Advertisement

Features Invariant Simultaneously to Convolution and Affine Transformation

  • Tomáš Suk
  • Jan Flusser
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2124)

Abstract

The contribution is devoted to the recognition of objects and patterns deformed by imaging geometry as well as by unknown blurring. We introduce a new class of features invariant simultaneously to blurring with a centrosymmetric PSF and to affine transformation. As we prove in the contribution, they can be constructed by combining affine moment invariants and blur invariants derived earlier. Combined invariants allow to recognize objects in the degraded scene without any restoration.

Keywords

pattern recognition image invariants 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Mundy, J.L., Zisserman, A.: Geometric Invariance in Computer Vision. MIT Press (1992)Google Scholar
  2. 2.
    Reiss, T.H.: Recognizing Planar Objects using Invariant Image Features. Lecture Notes in Computer Science, Vol. 676. Springer, Berlin (1993)zbMATHGoogle Scholar
  3. 3.
    Hu, M.K.: Visual pattern recognition by moment invariants. IRE Trans. Information Theory, 8 (1962) 179–187Google Scholar
  4. 4.
    Belkasim, S.O., Shridhar, M., Ahmadi, M.: Pattern recognition with moment invariants: a comparative study and new results. Pattern Recognition, 24 (1991) 1117–1138CrossRefGoogle Scholar
  5. 5.
    Arbter, K., Snyder, W.E., Burkhardt, H., Hirzinger, G.: Application of affine-invariant Fourier descriptors to recognition of 3-D objects. IEEE Trans. Pattern Analysis and Machine Intelligence, 12 (1990) 640–647CrossRefGoogle Scholar
  6. 6.
    Weiss, I.: Projective invariants of shapes. In: Proc. Image Understanding Workshop. Cambridge, Mass. (1988) 1125–1134Google Scholar
  7. 7.
    Suk, T., Flusser, J.: Vertex-based features for recognition of projectively deformed polygons. Pattern Recognition, 29 (1996) 361–367CrossRefGoogle Scholar
  8. 8.
    Lenz, R., Meer, P.: Point configuration invariants under simultaneous projective and permutation transformations. Pattern Recognition, 27 (1994) 1523–1532CrossRefGoogle Scholar
  9. 9.
    van Gool, L., Moons, T., Ungureanu, D.: Affine/photometric invariants for planar intensity patterns. In: Proc. 4th ECCV’96, LNCS Vol. 1064. Springer (1996) 642–651Google Scholar
  10. 10.
    Mindru, F., Moons, T., van Gool, L.: Recognizing color patterns irrespective of viewpoint and illumination. In: Proc. IEEE Conf. Computer Vision Pattern Recognition CVPR’99, Vol. 1 (1999) 368–373Google Scholar
  11. 11.
    Schmid, C., Mohr, R.: Local grayvalue invariants for image retrieval. IEEE Trans. Pattern Analysis and Machine Intelligence, 19 (1997) 530–535CrossRefGoogle Scholar
  12. 12.
    Flusser, J., Suk, T.: Degraded image analysis: An invariant approach. IEEE Trans. Pattern Analysis and Machine Intelligence, 20 (1998) 590–603CrossRefGoogle Scholar
  13. 13.
    Flusser, J., Suk, T., Saic, S.: Recognition of blurred images by the method of moments. IEEE Transactions on Image Processing, 5 (1996) 533–538CrossRefGoogle Scholar
  14. 14.
    Zhang, Y., Wen, C., Zhang, Y.: Estimation of motion parameters from blurred images. Pattern Recognition Letters, 21 (2000) 425–433CrossRefMathSciNetGoogle Scholar
  15. 15.
    Lu, J., Yoshida, Y.: Blurred image recognition based on phase invariants. IEICE Trans. Fundamentals of El. Comm. and Comp. Sci., E82A (1999) 1450–1455Google Scholar
  16. 16.
    Zhang, Y., Zhang, Y., Wen, C.: A new focus measure method using moments. Image and Vision Computing, 18 (2000) 959–965CrossRefGoogle Scholar
  17. 17.
    Flusser, J., Suk, T., Saic, S.: Image features invariant with respect to blur. Pattern Recognition, 28 (1995) 1723–1732CrossRefGoogle Scholar
  18. 18.
    Flusser, J., Suk, T., Saic, S.: Recognition of images degraded by linear motion blur without restoration. Computing Suppl., 11 (1996) 37–51MathSciNetGoogle Scholar
  19. 19.
    Flusser, J., Zitová, B.: Combined invariants to linear filtering and rotation. Intl. J. Pattern Recognition Art. Intell., 13 (1999) 1123–1136CrossRefGoogle Scholar
  20. 20.
    Flusser, J., Zitová, B., Suk, T.: Invariant-based registration of rotated and blurred images. In: Tammy, I.S. (ed.): IEEE 1999 International Geoscience and Remote Sensing Symposium. Proceedings. IEEE Computer Society, Los Alamitos (June 1999) 1262–1264Google Scholar
  21. 21.
    Reiss, T.H.: The revised fundamental theorem of moment invariants. IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 13 (1991) 830–834CrossRefGoogle Scholar
  22. 22.
    Flusser, J., Suk, T.: Pattern recognition by affine moment invariants. Pattern Recognition, 26 (1993) 167–174CrossRefMathSciNetGoogle Scholar
  23. 23.
    Schur, I.: Vorlesungen über Invariantentheorie. Springer, Berlin (1968)zbMATHGoogle Scholar
  24. 24.
    Gurevich, G.B.: Foundations of the Theory of Algebraic Invariants. Nordhoff, Groningen, The Netherlands (1964)zbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2001

Authors and Affiliations

  • Tomáš Suk
    • 1
  • Jan Flusser
    • 1
  1. 1.Institute of Information Theory and AutomationAcademy of Sciences of the Czech RepublicPraha 8Czech Republic

Personalised recommendations