UDC 004.93
ADAPTIVE FACE RECOGNITION IN CONDITIONS OF STRUCTURAL DISTORTIONS
K. A. Maikov, Doctor in Technical Sciences, Professor, Department of Computer Software and Information
Technologies, Bauman Moscow State Technical University, Moscow, Russia;
e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
A. K. Klimenko, Master's student, Department of Computer Software and Information Technology, Bauman
Moscow State Technical University, Moscow, Russia;
e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
S. A. Bubnov, PhD (in Physical and Mathematical sciences), Associate Professor, Department of Computational
and Applied Mathematics, RSREU named after V.F. Utkin, RSREU, Ryazan, Russia;
e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
A face recognition method resistant to structural distortions of source data using a combination of convolutional
and capsule neural networks is proposed. A comparative characteristic of the accuracy of known
face recognition methods in presence of occlusions is given. Experimental studies have shown that the proposed method surpasses known analogues in recognition accuracy
Key words: face recognition, structural interference, capsule neural network, convolutional neural network,
adaptive learning