Automatic Estimation for Parameters of Image Projective Transforms Based on Object-Invariant Cores

  • Vadim Lutsiv
Part of the Intelligent Systems Reference Library book series (ISRL, volume 73)


A lot of efforts were addressed to developing the affine-invariant image descriptions. At the same time, development of projective-invariant sets of features still remains the open problem. An opposite approach to automatic recognition of images with geometric transforms is proposed in this chapter. The images are transformed to object-invariant form, in which all generic-specific features are suppressed while the parameters of geometric transform are still preserved. Then the parameters of geometric transform of image are estimated by means of comparison of its object-invariant description with a template form common for all classes of objects. The estimated geometric transforms can be then compensated, and the image can be recognized by any pattern recognition techniques. The presented theoretical development is also proven by computer simulation, and the reached theoretical results are compared with the ones reached by other authors. Several examples of practical application of developed theory are also presented.


Image recognition Affine transform Projective transform Transformation parameters Object-invariant core 



This work was partially financially supported by the Government of Russian Federation, Grant 074-U01.


  1. 1.
    Shapiro LG, Stockman GC (2001) Computer vision. Prentice Hall, Upper Saddle RiverGoogle Scholar
  2. 2.
    Haralick RM (1974) A measure of circularity of digital figures. IEEE Trans Syst Man Cybern SMC-4:394–396Google Scholar
  3. 3.
    Casasent DP, Barnard E (1990) Adaptive clustering optical neural net. Appl Opt 29(17):2603–2615CrossRefGoogle Scholar
  4. 4.
    Casasent D, Psaltis D (1978) Deformation-invariant, space-variant optical pattern recognition. Prog Opt XVI:291–356Google Scholar
  5. 5.
    Qin-sheng C, Defrise M, Deconinck F (1994) Symmetric phase-only matched filtering of Fourier-Mellin transforms for image registration and recognition. IEEE Trans Pattern Anal Mach Intell 16(12):1156–1167CrossRefGoogle Scholar
  6. 6.
    Maitra S (1979) Moment invariants. Proc IEEE 67(4):697–699CrossRefGoogle Scholar
  7. 7.
    Freeman H (1974) Computer processing of line drawing images. Comput Surv 6:57–97CrossRefMATHGoogle Scholar
  8. 8.
    Gonzalez RC, Woods RE (2002) Digital image processing. Prentice Hall, Upper Saddle RiverGoogle Scholar
  9. 9.
    Ling H, Jacobs D (2007) Shape classification using the inner distance. IEEE Trans Pattern Anal Mach Intell 29(2):286–299CrossRefGoogle Scholar
  10. 10.
    Lowe DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60(2):91–110CrossRefGoogle Scholar
  11. 11.
    Morel JM, Yu G (2009) ASIFT: a new framework for fully affine invariant image comparison. SIAM J Imaging Sci 2(2):438–469CrossRefMathSciNetMATHGoogle Scholar
  12. 12.
    Murillo AS, Guerrero JJ, Sagüés C (2007) SURF features for efficient robot localization with omnidirectional images. In: IEEE international conference on robotics and automation, pp 3901–3907Google Scholar
  13. 13.
    Averkin AV, Potapov AS, Lutsev VR (2010) Construction of systems of local invariant image indicators based on the Fourier-Mellin transform. J Opt Technol 77(1):28–32CrossRefGoogle Scholar
  14. 14.
    Viola P, Jones MJ (2001) Rapid object detection using a boosted cascade of simple features. In: Proceedings of IEEE computer vision and pattern recognition conference, pp I-501–I-518Google Scholar
  15. 15.
    Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: IEEE conference on computer vision and pattern recognition, pp 886–893Google Scholar
  16. 16.
    Felzenszwalb PF, Girshick RB, McAllester D, Ramanan D (2010) Object detection with discriminatively trained part based models. IEEE Trans Pattern Anal Mach Intell 32(9):1627–1645CrossRefGoogle Scholar
