Model-based gradient field descriptor as a convenient tool for image recognition and analysis
V.V. Myasnikov

Full text of article: Russian language.

Abstract:
In the paper we propose a new descriptor which is used to describe a digital image, specifically, a model-oriented descriptor of gradient field. Derived characteristics of the descriptor, that are considered as features of a digital image, allow to solve effectively the problems of image analysis, recognition and retrieval. The examples of such tasks solutions with the proposed descriptor are given.

Key words:
digital images, descriptors, features, analysis, recognition, image retrieval.

References:

  1. Schmid, C. Evaluation of interest point detectors / C. Schmid, R. Mohr, C. Bauckhage // Int. Journal of Computer Vision. – 2000. – Vol. 37(2). – P. 151-172.
  2. Mikolajczyk, K. A performance evaluation of local descriptors / K. Mikolajczyk, C. Schmid // IEEE Transactions on Pattern Analysis and Machine Intelligence. – 2005. – Vol. 10(27). – P. 1615-1630.
  3. Dalal, N. Histograms of Oriented Gradients for Human Detection / N. Dalal, B. Triggs // Proceedings of IEEE Conference Computer Vision and Pattern Recognition, San Diego, USA. – 2005. – P. 886-893.
  4. Forsyth, D.A. Computer Vision: A Modern Approach / D.A. Forsyth, J. Ponce. – New Jersey: Prentice Hall, 2002. – 693 p.
  5. Shapiro, L.G. Computer Vision / L.G. Shapiro, G.C. Stockman. – New Jersey: Prentice Hall, 2001. – 608 p.
  6. Methods of computer image processing. / M.V. Gashnikov, N.I. Glumov, N.U. Ilyasova, V.V. Myasnikov [et al]. - 2-nd edition, reviewed. - Moscow.: “Fizmatlit Publisher”, 2003. – 784 p. – (In Russian).
  7. Johnson, A. Object recognition by matching oriented points / A. Johnson, M. Hebert // Proceedings of the Conference on Computer Vision and Pattern Recognition, Puerto Rico, USA. – 1997. – P. 684-689.
  8. Zabih, R. Non-parametric local transforms for computing visual correspondence / R. Zabih, J. Woodfill // Proceedings of the 3rd European Conference on Computer Vision, Stockholm, Sweden. – 1994. – P. 151-158.
  9. Lowe, D. Distinctive image features from scale-invariant keypoints / D. Lowe // International Journal of Computer Vision. – 2004. - Vol. 2(60). – 91-110.
  10. Sarfraz, O. Head Pose Estimation in Face Recognition across Pose Scenarios / O. Sarfraz, S. Hellwich // Proceedings of VISAPP 2008, Int. conference on Computer Vision Theory and Applications, Madeira, Portugal. – 2008. - P. 235-242.
  11. Ashbrook, A. Robust recognition of scaled shapes using pairwise geometric histograms / A. Ashbrook, N. Thacker, P. Ro­ckett, C. Brown // Proceedings of the sixth British Machine Vision Conference, Birmingham, UK. – 1995 – P. 503-512.
  12. Belongie, S. Shape matching and object recognition using shape contexts / S. Belongie, J. Malik, J. Puzicha // IEEE Transactions on Pattern Analysis and Machine Intelligence. – 2002. – Vol. 24(4). – P. 509-522.
  13. Gabor, D. Theory of communication / D. Gabor // Journal I.E.E. – 1946. – Vol. 3(93). – P. 429-457.
  14. Mallat, S. A Wavelet Tour of Signal Processing: The Sparse Way / S. Mallat. – Burlington, MA: Academic Press, 2009.
  15. Deans, S.R. The Radon Transform and Some of Its Applications / S.R. Deans. – New York: John Wiley & Sons, 1983.
  16. Duda, R.O. Use of the Hough Transformation to Detect Lines and Curves in Pictures/ R.O. Duda, P.E. Hart // Comm. ACM. – 1972. – Vol. 15. – P. 11–15.
  17. Hu, M.K. Visual Pattern Recognition by Moment Invariants / M.K. Hu // IRE Trans. Info. Theory. – 1962. – Vol. IT-8. – P. 179–187.
