Object Recognition Using Frequency Domain Blur Invariant Features

  • Ville Ojansivu
  • Janne Heikkilä
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4522)


In this paper, we propose novel blur invariant features for the recognition of objects in images. The features are computed either using the phase-only spectrum or bispectrum of the images and are invariant to centrally symmetric blur, such as linear motion or defocus blur as well as linear illumination changes. The features based on the bispectrum are also invariant to translation, and according to our knowledge they are the only combined blur-translation invariants in the frequency domain. We have compared our features to the blur invariants based on image moments in simulated and real experiments. The results show that our features can recognize blurred images better and, in a practical situation, they are faster to compute using FFT.


Object Recognition Discrete Fourier Transform Point Spread Function Motion Blur Moment Invariant 
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.


  1. 1.
    Wood, J.: Invariant pattern recognition: A review. Pattern Recognition 29, 1–17 (1996)CrossRefGoogle Scholar
  2. 2.
    Banham, M.R., Katsaggelos, A.K.: Digital image restoration. IEEE Signal Processing Magazine 14(2), 24–41 (1997)CrossRefGoogle Scholar
  3. 3.
    Kundur, D., Hatzinakos, D.: Blind image deconvolution. IEEE Signal Processing Magazine 13(3), 43–64 (1996)CrossRefGoogle Scholar
  4. 4.
    Flusser, J., Suk, T.: Degraded image analysis: An invariant approach. IEEE Trans. Pattern Anal. Machine Intell. 20, 590–603 (1998)CrossRefGoogle Scholar
  5. 5.
    Flusser, J., Suk, T., Saic, S.: Recognition of blurred images by the method of moments. IEEE Transactions on Image Processing 5(3), 533–538 (1996)CrossRefGoogle Scholar
  6. 6.
    Bentoutou, Y., Taleb, N., Mezouar, M.C.E., Taleb, M., Jetto, L.: An invariant approach for image registration in digital subtraction angiography. Pattern Recognition 35, 2853–2865 (2002)zbMATHCrossRefGoogle Scholar
  7. 7.
    Flusser, J., Zitová, B.: Combined invariants to linear filtering and rotation. Int. J. Pattern Recognition and Artificial Intelligence 13(8), 1123–1136 (1999)CrossRefGoogle Scholar
  8. 8.
    Zhang, Y., Wen, C., Zhang, Y., Soh, Y.C.: Determination of blur and affine combined invariants by normalization. Pattern recognition 35(1), 211–221 (2002)zbMATHCrossRefGoogle Scholar
  9. 9.
    Suk, T., Flusser, J.: Combined blur and affine moment invariants and their use in pattern recognition. Pattern Recognition 26(12), 2895–2907 (2003)CrossRefMathSciNetGoogle Scholar
  10. 10.
    Ojansivu, V., Heikkilä, J.: Motion Blur Concealment of Digital Video Using Invariant Features. In: Blanc-Talon, J., Philips, W., Popescu, D., Scheunders, P. (eds.) ACIVS 2006. LNCS, vol. 4179, pp. 35–45. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  11. 11.
    Chandran, V., Carswell, B., Boashash, B., Elgar, S.: Pattern recognition using invariants defined from higher order spectra: 2-d image inputs. IEEE Transactions on Image Processing 6(5), 703–712 (1997)CrossRefGoogle Scholar
  12. 12.
    Dianat, S.A., Rao, R.M.: Fast algorithms for phase and magnitude reconstruction from bispectra. Optical Engineering 29(5), 504–512 (1990)CrossRefGoogle Scholar
  13. 13.
    Petropulu, A.P., Pozidis, H.: Phase reconstruction from bispectrum slices. IEEE Transactions on Signal Processing 46(2), 527–530 (1998)CrossRefGoogle Scholar

Copyright information

© Springer Berlin Heidelberg 2007

Authors and Affiliations

  • Ville Ojansivu
    • 1
  • Janne Heikkilä
    • 1
  1. 1.Machine Vision Group, Department of Electrical and Information Engineering, University of Oulu, PO Box 4500, 90014Finland

Personalised recommendations