THE ALGORITHMS FOR FACIAL RECOGNITION

The basic idea of face recognition is the selection of informative features in the face image, encoding, and comparison of the encoded entity with the database. In this paper the analysis of algorithms based on the method of principal components, linear discriminant analysis, detection of local features, with the application of Gabor wavelets, discrete cosine transform, local binary patterns are given. It is noted that the correlation methods are characterized by computational complexity and require large amounts of memory, in this regard, in practice it is reasonable to use appropriate methods to reduce the dimensionality of the features. Shows the latest developments of the company "Vokord" based on the use of deep neural networks using a test database with a million photos.

1. Brunelli R., Poggio T. Face recognition through geometrical features / R.Brunelli, T.Poggio // European Conference on Computer Vision (ECCV). 1992. P. 792-800

2. Turk M. Eigenfaces for recognition/ M.Turk, A.Pentland // Journal of Cognitive Neuroscience. 1991. no. 3. P. 71-86.

3. Belhumeur P.N. Eigenfaces vs. fisherfaces: recognition using class specific linear projection / P.N.Belhumeur, J.Hespanha, D.Kriegman // IEEE Transactions on Pattern Analysis and Machine Intelligence. 1997. V. 19. P. 711-720

4. Wiskott L. Face recognition by elastic bunch graph matching / L.Wiskott, J.Fellous, N.Kruger, C.Malsburg // IEEE Transactions on Pattern Analysis and Machine Intelligence. 1997. V. 19. P. 775-779.

5. Messer K. Performance characterization of face recognition algorithms and their sensitivity to severe illumination changes / K.Messer, J.Kittler, J.Short // Proc. of the International Conference on Biometrics (ICB). 2006. P. 1-11.

6. Zhao W. Face recognition: A literature survey / W.Zhao, R.Chellappa, P.Phillips, A.Rosenfeld // ACM Computing Surveys (CSUR). 2003. V. 35, № 4. P. 399-458.

7. Comon P. Independent Component Analysis - A New Concept? / P.Comon // Signal Processing. 1994. V. 36. P. 287-314.

8. Ojala T. Performance evaluation of texture measures with classification based on Kullback discrimination of distributions / T.Ojala, M.Pietikainen, D.Harwood // Proc. of the 12th IAPR International Conference on Pattern Recognition (ICPR). 1994. V. 1. P. 582-585.

9. Ahonen T. Face recognition with local binary patterns / T.Ahonen, A.Hadid, M.Pietikainen // Proc. of the European Conference on Computer Vision (ECCV). 2004. P. 469-481.

10. Huang D. Local binary patterns and its application to facial image analysis: a survey / D.Huang, C.Shan, M.Ardabilian, Y.Wang, L.Chen // IEEE transactions on systems, man, and cybernetics - part C: applications and reviews. 2011. V. 41, no. 6. P. 765-781.

11. Petruk V.I. Primenenie lokal'nykh binarnykh shablonov k resheniyu zadachi raspoznavaniya lits / V.I.Petruk, A.V.Samorodov, I.N. Spiridonov // Vestnik Moskovskogo gosudarstvennogo tekhnicheskogo universiteta im. N.E. Baumana. Ser. Priborostroenie. 2011. Spets. vyp. Biometricheskie tekhnologii. pp. 58-63.

12. Pen'kov P.V. Ekspertnye metody uluchsheniya sistem upravleniya / P.V.Pen'kov // Vestnik Voronezhskogo instituta vysokikh tekhnologiy. 2012. No. 9. pp. 108-110.

13. Golovinov S.O. Tsifrovaya obrabotka signalov / S.O.Golovinov, S.G.Mironchenko, E.V.Shchepilov, A.P.Preobrazhenskiy // Vestnik Voronezhskogo instituta vysokikh tekhnologiy. 2009. No. 4. pp. 064-065.

14. Preobrazhenskiy A.P. Issledovanie vozmozhnosti opredeleniya formy ob"ekta v okrestnosti vosstanovleniya lokal'nykh otrazhateley na poverkhnosti ob"ektov po ikh diagrammam obratnogo rasseyaniya / A.P.Preobrazhenskiy // Telekommunikatsii. 2003. No. 4. pp. 29-32.

15. Preobrazhenskiy A.P. Approksimatsiya kharakteristik rasseyaniya elektromagnitnykh voln elementov, vkhodyashchikh v sostav ob"ektov slozhnoy formy / A.P.Preobrazhenskiy, Yu.P.Khukhryanskiy // Vestnik Voronezhskogo gosudarstvennogo tekhnicheskogo universiteta. 2005. Vol. 1. No. 8. pp. 15-16.

16. Preobrazhenskiy A.P. Algoritmy prognozirovaniya radiolokatsionnykh kharakteristik ob"ektov pri vosstanovlenii radiolokatsionnykh izobrazheniy / A.P.Preobrazhenskiy, O.N.Choporov // Sistemy upravleniya i informatsionnye tekhnologii. 2004. Vol. 17. No. 5. pp. 85- 87.

17. Kosilov A.T. Vosstanovlenie radiolokatsionnykh izobrazheniy ob"ektov s ispol'zovaniem metodov radiogolografii / A.T.Kosilov, A.P.Preobrazhenskiy // Vestnik Voronezhskogo gosudarstvennogo tekhnicheskogo universiteta. 2005. Vol. 1. No. 8. pp. 79-81.

18. Chutchenko Yu.E. Issledovanie vozmozhnosti uluchsheniya kachestva izobrazheniya / Yu.E.Chutchenko, A.P.Preobrazhenskiy // Territoriya nauki. 2007. No. 3. pp. 364-369.

19. Mokeev V.V. Ob effektivnosti analiza i raspoznavaniya izobrazheniy metodom glavnykh komponent i lineynym diskriminantnym analizom / V.V.Mokeev, S.V. Tomilov // Vestnik Yuzhno-Ural'skogo gosudarstvennogo universiteta. Seriya: Komp'yuternye tekhnologii, upravlenie, radioelektronika. 2013. Vyp. No. 3, Vol. 13. pp. 61-70.

20. Danitsa A.I. Modeli kanalov peredachi dannykh / A.I.Danitsa, V.N.Kostrova // Vestnik Voronezhskogo instituta vysokikh tekhnologiy. 2016. No. 2(17). pp. 86-90.

21. Maksimova A.A. Metody issledovaniya kharakteristik rasseyaniya elektromagnitnykh voln ob"ektami / A.A.Maksimova, A.G.Yurochkin // Vestnik Voronezhskogo instituta vysokikh tekhnologiy. 2016. No. 1(16). pp. 53-56.

22. http://www.ixbt.com/news/2016/09/05/algoritm-identifikacii-lickompanii-vokord-pokazal-luchshij-rezultat-v-mire-v-teste-megaface.html