  17. 17.
    Lutsiv VR, Malyshev IA, Pepelka VA, Potapov AS (2002) The target independent algorithms for description and structural matching of aerospace photographs. SPIE Proc 4741:351–362CrossRefGoogle Scholar
  18. 18.
    Lutsiv VR, Malyshev IA, Potapov AS (2003) Hierarchical structural matching algorithms for registration of aerospace images. SPIE Proc 5238:164–175CrossRefGoogle Scholar
  19. 19.
    Lutsiv V, Potapov A, Novikova T, Lapina N (2005) Hierarchical 3D structural matching in the aerospace photographs and indoor scenes. SPIE Proc 5807:455–466CrossRefGoogle Scholar
  20. 20.
    Lutsiv V (1985) Methods and tools of control of industrial equipment on the base of video-information. Ph.D. thesis, Institute of Aircraft Instrumentation (in Russian)Google Scholar
  21. 21.
    Lutsiv V, Malyshev I (2013) Image structural analysis in the tasks of automatic navigation of unmanned vehicles and inspection of earth surface. Proc SPIE 8897. doi: 10.1117/12.2028840
  22. 22.
    Marr D (1982) Vision: a computational investigation into the human representation and processing of visual information. W.H. Freeman and Co., New YorkGoogle Scholar
  23. 23.
    Erosh IL (1984) The tasks of pattern recognition in robot systems. In: Problems and prospects of optical image processing methods. Physic-technical Institute of Soviet Academy of Sciences (in Russian), pp 75–78Google Scholar
  24. 24.
    Erosh IL (1981) Application of Krestenson transform for determination of object position parameters from plain projections. Eng Cybern 3:46–52 (in Russian)Google Scholar
  25. 25.
    Lutsiv V (2012) An object-independent approach to image structural analysis. DPhil thesis, Saint Petersburg University of Aerospace Instrumentation, Russia (in Russian)Google Scholar
  26. 26.
    Lutsiv V (2009) Method of iteratively compensating projective image distortions. J Opt Technol 76(7):417–422CrossRefGoogle Scholar
  27. 27.
    Lutciv VR, Dolinov DS, Zherebko AK, Novikova TA (1997) Using artificial neural networks in image processing problems. J Opt Technol 64(2):112–118Google Scholar
  28. 28.
    Lutsiv V, Malyshev I, Novikova T (2004) Hierarchical approaches to analysis of natural textures. SPIE Proc 5426:144–154CrossRefGoogle Scholar
  29. 29.
    Lutsiv VR (2007) The application of generalized reference functions in natural and artificial visual systems. J Opt Technol 74(11):759–763CrossRefGoogle Scholar
  30. 30.
    Lutsiv VR (2008) Object-independent approach to the structural analysis of images. J Opt Technol 75(11):708–714CrossRefGoogle Scholar
  31. 31.
    Lutsiv VR (2007) Modelling the attention zones in problems involving the automatic decomposition and structural analysis of images. J Opt Technol 74(4):274–281CrossRefGoogle Scholar
  32. 32.
    Lutsiv VR, Novikova TA (2008) Modeling attention zones on the basis of an analysis of local features of the image texture. J Opt Technol 75(7):449–456CrossRefGoogle Scholar
  33. 33.
    Bradski R (1998) Computer vision face tracking for use in perceptual user interface. Intel Technology J Q2’98:706–740Google Scholar
  34. 34.
    Freeman WT, Tanaka K, Ohta J, Kyuma K (1996) Computer vision for computer games. In: 2nd International conference on automatic face and gesture recognition, pp 100–105Google Scholar
  35. 35.
    Jähne B (2005) Digital image processing. Springer, Berlin-HeidelbergGoogle Scholar
  36. 36.
    Baumberg A (2000) Reliable feature matching across widely separated views. In: IEEE conference on computer vision and pattern recognition, vol 1, pp 774–781Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.Vavilov State Optical InstituteSt. PetersburgRussian Federation
  2. 2.National Research University of Information Technologies, Mechanics and OpticsSt. PetersburgRussian Federation

Personalised recommendations