18. 18.
    Schattschneider, D.: MC Escher. Visions of Symmetry. Plenum Press (1990)Google Scholar
  19. 19.
    Holser, W.T.: Classification of symmetry groups. Acta Crystallographica 14, 1236–1242 (1961)CrossRefGoogle Scholar
  20. 20.
    Loeb, A.A.: Color and Symmetry. Robert E. Krieger (1978)Google Scholar
  21. 21.
    Klein, F.: A comparative review of recent researches in geometry (trans. by MW Haskell). Bulletin of the New York Mathematical Society 2, 215–249 (1892)CrossRefGoogle Scholar
  22. 22.
    Koenderink, J.J., van Doorn, A.J.: Image processing done right. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2350, pp. 158–172. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  23. 23.
    Cayley, A.: Sixth memoir upon the quantics. Philosophical Transactions of the Royal Society 149, 61–70 (1859)CrossRefGoogle Scholar
  24. 24.
    Koenderink, J.J., van Doorn, A.J.: Generic Neighborhood Operators. IEEE Transactions on Pattern Analysis and Machine Intelligence 14(6), 597–605 (1992)CrossRefGoogle Scholar
  25. 25.
    Varma, M., Zisserman, A.: Texture classification: are filter banks necessary? In: CVPR 2003. IEEE, Los Alamitos (2003)Google Scholar
  26. 26.
    Varma, M., Zisserman, A.: A statistical approach to texture classification from single images. International Journal of Computer Vision 62(1), 61–81 (2005)CrossRefGoogle Scholar
  27. 27.
    Hayman, E., et al.: On the signifigance of real-world conditions for material classification. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3024, pp. 253–266. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  28. 28.
    Zhang, J., et al.: Local features and kernels for classification of texture and object categories: a comprehensive study. In: CVPR 2006 (2006)Google Scholar
  29. 29.
    Perronnin, F., et al.: Adapted vocabularies for generic visual categorization. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3954, pp. 464–475. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  30. 30.
    Varma, M., Zisserman, A.: Unifying Statistical Texture Classification Frameworks. Image and Vision Computing (in press) (2005)Google Scholar
  31. 31.
    Cula, O.G., Dana, K.J.: Compact representation of bidirectional texture functions. In: CVPR 2001. IEEE, Los Alamitos (2001)Google Scholar
  32. 32.
    Lazebnik, S.C., Schmid, C., Ponce, J.: A spare texture representation using local affine regions. IEEE Transactions on Pattern Analysis and Machine Intelligence 27(8), 1265–1278 (2005)CrossRefGoogle Scholar
  33. 33.
    Csurka, G., et al.: Visual categorization with a bag of keypoints. In: ECCV 2004, pp. 1–22 (2004)Google Scholar
  34. 34.
    Lowe, D.G.: Towards a computational model for object recognition in IT cortex. In: Biologically Motivated Computer Vision, Proceeding, pp. 20–31 (2000)Google Scholar
  35. 35.
    Lowe, D.G.: Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision 60(2), 91–110 (2004)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Lewis D. Griffin
    • 1
  • Martin Lillholm
    • 1
  • Mike Crosier
    • 1
  • Justus van Sande
    • 2
  1. 1.Computer ScienceUniversity College LondonLondonUK
  2. 2.Biomedical EngineeringEindhoven University of TechnologyThe Netherlands

Personalised recommendations