Investigation of scale-invariant image classification mechanisms

Moiseenko, G.A., Pronin, S.V., Shelepin, Y.E.

Full text «Opticheskii Zhurnal»

Full text on elibrary.ru

Publication in Journal of Optical Technology

For Russian citation (Opticheskii Zhurnal):

Моисеенко Г.А., Пронин С.В., Шелепин Ю.Е. Исследование инвариантных к масштабным преобразованиям механизмов классификации изображений // Оптический журнал. 2019. Т. 86. № 11. С. 66–71. http://doi.org/10.17586/1023-5086-2019-86-11-66-71

Moiseenko G.A., Pronin S.V., Shelepin Yu.E. Investigation of scale-invariant image classification mechanisms [in Russian] // Opticheskii Zhurnal. 2019. V. 86. № 11. P. 66–71. http://doi.org/10.17586/1023-5086-2019-86-11-66-71

For citation (Journal of Optical Technology):

G. A. Moiseenko, S. V. Pronin, and Yu. E. Shelepin, "Investigation of scale-invariant image classification mechanisms," Journal of Optical Technology. 86(11), 729-733 (2019). https://doi.org/10.1364/JOT.86.000729

Abstract:

This study investigates the markers of operation of the classification mechanism that is invariant to scale transformations of images of test objects. Observers were asked to classify images according to the criterion of animate/inanimate object. Two series of studies were conducted using the method of cognitive evoked potentials. The angular sizes of the image of the objects presented to the observer were 3° in one series and 0.4° in another. It was established that the classification of the images of the stimuli of various angular sizes according to semantic features (animate/inanimate) causes a difference in the amplitudes of the P200 components (in the leads F7 and F8 of the frontal area). The role of the P200 components of the evoked potentials in the frontal areas of the brain as a marker of the classification process was investigated. It is observed that neural networks of the prefrontal cortex use the invariant description of images implemented in the previous stages of their processing to perform the classification of objects.

Keywords:

objects classification, decision making, invariant perception, cognitive evoked potentials

Acknowledgements:

The research was supported by the Program of Fundamental Scientific Research of State Academies, I.P. Pavlov Institute of Physiology (GP-14, section 63).

OCIS codes: 330.1070, 330.4270

References:

1. D. Bohm, The Special Theory of Relativity (Benjamin Inc., NY, 1965).
2. V. D. Glezer, K. N. Dudkin, N. F. Podvigin, A. A. Nevskaya, and N. V. Prazdnikova, Visual Recognition and Its Neurophysiological Mechanisms (Nauka, Moscow, 1975).
3. Yu. E. Shelepin, V. N. Chikhman, O. A. Vakhrameeva, S. V. Pronin, N. Foreman, and P. Pesmore, “Invariance of visual perception,” Eksp. Psikhol. 1(1), 7–33 (2008).
4. V. M. Bondarko, L. A. Semenov, S. D. Solnushkin, and V. N. Chikhman, “Invariance to size in the perception of illusory and fragmented contours depending on the age of the observers,” Fiziol. Chel. 36 (6), 41–47 (2008).
5. Yu. E. Shelepin and V. N. Chikhman, eds., Neurotechnology (VVM, St. Petersburg, 2018).
6. V. D. Glezer, Vision and Thinking, 2nd ed., corrected and extended (Nauka, St. Petersburg, 1993).
7. G. A. Moiseenko, Yu. E. Shelepin, A. K. Kharauzov, S. V. Pronin, V. N. Chikhman, and O. A. Vakhrameeva, “Classification and recognition of images of animate and inanimate objects,” J. Opt. Technol. 82(10), 685–693 (2015) [Opt. Zh. 82(10), 53–64 (2015)].
8. O. A. Vakhrameeva, Yu. E. Shelepin, A. Yu. Mezentsev, and S. V. Pronin, “Studying the perception of incomplete contour images of various sizes,” Ross. Fiziol. Zh. im. I. M. Sechenova 94(10), 1158–1170 (2008).
9. E. C. Leek, M. Roberts, Z. J. Oliver, F. Cristino, and A. J. Pegna, “Early differential sensitivity of evoked-potentials to local and global shape during the perception of three-dimensional objects,” Neuropsychologia 89, 495–509 (2016).
10. M. Dzhelyova and B. Rossion, “The effect of parametric stimulus size variation on individual face discrimination indexed by fast periodic visual stimulation,” BMC Neurosci. 15(87), 1471–2202 (2014).
11. H. Cecotti, “Toward shift invariant detection of event-related potential in non-invasive brain-computer interface,” Pattern Recognit. Lett. 66, 127–134 (2015).
12. L. Wiskott, “How does our visual system achieve shift and size invariance?” in 23 Problems in Systems Neuroscience, J. L. van Hemmen and T. J. Sejnowski, eds. (Oxford University Press, Oxford, 2003).
13. R. P. Baranov and A. V. Belokon, “Determination and priority of features of objects in the image in recognition systems,” Aktual. Probl. Aviats. Kosmonavt., 328–329 (2012).
14. L. Wiskott and T. Sejnowski, “Slow feature analysis: unsupervised learning of invariances,” Neural Comput. 14, 715–770 (2002).
15. D. G. Lowe, “Object recognition from local scale-invariant features,” in Proceedings of the International Conference on Computer Vision (1999), pp. 1150–1157.
16. Yu. E. Shelepin, V. A. Fokin, A. K. Kharauzov, S. V. Pronin, and V. N. Chikhman, “Localization of the decision-making center and perception of the form of visual stimuli,” Dokl. Akad. Nauk 429(6), 835–837 (2009).
17. Yu. E. Shelepin, Introduction to Neuroimaging (Troitski˘ı Most, St. Petersburg, 2017).
18. Yu. E. Shelepin, “On the dependence of the parameters of evoked potentials in the striatal cortex of a cat on the image size,” Fiziol. Zh. 59(5), 688–695 (1973).
19. Yu. E. Shelepin, “Localization of the visual cortex of a cat, giving an invariant response when resizing an image,” Neirofiziologiya 5(2), 115–121 (1973).
20. V. V. Yakovlev, “Differences in the description of the visual image at the level of the posterior parietal and inferior temporal cortex of monkeys,” Fiziologiya, 754–757 (1982).
21. Yu. E. Shelepin, V. A. Fokin, N. Foreman, A. K. Kharauzov, S. V. Pronin, O. A. Vakhrameeva, and V. N. Chikhman, “Using neuroimaging methods to localize mechanisms for making decisions concerning the ordering of textures,” J. Opt. Technol. 78(12), 808–816 (2011) [Opt. Zh. 78(12), 57–69 (2011)].