KFU. Card publication. Recognition of Handwritten Digits Based on Images Spectrum Decomposition

KAZAN
FEDERAL UNIVERSITY

- RUS
- 中文
- ES

RECOGNITION OF HANDWRITTEN DIGITS BASED ON IMAGES SPECTRUM DECOMPOSITION

Form of presentation

Articles in international journals and collections

Year of publication

2021

Язык

английский

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., Recognition of Handwritten Digits Based on Images Spectrum Decomposition//2021 23rd International Conference on Digital Signal Processing and its Applications, DSPA 2021. - 2021. - Vol., Is.. - .

Annotation

Recognition of handwritten digits by convolutional neural network (CNN) using Fourier transforms of images as a preprocessing is considered. An algorithm of image preprocessing for effective CNN training and handwritten digits recognition is proposed. A discrete two-dimensional Fourier transform is applied to the original images. The real and imaginary parts are separated from the obtained complex values, as well as the amplitude and phase are calculated. Convolutional neural network is trained on the resulting characteristics obtained after Fourier transform. The proposed approach is tested on the MNIST database. The effects of image preprocessing using spectral decomposition and application of obtained different essential characteristics on the errors of handwritten digits recognition are estimated.

Keywords

handwritten digit, recognition, Fourier transform, MNIST

The name of the journal

2021 23rd International Conference on Digital Signal Processing and its Applications, DSPA 2021

URL

https://www.scopus.com/inward/record.uri?eid=2-s2.0-85115949739&doi=10.1109%2fDSPA51283.2021.9535947&partnerID=40&md5=231a2a702c7890dce350bfa5df3d2366

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

https://repository.kpfu.ru/eng/?p_id=258364&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	2021-01-01T00:00:00Z	ru_RU
dc.date.available	2021-01-01T00:00:00Z	ru_RU
dc.date.issued	2021	ru_RU
dc.identifier.citation	Kayumov Z, Tumakov D, Mosin S., Recognition of Handwritten Digits Based on Images Spectrum Decomposition//2021 23rd International Conference on Digital Signal Processing and its Applications, DSPA 2021. - 2021. - Vol., Is.. - .	ru_RU
dc.identifier.uri	https://repository.kpfu.ru/eng/?p_id=258364&p_lang=2	ru_RU
dc.description.abstract	2021 23rd International Conference on Digital Signal Processing and its Applications, DSPA 2021	ru_RU
dc.description.abstract	Recognition of handwritten digits by convolutional neural network (CNN) using Fourier transforms of images as a preprocessing is considered. An algorithm of image preprocessing for effective CNN training and handwritten digits recognition is proposed. A discrete two-dimensional Fourier transform is applied to the original images. The real and imaginary parts are separated from the obtained complex values, as well as the amplitude and phase are calculated. Convolutional neural network is trained on the resulting characteristics obtained after Fourier transform. The proposed approach is tested on the MNIST database. The effects of image preprocessing using spectral decomposition and application of obtained different essential characteristics on the errors of handwritten digits recognition are estimated.	ru_RU
dc.language.iso	ru	ru_RU
dc.subject	handwritten digit	ru_RU
dc.subject	recognition	ru_RU
dc.subject	Fourier transform	ru_RU
dc.subject	MNIST	ru_RU
dc.title	Recognition of Handwritten Digits Based on Images Spectrum Decomposition	ru_RU
dc.type	Articles in international journals and collections	ru_RU