Advertisement

International Journal of Computer Vision

, Volume 75, Issue 2, pp 231–246 | Cite as

Self-Invertible 2D Log-Gabor Wavelets

  • Sylvain Fischer
  • Filip Šroubek
  • Laurent Perrinet
  • Rafael Redondo
  • Gabriel Cristóbal
Article

Abstract

Orthogonal and biorthogonal wavelets became very popular image processing tools but exhibit major drawbacks, namely a poor resolution in orientation and the lack of translation invariance due to aliasing between subbands. Alternative multiresolution transforms which specifically solve these drawbacks have been proposed. These transforms are generally overcomplete and consequently offer large degrees of freedom in their design. At the same time their optimization gets a challenging task. We propose here the construction of log-Gabor wavelet transforms which allow exact reconstruction and strengthen the excellent mathematical properties of the Gabor filters. Two major improvements on the previous Gabor wavelet schemes are proposed: first the highest frequency bands are covered by narrowly localized oriented filters. Secondly, the set of filters cover uniformly the Fourier domain including the highest and lowest frequencies and thus exact reconstruction is achieved using the same filters in both the direct and the inverse transforms (which means that the transform is self-invertible). The present transform not only achieves important mathematical properties, it also follows as much as possible the knowledge on the receptive field properties of the simple cells of the Primary Visual Cortex (V1) and on the statistics of natural images. Compared to the state of the art, the log-Gabor wavelets show excellent ability to segregate the image information (e.g. the contrast edges) from spatially incoherent Gaussian noise by hard thresholding, and then to represent image features through a reduced set of large magnitude coefficients. Such characteristics make the transform a promising tool for processing natural images.

