УДК: 004.932.4

Algorithm for recognizing objects based on clustering vectors in the space of coefficients of affine transformations

Publication in Journal of Optical Technology

For Russian citation (Opticheskii Zhurnal):

Пантюхин М.А., Самойлин Е.А. Алгоритм распознавания объектов на основе кластеризации векторов в пространстве коэффициентов аффинных преобразований // Оптический журнал. 2017. Т. 84. № 5. С. 29–37.

Pantyukhin M.A., Samoylin E.A. Algorithm for recognizing objects based on clustering vectors in the space of coefficients of affine transformations [in Russian] // Opticheskii Zhurnal. 2017. V. 84. № 5. P. 29–37.

For citation (Journal of Optical Technology):

M. A. Pantyukhin and E. A. Samoylin, "Algorithm for recognizing objects based on clustering vectors in the space of coefficients of affine transformations," Journal of Optical Technology. 84(5), 308-315 (2017). https://doi.org/10.1364/JOT.84.000308

Abstract:

We propose an algorithm for object recognition based on clustering of vectors in the space of coefficients of affine transformations obtained as a result of the formation of hypotheses about the correspondence of segments of contours of a reference image and an input image approximated by linear segments. The results of numerical studies using a collection of images from New York University show that the proposed algorithm has a higher efficiency than an algorithm based on invariant moments or an algorithm for the invariant-to-scale comparison of singular points.

Keywords:

object recognition, reference images, contour analysis, affine transformations, clustering

OCIS codes: 150.1135, 330.5000

References:

1. D. A. Forsythe and J. Ponce, Computer Vision: a Modern Approach (Prentice-Hall, Boston, 2012; Vil’yams, Moscow, 2004).
2. S. K. Bose, K. K. Biswas, and S. K. Gupta, “Model based object recognition—the role of affine invariants,” Artif. Intell. Eng. 10(3), 227–234 (1996).
3. M. Pontil and A. Verri, “Support vector machines for 3D object recognition,” IEEE Trans. Pattern Anal. Mach. Intell. 20(6), 637–646 (1998).
4. Yu. A. Bolotova, V. G. Spitsyn, and M. N. Rudometkina, “Identification of car license plates based on the method of connected components and a hierarchical time network,” Komput. Opt. 39(2), 275–280 (2015).
5. Y. LeCun, F.-J. Huang, and L. Bottou, “Learning methods for generic objects recognition with invariance to pose and lighting,” in Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR), Los Alamitos, CA, (IEEE Computer Society, 2004), vol. 2, pp. 97–104.
6. S. Chikkerur, T. Serre, C. Tan, and T. Poggio, “What and where: a Bayesian inference theory of attention,” Vis. Res. 50, 2233–2247 (2010).
7. B. B. Mikhaı˘lov, “Computer vision of mobile robots,” in Computer Vision in Systems of Control of Mobile Objects 2010: Proceedings of the Scientific and Technical Conference and Seminar, R. R. Nazirov, ed. (KDU, Moscow, 2011), issue 4, pp. 191–201.
8. D. V. Vasil’ev, “Fragments of the applied theory of systems of computer vision for unmanned aerial vehicles,” in Computer Vision in Systems of Control of Mobile Objects 2010: Proceedings of the Scientific and Technical Conference and Seminar, R. R. Nazirov, ed. (KDU, Moscow, 2011), issue 4, pp. 109–131.

9. I. O. Titov and G. M. Emel’yanov, “System of computer vision for a moving aerial object,” Komput. Opt. 35(4), 491–494 (2011).
10. K. M. Nguyen and V. Ya. Kolyuchkin, “Algorithms of contour segmentation and pattern recognition of objects of technical vision systems,” Nauka Obraz.: Nauch. Izd. N. É. Bauman MSTU (4), 187–200 (2013).
11. L. M. Mestetskiı˘ and I. A. Reı˘er, “Recognition of the form of raster binary images of plane figures using the morphology of edge contours,” Iskusstv. Intell.: Zh. NAS Ukr. (2), 401–406 (2000).
12. D. Lowe, “Distinctive image features from scale-invariant keypoints,” Int. J. Comput. Vis. 60(2), 91–110 (2004).
13. F. Stein and G. Medioni, “Structural indexing: efficient 2D object recognition,” IEEE Trans. Pattern Anal. Mach. Intell. 14(12), 1198–1204 (1992).
14. M. A. Pantyukhin and E. A. Samoylin, “The rule of choosing threshold parameters of the Canny edge detection operator when processing images in optoelectronic systems,” in Proceedings of the Third All-Russia Scientific and Practical Conference “AVIATOR,” Voronezh, Russia, February 11–12, 2016 (Military Educational and Scientific Center of the Air Force, 2016), vol. 1, pp. 89–94.
15. A. Yu. Andreev and S. P. Bobkov, “Segmentation of symbols in the image using the modified beetle method,” Sovrem. Nauko. Tekhnol. Reg. Prilozh. 1(37), 85–88 (2014).
16. M. N. Arshinov and L. E. Sadovskiı˘, Codes and Math (Nauka, Moscow, 1983).
17. I. M. Yaglom and V. G. Ashkinuze, Ideas and Methods of Affine and Projective Geometry. Part I. Affine Geometry (Uchpedgiz, Moscow, 1962).
18. S. Prince, Computer Vision: Models, Learning and Inference (Cambridge University, Cambridge, UK, 2012).
19. M. M. Postnikov, Analytic Geometry (Nauka, Moscow, 1973).