  18. Gool, L. Affine/photometric invariants for planar intensity patterns / L. Gool, T. Moons, D. Ungureanu // Proceedings of the 4th European Conference on Computer Vision, Cambridge, UK. – 1996. – P.642-651.
  19. Glumov, N.I. Polynomial bases for image processing in a sliding window / N.I. Glumov, V.V. Myasnikov, V.V. Ser­geyev // Pattern Recognition and Image Analysis. – 1994. - Vol. 4(4). - P. 408-413. – ISSN: 1054-6618.
  20. Flusser, J. Moments and Moment Invariants in Pattern Recognition / J. Flusser, T. Suk, B. Zitová. – Wiley & Sons Ltd, 2009. – 312 p.
  21. Koenderink, J. Representation of local geometry in the visual system / J. Koenderink, A. Doorn // Biological Cybernetics. – 1987. – Vol. 55. – P. 367-375.
  22. Florack, L. General intensity transformations and second order invariants / L. Florack, B. Romeny, J. Koenderink, M. Vier­gever // Proceedings of the 7th Scandinavian Conference on Image Analysis, Aalborg, Denmark. – 1991. – P. 338-345.
  23. Freeman, W. The design and use of steerable filters // W. Freeman, E. Adelson / IEEE Transactions on Pattern Analysis and Machine Intelligence. – 1991. – Vol.13(9). – P. 891-906.
  24. Baumberg, A. Reliable feature matching across widely separated views / A. Baumberg // Proceedings of the Conference on Computer Vision and Pattern Recognition, Hilton Head Island, South Carolina, USA. – 2000. – P. 774-781.
  25. Schaffalitzky, F. Multi-view matching for unordered image sets / F. Schaffalitzky, A. Zisserman // Proceedings of the 7th European Conference on Computer Vision, Copenhagen, Denmark. – 2002. – P. 414- 431.
  26. Khramov, A.G. Method of direction field for analysis and interpretation of diagnostic images. Doctoral thesis, speciality 05.13.17 – Informatics theoretical basis / A.G. Khramov. – Samara, 2006. – 230 p. – (In Russian).
  27. Dalal, N. Finding People in Images and Videos. PhD Thesis, Institut National Polytechnique de Grenoble / N. Dalal. – Grenoble, 2006. – 135 p.
  28. Fukunaga, K. Introduction to Statistical Pattern Recognition / K. Fukunaga. – 2nd ed., – New York: Academic Press, Inc, 1991. – 591 p.
  29. Schapire, R. Boosting: Foundations and Algorithms / R. Schapire, Y. Freund. – MIT Press, 2012. – 496 p.
  30. Viola, P. Rapid Object Detection using a Boosted Cascade of Simple Features / P. Viola, M.J. Jones // Proceedings IEEE Conf. on Computer Vision and Pattern Recognition, – 2001. – P. 511-518.
  31. Cramér, H. Mathematical Methods of Statistics / H. Cramér. – Princeton: Princeton University Press, 1999. – 575 p.
  32. Dempster, A.P. Maximum Likelihood from Incomplete Data via the EM Algorithm / A.P. Dempster, N.M. Laird, D.B. Rubin // Journal of the Royal Statistical Society. Series B (Methodological). – 1977. – Vol. 39(1). – P. 1–38.
  33. Myasnikov, V.V. Methods of vehicle detection on the aero and space images of Earth remote sensing / V.V. Myasnikov // Computer Optics. – 2012. – ISSN 0134-2452. – (in printing, in Russian).
  34. Zhuravlev, J.I. Pattern recognition algorithms, based on valuation calculation / J.I. Zhuravlev, V.V. Nikiforov // Cybernetics. — 1971. — N°3. – (In Russian).
  35. Zhuravlev, J.I. An algebraic approach to recognition or classifications problems / J.I. Zhuravlev // Pattern Recognition and Image Analysis. — 1998. — Vol. 8(1) — P. 59–100. – ISSN: 1054-6618.
© 2009, IPSI RAS
Institution of Russian Academy of Sciences, Image Processing Systems Institute of RAS, Russia, 443001, Samara, Molodogvardeyskaya Street 151; E-mail: ko@smr.ru; Phones: +7 (846 2) 332-56-22, Fax: +7 (846 2) 332-56-20