Open AccessThe using of data augmentation in machine learning in image processing tasks in the face of data scarcity
Author(s) -
Nikita Andriyanov,
Danila Andriyanov
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1661/1/012018
Subject(s) - computer science , artificial neural network , distortion (music) , face (sociological concept) , noise (video) , artificial intelligence , image (mathematics) , signal (programming language) , additive white gaussian noise , pattern recognition (psychology) , signal to noise ratio (imaging) , gaussian noise , speech recognition , white noise , computer network , amplifier , social science , telecommunications , bandwidth (computing) , sociology , programming language
The article presents the results of a study of the efficiency of various neural networks in the limited conditions of the source data and with a number of simple augmentations. In this case, the dependences were obtained for a serial neural network with back propagation of error. For data augmentation, the simplest transformations were used, including the letters tilting (italics), changing the color of letters (from black to red), as well as distortion of the reference images with white Gaussian noise at a signal-to-noise ratio q from 1 to 10. It is shown that the best results of recognition of letters of the Russian alphabet are provided by a network for which all the augmentation methods discussed in this work were used. A study of the dependence of recognition accuracy on the signal-to-noise ratio in all trained neural networkswas also conducted.