The using of data augmentation in machine learning in image processing tasks in the face of data scarcity

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 augmentati...

Full description

Saved in:
Bibliographic Details
Published in:Journal of physics. Conference series 2020-11, Vol.1661 (1), p.12018
Main Authors: Andriyanov, N A, Andriyanov, D A
Format: Article
Language:English
Subjects:
Back propagation networks
Data augmentation
Image processing
Machine learning
Neural networks
Random noise
Recognition
Signal to noise ratio
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:1742-6588
1742-6596
DOI:10.1088/1742-6596/1661/1/012018