КФУ. Карточка публикации. An Effect of Binarization on Handwritten Digits Recognition by Hierarchical Neural Network

КАЗАНСКИЙ
ФЕДЕРАЛЬНЫЙ УНИВЕРСИТЕТ

RUS

- EN
- 中文
- ES

AN EFFECT OF BINARIZATION ON HANDWRITTEN DIGITS RECOGNITION BY HIERARCHICAL NEURAL NETWORK

Форма представления

Статьи в зарубежных журналах и сборниках

Год публикации

2022

Язык

английский

Авторы, сотрудники КФУ

Каюмов Зуфар Дамирович, автор

Мосин Сергей Геннадьевич, автор

Тумаков Дмитрий Николаевич, автор

Библиографическое описание на языке оригинала

Kayumov Z, Tumakov D, Mosin S., An Effect of Binarization on Handwritten Digits Recognition by Hierarchical Neural Network//Lecture Notes in Networks and Systems. - 2022. - Vol.300 LNNS, Is.. - P.94-106.

Аннотация

The influence of binarization on the recognition of handwritten digits has been investigated. The main methods of converting images from grayscale to black and white images are analyzed. The binarization process is applied to images of handwritten digits. Both the Convolutional neural network (CNN) and the multilayer perceptron (MLP) architectures are proposed for an automated recognizing the handwritten digits. The CNN and MLP are trained on the raw data of images. Essential characteristics are obtained by the method of feature extraction from binarized images and then are used for the CNN and MLP training. The influence of the binarization threshold on network recognition errors is analyzed. A comparison of the recognition accuracy by the neural networks for different algorithms is carried out. It was estimated that the minimum error of combining the proposed networks does not exceed 99.86%. A new approach to the design of a hierarchical network composed of a network trained on basic images of digits and images of digits obtained by binarization is proposed. The hierarchical neural networks with an accuracy of 99.61% on the MNIST dataset are proposed.

Ключевые слова

Handwritten digits, Recognition, CNN, Hierarchical neural network, Binarization, MNIST

Название журнала

Lecture Notes in Networks and Systems

URL

https://www.scopus.com/inward/record.uri?eid=2-s2.0-85115624156&doi=10.1007%2f978-3-030-84760-9_9&partnerID=40&md5=2fde4b83bb5711f32d33668e5fdc21c9

Пожалуйста, используйте этот идентификатор, чтобы цитировать или ссылаться на эту карточку

https://repository.kpfu.ru/?p_id=258363

Полная запись метаданных

Поле DC	Значение	Язык
dc.contributor.author	Каюмов Зуфар Дамирович	ru_RU
dc.contributor.author	Мосин Сергей Геннадьевич	ru_RU
dc.contributor.author	Тумаков Дмитрий Николаевич	ru_RU
dc.date.accessioned	2022-01-01T00:00:00Z	ru_RU
dc.date.available	2022-01-01T00:00:00Z	ru_RU
dc.date.issued	2022	ru_RU
dc.identifier.citation	Kayumov Z, Tumakov D, Mosin S., An Effect of Binarization on Handwritten Digits Recognition by Hierarchical Neural Network//Lecture Notes in Networks and Systems. - 2022. - Vol.300 LNNS, Is.. - P.94-106.	ru_RU
dc.identifier.uri	https://repository.kpfu.ru/?p_id=258363	ru_RU
dc.description.abstract	Lecture Notes in Networks and Systems	ru_RU
dc.description.abstract	The influence of binarization on the recognition of handwritten digits has been investigated. The main methods of converting images from grayscale to black and white images are analyzed. The binarization process is applied to images of handwritten digits. Both the Convolutional neural network (CNN) and the multilayer perceptron (MLP) architectures are proposed for an automated recognizing the handwritten digits. The CNN and MLP are trained on the raw data of images. Essential characteristics are obtained by the method of feature extraction from binarized images and then are used for the CNN and MLP training. The influence of the binarization threshold on network recognition errors is analyzed. A comparison of the recognition accuracy by the neural networks for different algorithms is carried out. It was estimated that the minimum error of combining the proposed networks does not exceed 99.86%. A new approach to the design of a hierarchical network composed of a network trained on basic images of digits and images of digits obtained by binarization is proposed. The hierarchical neural networks with an accuracy of 99.61% on the MNIST dataset are proposed.	ru_RU
dc.language.iso	ru	ru_RU
dc.subject	Handwritten digits	ru_RU
dc.subject	Recognition	ru_RU
dc.subject	CNN	ru_RU
dc.subject	Hierarchical neural network	ru_RU
dc.subject	Binarization	ru_RU
dc.subject	MNIST	ru_RU
dc.title	An Effect of Binarization on Handwritten Digits Recognition by Hierarchical Neural Network	ru_RU
dc.type	Статьи в зарубежных журналах и сборниках	ru_RU