Keywords

wavelet transforms log-Gabor filters oriented high-pass filters image denoising visual system 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Carandini, M., Demb, J.B., Mante, V., Tolhurst, D.J., Dan, Y., Olshausen, B.A., Gallant, J.L. and Rust, N.C. 2005. Do we know what the early visual system does? J Neurosci, 25(46):10577–10597.CrossRefGoogle Scholar
  2. Chang, S.G., Yu, B. and Vetterli, M. 2000. Adaptive wavelet thresholding for image denoising and compression. IEEE Trans. on Image Proc., 9(9):1532–1546.zbMATHCrossRefMathSciNetGoogle Scholar
  3. Chang, S.G., Yu, B. and Vetterli, M. 2000. Spatially adaptive wavelet thresholding with context modeling for image denoising. IEEE Trans. on Image Processing, 9(9):1522–1531.zbMATHCrossRefMathSciNetGoogle Scholar
  4. Christiansen, O. 2002. Time-Frequency Analysis and its Applications in Denoising. PhD thesis, Department of Informatics, University of Bergen, Norway.Google Scholar
  5. Clausi, D.A. and Jernigan, M.E. 2000. Designing Gabor filters for optimal texture separability. Pattern Recognition, 33:1835–1849.CrossRefGoogle Scholar
  6. Coifman, R.R. and Donoho, D. 1995. Translation-invariant de-noising. In Wavelets and Statistics, Lecture Notes in Statistics 103, Springer Verlag: NY. A. Antoniadis and G. Oppenheim (eds), pp. 125–150.Google Scholar
  7. Cristóbal, G. and Navarro, R. 1994. Space and frequency variant image enhancement based on a Gabor representation. Patt. Rec. Letters, 15(3):273–277.zbMATHCrossRefGoogle Scholar
  8. Daubechies, I. 1992. Ten Lectures on Wavelets. SIAM, Philadelphia: PA.zbMATHGoogle Scholar
  9. Daugman, J. 1985. Uncertainty relation for resolution in space, spatial frequency and orientation optimized by two-dimensional visual cortical filters. J. Opt. Soc. Am. A, 2(7):1160–1169.Google Scholar
  10. Daugman, J. 1988. Complete discrete 2-D Gabor transforms by neural networks for image analysis and compression. IEEE Trans. Acoust. Speech Signal Proc., 36(7):1169–1179.zbMATHCrossRefGoogle Scholar
  11. DeValois, R.L., Albrecht, D.G. and Thorell, L.G. 1982. Spatial frequency selectivity of cells in macaque visual cortex. Vision Res., 22:545–559.CrossRefGoogle Scholar
  12. Do, M.N. and Vetterli, M. 2005. The contourlet transform: An efficient directional multiresolution image representation. IEEE Trans. on Image Proc., 14(12):2091–2106.CrossRefMathSciNetGoogle Scholar
  13. Doi, E. and Lewicki, M.S. 2005. Relations between the statistical regularities of natural images and the response properties of the early visual system. Japanese Cognitive Science Society, SIG P&P, pp. 1–8.Google Scholar
  14. Donoho, D. 1995. De-noising by soft-thresholding. IEEE Trans. Inf. Theory, 41(3):613–627.zbMATHCrossRefMathSciNetGoogle Scholar
  15. Field, D.J. 1987. Relation between the statistics of natural images and the response properties of cortical cells. J. Opt. Soc. Am. A, 4(12):2379–2394.Google Scholar
  16. Fischer, S., Cristóbal, G. and Redondo, R. 2006. Sparse overcomplete Gabor wavelet representation based on local competitions. IEEE Trans. on Image Proc., 15(2):265–272.CrossRefGoogle Scholar
  17. Fischer, S., Redondo, R. and Cristóbal, G. 2005. Sparse edge coding using overcomplete Gabor wavelets. In IEEE Int. Conf. on Image Proc., vol. 1, pp. 85–88.CrossRefGoogle Scholar
  18. Fischer, S., Redondo, R., Perrinet, L. and Cristóbal, G. 2005. Sparse Gabor wavelets by local operations. In Proc. SPIE, Bioengineered and Bioinspired Systems II, G. Linan-Cembrano; R.A. Carmona (eds), Vol. 5839, pp. 75–86.Google Scholar
  19. Fischer, S., Redondo, R., Perrinet, L. and Cristóbal, G. Sparse approximation of images inspired from the functional architecture of the primary visual areas. EURASIP JASP, special issue on Image Perception in press.Google Scholar
  20. Gabor, D. 1946. Theory of communication. J. Inst. Electr. Eng., 93:429–457.Google Scholar
  21. Grigorescu, C., Petkov, N. and Westenberg, M.A. 2003. Contour detection based on nonclassical receptive field inhibition. IEEE Trans. on Image Proc., 12(7):729–739.CrossRefGoogle Scholar
  22. Gross, M.H. and Koch, R. 1995. Visualization of multidimensional shape and texture features in laser range data using complex-valued Gabor wavelets. IEEE Trans. Visual. and Comput. Graphics, 1(1):44–59.CrossRefGoogle Scholar
  23. Hamza, A.B., Krim, H. and Unal, G. 2002. Unifying probabilistic and variational estimation. IEEE Signal Proc., 19(5):37–47.CrossRefGoogle Scholar
  24. Heitger, F., Von der Heydt, R., Peterhans, E., Rosenthaler, L. and Kubler, O. 1998. Simulation of neural contour mechanisms: Representing anomalous contours. Image and Vision Computing, 16:409–423.CrossRefGoogle Scholar
  25. Hubel, D. 1988. Eye, Brain and Vision. WH Freeman: Sc. Am. Lib. Series, New York.Google Scholar
  26. Kingsbury, N.G. 2001. Complex wavelets for shift invariant analysis and filtering of signals. Jour. of Applied and Comput. Harmonic Analysis, 10(3):234–253.zbMATHCrossRefMathSciNetGoogle Scholar
  27. Kovesi, P. 1999. Phase preserving denoising of images. In Australian Patt. Recog. Soc. Conf. DICTA. Perth WA., pp. 212–217.Google Scholar
