Radiotekhnika
Publishing house Radiotekhnika

"Publishing house Radiotekhnika":
scientific and technical literature.
Books and journals of publishing houses: IPRZHR, RS-PRESS, SCIENCE-PRESS


Тел.: +7 (495) 625-9241

 

Face image biometric verification algorithm based on deep convolution neural network

Keywords:

V.V. Khryashchev – Ph. D. (Eng.), Associate Professor of Department of Infocommunication and Radiophysics, P.G. Demidov Yaroslavl State University
E-mail: vhr@yandex.ru
A.A. Lebedev – Master of Department of Infocommunication and Radiophysics, P.G. Demidov Yaroslavl State University
E-mail: lebedevdes@gmail.com
A.M. Shemyakov – Post-graduate Student of Department of Infocommunication and Radiophysics, P.G. Demidov Yaroslavl State University
E-mail: andrey.shemiakov@gmail.com
V.A. Pavlov – Post-graduate Student of Department of Infocommunication and Radiophysics, P.G. Demidov Yaroslavl State University
E-mail: i@yajon.ru


This paper presents the new algorithm for face recognition based on deep convolution neural network. The algorithm produces face feature vectors, distance between these vectors allows to determine whether images from the same class. Comparative experimental results are given for LFW test database and modern face recognition algorithms. ROC-curve and EER are used to determine the accuracy of compared algorithms.
Testing was carried out under the «image resctricted» verification paradigm. With uncontrolled learning, the algorithm can’t have any access to the data class labels, the statistics of these labels, or the means of generating these labels. Proposed face recognition algorithm is more accurate than other modern algorithms.

References:
  1. Luk’yanicza A.A., Shishkin A.G. Czifrovaya obrabotka videoizobrazhenij // M.: Aj-E’s-E’s Press. 2009. 518 s.
  2. Dvorkovich V.P., Dvorkovich A.V. Czifrovy’e videoinformaczionny’e sistemy’ (teoriya i praktika). M.: Texnosfera. 2012. 1009 s.
  3. Kuxarev G.A. Metody’ obrabotki i raspoznavaniya izobrazhenij licz v zadachax biometrii. SPb.: Politexnika. 2013. 388 s.
  4. Nenaxov I.S., Xryashhev V.V., Priorov A.L., Lebedev A.A. Issledovanie metrik kachestva izobrazheniya licza v zadachax raspoznavaniya // Uspexi sovremennoj radioe’lektroniki. 2016. № 10. S. 48−53.
  5. Xryashhev V.V., Matveev D.V., Lebedev A.A., Nenaxov I.S. Detektirovanie cheloveka pri analize videoposledovatel’nostej s kupol’ny’x kamer // Uspexi sovremennoj radioe’lektroniki. 2016. № 8. S. 47−55.
  6. Khryashchev V., Nenakhov I., Lebedev A., Priorov A. Evaluation of Face Image Quality Metrics in Person Identification Problem // Proceedings of the 19th Conference of Open Innovations Association (FRUCT). Jyvaskyla (Finland). 2016. P. 80−87.
  7. Cinbis R.G., Verbeek J.J., Schmid C. Unsupervised metric learning for face identification in TV video // Proc. ICCV. 2011. P. 1559−1566.
  8. C. Lu, Tang X. Surpassing human-level face verification performance on lfw with gaussianface. AAAI. 2015.
  9. Sivic J., Everingham M., Zisserman A. Person spotting: Video shot retrieval for face sets // Proc. CIVR. 2005.
  10. Sivic J., Everingham M., Zisserman A. «Who are you?» – learning person specific classifiers from video // Proc. CVPR. 2009.
  11. Wolf L., Hassner Tal., Maoz I. Face recognition in unconstrained videos with matched background similarity // Proc. CVPR. 2011.
  12. Parkhi O.M., Simonyan K., Vedaldi A., Zisserman A. A compact and discriminative face track descriptor // Proc. CVPR. 2014.
  13. Simonyan K., Parkhi O.M., Vedaldi A., Zisserman A. Fisher Vector Faces in the Wild // Proc. BMVC. 2013.
  14. Russakovsky O., Deng J., H. Su, Krause J., Satheesh S., S. Ma, Huang S., Karpathy A., Khosla A., Bernstein M., Berg A.C., F.F. Li. Imagenet large scale visual recognition challenge. IJCV. 2015.
  15. Goodfellow I.J., Bulatov Y., Ibarz J., Arnoud S., Shet V. Multi-digit number recognition from street view imagery using deep convolutional neural networks. 2014.
  16. Simonyan K. and Zisserman A. Very deep convolutional networks for large-scale image recognition // International Conference on Learning Representations. 2015.
  17. Szegedy C., Liu W., Jia Y., Sermanet P., Reed S., Anguelov D., Erhan D., Vanhoucke V., Rabinovich A. Going deeper with convolutions. CoRR, abs/1409.4842. 2014.
  18. LeCun Y., Boser B., Denker J.S., Henderson D., Howard R.E., Hubbard W., Jackel L.D. Backpropagation applied to handwritten zip code recognition // Neural Computation. 1989. 1(4):541−551.
  19. Parkhi O.M., Vedaldi A., Zisserman A. Deep Face Recognition British Machine Vision Conference. 2015.
  20. Gary B. Huang and Erik Learned-Miller. Labeled Faces in the Wild: Updates and New Reporting Procedures. University of Massachusetts, Amherst. Technical Report UM-CS-2014-003. May. 2014.
  21. Fawcett T. An introduction to ROC analysis // Pattern Recognition Letters. 2006. V. 27. № 8. P. 861−874.
  22. Lior Wolf, Tal Hassner, Yaniv Taigman, Effective Face Recognition by Combining Multiple Descriptors and Learned Background Statistics // IEEE Trans. on Pattern Analysis and Machine Intelligence (TPAMI) . October 2011. 33(10).
  23. Javier Ruiz-del-Solar, Rodrigo Verschae, Mauricio Correa. Recognition of Faces in Unconstrained Environments: A Comparative Study // EURASIP Journal on Advances in Signal Processing (Recent Advances in Biometric Systems: A Signal Processing Perspective). V. 2009. Article ID 184617. 19 p.
  24. Meng Xi, Liang Chen, Desanka Polajnar, Weiyang Tong. Local Binary Pattern Network: A Deep Learning Approach for Face Recognition // International Conference on Image Processing (ICIP). 2016.

© Издательство «РАДИОТЕХНИКА», 2004-2017            Тел.: (495) 625-9241                   Designed by [SWAP]Studio