KFU. Card publication. Combined Convolutional and Perceptron Neural Networks for Handwritten Digits Recognition

KAZAN
FEDERAL UNIVERSITY

- RUS
- 中文
- ES

COMBINED CONVOLUTIONAL AND PERCEPTRON NEURAL NETWORKS FOR HANDWRITTEN DIGITS RECOGNITION

Form of presentation

Articles in international journals and collections

Year of publication

2020

��

��

Authors, employees of KFU

Kayumov Zufar Damirovich, author

Mosin Sergey Gennadevich, author

Tumakov Dmitriy Nikolaevich, author

Bibliographic description in the original language

Kayumov Z, Tumakov D, Mosin S., Combined Convolutional and Perceptron Neural Networks for Handwritten Digits Recognition//2020 22th International Conference on Digital Signal Processing and its Applications, DSPA 2020. - 2020. - Vol., Is.. - Art. � 9213301.

Annotation

The use of a combination of a convolutional neural network and multilayer perceptrons for recognizing handwritten digits is considered. Recognition is carried out by two sets of networks following each other. The first neural network selects two digits with maximum activation functions. Depending on the winners, the following network is activated (multilayer perceptron), which selects one digit from two. The proposed algorithm is tested on the data from MNIST. The recognition error is 0.75%. Obtained results demonstrate that the minimum error with this approach is 0.68%, and the accuracy of the F-metric is about 0.99 for each digit. The main feature of the proposed solution is dealt with the fact that the proposed cascaded combination of neural networks provides a sufficiently high accuracy with a simple architecture.

Keywords

handwritten digits, recognition, hierarchical convolutional neural network, MNIST

The name of the journal

2020 22th International Conference on Digital Signal Processing and its Applications, DSPA 2020

URL

https://www.scopus.com/inward/record.uri?eid=2-s2.0-85094597199&doi=10.1109%2fDSPA48919.2020.9213301&partnerID=40&md5=ef648da1f9071d6742ea52a7d886dfe1

Please use this ID to quote from or refer to the card

https://repository.kpfu.ru/eng/?p_id=242052&p_lang=2

Full metadata record

Field DC	Value	Language
dc.contributor.author	Kayumov Zufar Damirovich	ru_RU
dc.contributor.author	Mosin Sergey Gennadevich	ru_RU
dc.contributor.author	Tumakov Dmitriy Nikolaevich	ru_RU
dc.date.accessioned	2020-01-01T00:00:00Z	ru_RU
dc.date.available	2020-01-01T00:00:00Z	ru_RU
dc.date.issued	2020	ru_RU
dc.identifier.citation	Kayumov Z, Tumakov D, Mosin S., Combined Convolutional and Perceptron Neural Networks for Handwritten Digits Recognition//2020 22th International Conference on Digital Signal Processing and its Applications, DSPA 2020. - 2020. - Vol., Is.. - Art. � 9213301.	ru_RU
dc.identifier.uri	https://repository.kpfu.ru/eng/?p_id=242052&p_lang=2	ru_RU
dc.description.abstract	2020 22th International Conference on Digital Signal Processing and its Applications, DSPA 2020	ru_RU
dc.description.abstract	The use of a combination of a convolutional neural network and multilayer perceptrons for recognizing handwritten digits is considered. Recognition is carried out by two sets of networks following each other. The first neural network selects two digits with maximum activation functions. Depending on the winners, the following network is activated (multilayer perceptron), which selects one digit from two. The proposed algorithm is tested on the data from MNIST. The recognition error is 0.75%. Obtained results demonstrate that the minimum error with this approach is 0.68%, and the accuracy of the F-metric is about 0.99 for each digit. The main feature of the proposed solution is dealt with the fact that the proposed cascaded combination of neural networks provides a sufficiently high accuracy with a simple architecture.	ru_RU
dc.language.iso	ru	ru_RU
dc.subject	handwritten digits	ru_RU
dc.subject	recognition	ru_RU
dc.subject	hierarchical convolutional neural network	ru_RU
dc.subject	MNIST	ru_RU
dc.title	Combined Convolutional and Perceptron Neural Networks for Handwritten Digits Recognition	ru_RU
dc.type	Articles in international journals and collections	ru_RU