Open AccessBiometrical driver face verification
Author(s) -
Jolanta Chmielińska,
Jacek Jakubowski
Publication year - 2018
Publication title -
autobusy
Language(s) - English
Resource type - Journals
eISSN - 2450-7725
pISSN - 1509-5878
DOI - 10.24136/atest.2018.039
Subject(s) - computer science , convolutional neural network , face (sociological concept) , artificial intelligence , transfer of learning , facial recognition system , machine learning , computer vision , real time computing , pattern recognition (psychology) , social science , sociology
The paper discusses the problem of face verification in a driver monitoring system for the purpose of traffic safety. Two different methods of face verification were proposed. Both of them are based on a convolutional neural network and were developed with the use of a transfer learning technique. In the paper, the results produced by both proposed method have been presented and compared. Moreover, their advantages and disadvantages have been discussed.