  28. Kovesi, P. 2003. Phase congruency detects corners and edges. In Australian Patt. Recog. Soc. Conf. DICTA. Sydney WA., pp. 309–318.Google Scholar
  29. Krüger, V. 2001. Gabor Wavelet Networks for Object Representation. PhD thesis, Christian-Albrechts-University Kiel, Technical Faculty.Google Scholar
  30. Lee, T.S. 1996. Image representation using 2D Gabor wavelets. IEEE Trans. Pattern Anal. Mach. Intell., 18(10):959–971.CrossRefGoogle Scholar
  31. Li, X. and Orchard, M.T. 2000. Spatially adaptive image denoising under overcomplete expansion. In Int. Conf. on Image Proc., Vol. 3, pp. 300–303.Google Scholar
  32. Marcelja, S. 1980. Mathematical description of the responses of simple cortical cells. J. Opt. Soc. Am. A, 70(11):1297–1300.CrossRefMathSciNetGoogle Scholar
  33. Mingolla, E., Ross, W. and Grossberg, S. 1999. A neural network for enhancing boundaries and surfaces in synthetic aperture radar images. Neural Networks, 12(3):499–511.CrossRefGoogle Scholar
  34. Morlet, J., Arens, G., Fourgeau, E. and Girard, D. 1982. Wave propagation and sampling theory. Geophysics, 47:203–236.CrossRefGoogle Scholar
  35. Nestares, O., Navarro, R., Portilla, J. and Tabernero, A. 1998. Efficient spatial-domain implementation of a multiscale image representation based on Gabor functions. Jour. of Eletr. Imag., 7(1):166–173.CrossRefGoogle Scholar
  36. Olshausen, B. and Field, D.J. 1996. Wavelet-like receptive fields emerge from a network that learns sparse codes for natural images. Nature, 381:607–609.CrossRefGoogle Scholar
  37. Perrinet, L. 2004. Feature detection using spikes: The greedy approach. J. Physiology (Paris), 98(4–6):530–539.CrossRefGoogle Scholar
  38. Perrinet, L., Samuelides, M. and Thorpe, S. 2004. Coding static natural images using spiking event times: Do neurons cooperate? IEEE Trans. on Neural Networks, 15(5):1164–1175.CrossRefGoogle Scholar
  39. Pollen, D.A. and Ronner, S.F. 1981. Phase relationships between adjacent simple cells in the visual cortex. Science, 212:1409–1411.CrossRefGoogle Scholar
  40. Portilla, J., Navarro, R., Nestares, O. and Tabernero, A. 1996. Texture synthesis-by-analysis based on a multiscale early-vision model. Opt. Eng., 35(8):1–15.CrossRefGoogle Scholar
  41. Portilla, J. and Simoncelli, E.P. 2000. A parametric texture model based on joint statistics of complex wavelet coefficients. Int. Jour. Comp. Vis., 40(1):49–70.zbMATHCrossRefGoogle Scholar
  42. Portilla, J., Strela, V., Wainwright, M. and Simoncelli, E. 2003. Image denoising using scale mixtures of Gaussians in the wavelet domain. IEEE Trans. Image Proc., 12(11):1338–1351.CrossRefMathSciNetGoogle Scholar
  43. Pötzsch, M., Krüger, N. and Malsburg, C. 1996. Improving object recognition by transforming Gabor filter responses. Network: Computation in Neural Systems, 7(2):341–347.CrossRefGoogle Scholar
  44. Redondo, R., Fischer, S., Perrinet, L. and Cristóbal, G. 2005. Modeling of simple cells through a sparse overcomplete Gabor wavelet representation based on local inhibition and facilitation. In European Conf. On Visual Perception, A Coruña, Spain.Google Scholar
  45. Redondo, R., Sroubek, F., Fischer, S. and Cristóbal, G. in press. A multiresolution-based fusion scheme through log-Gabor wavelets and a multisize windows technique. Information Fusion. Google Scholar
  46. Ro, Y.M., Kim, M., Kang, H.K., Manjunath, B.S. and Kim, J. 2001. MPEG-7 homogeneous texture descriptor. ETRI Journal, 23(2):41–51.Google Scholar
  47. Simoncelli, E.P., Freeman, W.T. and Heeger, D.J. 1992. Shiftable multiscale transforms. IEEE Trans. Inf. Theory, 38(2):587–607.CrossRefMathSciNetGoogle Scholar
  48. Sroubek, F. and Flusser, J. 2003. Multichannel blind iterative image restoration. IEEE Trans. Image Proc., 12(9):1094–1106.CrossRefMathSciNetGoogle Scholar
  49. Starck, J.L., Candès, E.J. and Donoho, D.L. 2002. The curvelet transform for image denoising. IEEE Trans. on Image Proc., 11(6):670–684.CrossRefGoogle Scholar
  50. Taswell, C. 2000. The what, how and why of wavelet shrinkage denoising. Computing in Science and Engineering, pp. 12–19.Google Scholar
  51. Tschumperlé, D. and Deriche, R. 2005. Vector-valued image regularization with PDE's: A common framework for different applications. IEEE Trans. on Pattern Analysis and Machine Intelligence, 27(4):506–517.CrossRefGoogle Scholar
  52. Wurtz, R. 1994. Multilayer Dynamic Link Networks for Establishing Image Point Correspondences and Visual Object Recognition. PhD thesis, Bochum University.Google Scholar
  53. Zhong, S. and Cherkassky, V. 2000. Image denoising using wavelet thresholding and model selection. In Int. Conf. on Image Proc., Vol. 3, pp. 262–265.Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2006

Authors and Affiliations

  • Sylvain Fischer
    • 1
    • 2
  • Filip Šroubek
    • 3
    • 4
  • Laurent Perrinet
    • 5
  • Rafael Redondo
    • 6
  • Gabriel Cristóbal
    • 6
  1. 1.Instituto de OpticaCSICMadridSpain
  2. 2.INCM, UMR6193CNRS & Aix-Marseille UniversityMarseille Cedex 20France
  3. 3.Instituto de OpticaCSICMadridSpain
  4. 4.Academy of SciencesPragueCzech Republic
  5. 5.INCM, UMR6193CNRS & Aix-Marseille UniversityMarseille Cedex 20France
  6. 6.Instituto de OpticaCSICMadridSpain

Personalised recommendations