Comparative Analysis of the Application of Multilayer and Convolutional Neural Networks for Recognition of Handwritten Letters of the Azerbaijani Alphabet

Introduction. The implementation of information technologies in various spheres of public life dictates the creation of efficient and productive systems for entering information into computer systems. In such systems it is important to build an effective recognition module. At the moment, the most e...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Elshan Mustafayev, Rustam Azimov
Formato:	article
Lenguaje:	EN RU UK
Publicado:	V.M. Glushkov Institute of Cybernetics 2021
Materias:	neural networks feature extraction ocr Cybernetics Q300-390
Acceso en línea:	https://doaj.org/article/d40906d19ee347c99b5a46101498d9b7
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:d40906d19ee347c99b5a46101498d9b7
record_format	dspace
spelling	oai:doaj.org-article:d40906d19ee347c99b5a46101498d9b72021-11-08T19:44:54ZComparative Analysis of the Application of Multilayer and Convolutional Neural Networks for Recognition of Handwritten Letters of the Azerbaijani Alphabet2707-45012707-451X10.34229/2707-451X.21.3.6https://doaj.org/article/d40906d19ee347c99b5a46101498d9b72021-09-01T00:00:00Zhttp://cctech.org.ua/13-vertikalnoe-menyu-en/281-abstract-21-3-6-artehttps://doaj.org/toc/2707-4501https://doaj.org/toc/2707-451XIntroduction. The implementation of information technologies in various spheres of public life dictates the creation of efficient and productive systems for entering information into computer systems. In such systems it is important to build an effective recognition module. At the moment, the most effective method for solving this problem is the use of artificial multilayer neural and convolutional networks. The purpose of the paper. This paper is devoted to a comparative analysis of the recognition results of handwritten characters of the Azerbaijani alphabet using neural and convolutional neural networks. Results. The analysis of the dependence of the recognition results on the following parameters is carried out: the architecture of neural networks, the size of the training base, the choice of the subsampling algorithm, the use of the feature extraction algorithm. To increase the training sample, the image augmentation technique was used. Based on the real base of 14000 characters, the bases of 28000, 42000 and 72000 characters were formed. The description of the feature extraction algorithm is given. Conclusions. Analysis of recognition results on the test sample showed: as expected, convolutional neural networks showed higher results than multilayer neural networks; the classical convolutional network LeNet-5 showed the highest results among all types of neural networks. However, the multi-layer 3-layer network, which was input by the feature extraction results; showed rather high results comparable with convolutional networks; there is no definite advantage in the choice of the method in the subsampling layer. The choice of the subsampling method (max-pooling or average-pooling) for a particular model can be selected experimentally; increasing the training database for this task did not give a tangible improvement in recognition results for convolutional networks and networks with preliminary feature extraction. However, for networks learning without feature extraction, an increase in the size of the database led to a noticeable improvement in performance.Elshan MustafayevRustam AzimovV.M. Glushkov Institute of Cyberneticsarticleneural networksfeature extractionocrCyberneticsQ300-390ENRUUKКібернетика та комп'ютерні технології, Iss 3, Pp 65-73 (2021)
institution	DOAJ
collection	DOAJ
language	EN RU UK
topic	neural networks feature extraction ocr Cybernetics Q300-390
spellingShingle	neural networks feature extraction ocr Cybernetics Q300-390 Elshan Mustafayev Rustam Azimov Comparative Analysis of the Application of Multilayer and Convolutional Neural Networks for Recognition of Handwritten Letters of the Azerbaijani Alphabet
description	Introduction. The implementation of information technologies in various spheres of public life dictates the creation of efficient and productive systems for entering information into computer systems. In such systems it is important to build an effective recognition module. At the moment, the most effective method for solving this problem is the use of artificial multilayer neural and convolutional networks. The purpose of the paper. This paper is devoted to a comparative analysis of the recognition results of handwritten characters of the Azerbaijani alphabet using neural and convolutional neural networks. Results. The analysis of the dependence of the recognition results on the following parameters is carried out: the architecture of neural networks, the size of the training base, the choice of the subsampling algorithm, the use of the feature extraction algorithm. To increase the training sample, the image augmentation technique was used. Based on the real base of 14000 characters, the bases of 28000, 42000 and 72000 characters were formed. The description of the feature extraction algorithm is given. Conclusions. Analysis of recognition results on the test sample showed: as expected, convolutional neural networks showed higher results than multilayer neural networks; the classical convolutional network LeNet-5 showed the highest results among all types of neural networks. However, the multi-layer 3-layer network, which was input by the feature extraction results; showed rather high results comparable with convolutional networks; there is no definite advantage in the choice of the method in the subsampling layer. The choice of the subsampling method (max-pooling or average-pooling) for a particular model can be selected experimentally; increasing the training database for this task did not give a tangible improvement in recognition results for convolutional networks and networks with preliminary feature extraction. However, for networks learning without feature extraction, an increase in the size of the database led to a noticeable improvement in performance.
format	article
author	Elshan Mustafayev Rustam Azimov
author_facet	Elshan Mustafayev Rustam Azimov
author_sort	Elshan Mustafayev
title	Comparative Analysis of the Application of Multilayer and Convolutional Neural Networks for Recognition of Handwritten Letters of the Azerbaijani Alphabet
title_short	Comparative Analysis of the Application of Multilayer and Convolutional Neural Networks for Recognition of Handwritten Letters of the Azerbaijani Alphabet
title_full	Comparative Analysis of the Application of Multilayer and Convolutional Neural Networks for Recognition of Handwritten Letters of the Azerbaijani Alphabet
title_fullStr	Comparative Analysis of the Application of Multilayer and Convolutional Neural Networks for Recognition of Handwritten Letters of the Azerbaijani Alphabet
title_full_unstemmed	Comparative Analysis of the Application of Multilayer and Convolutional Neural Networks for Recognition of Handwritten Letters of the Azerbaijani Alphabet
title_sort	comparative analysis of the application of multilayer and convolutional neural networks for recognition of handwritten letters of the azerbaijani alphabet
publisher	V.M. Glushkov Institute of Cybernetics
publishDate	2021
url	https://doaj.org/article/d40906d19ee347c99b5a46101498d9b7
work_keys_str_mv	AT elshanmustafayev comparativeanalysisoftheapplicationofmultilayerandconvolutionalneuralnetworksforrecognitionofhandwrittenlettersoftheazerbaijanialphabet AT rustamazimov comparativeanalysisoftheapplicationofmultilayerandconvolutionalneuralnetworksforrecognitionofhandwrittenlettersoftheazerbaijanialphabet
_version_	1718441521328422912

Comparative Analysis of the Application of Multilayer and Convolutional Neural Networks for Recognition of Handwritten Letters of the Azerbaijani Alphabet

Ejemplares similares