Recognition of the MNIST-dataset with skeletonized images Full article
| Conference |
15th International Scientific and Technical Conference: Applied Mechanics and Systems Dynamics 09-11 Nov 2021 , Омск |
||||
|---|---|---|---|---|---|
| Journal |
Journal of Physics: Conference Series
ISSN: 1742-6588 , E-ISSN: 1742-6596 |
||||
| Output data | Year: 2022, Volume: 2182, Number: 1, Article number : 012032, Pages count : DOI: 10.1088/1742-6596/2182/1/012032 | ||||
| Authors |
|
||||
| Affiliations |
|
Funding (1)
| 1 | Омский филиал ФГБУН «Институт математики им. С.Л. Соболева СО РАН». | FWNF-2022-0003 |
Abstract:
For a long time there have been many neural networks that are able to recognize handwritten numbers. In our work, we will investigate a neural network according to a specific feature, indicating the number in the picture. We will try to achieve an important image skeleton for recognition. © Published under licence by IOP Publishing Ltd.
Cite:
Shevlyakov A.N.
, Lobanov V.P.
Recognition of the MNIST-dataset with skeletonized images
Journal of Physics: Conference Series. 2022. V.2182. N1. 012032 . DOI: 10.1088/1742-6596/2182/1/012032 Scopus РИНЦ OpenAlex
Recognition of the MNIST-dataset with skeletonized images
Journal of Physics: Conference Series. 2022. V.2182. N1. 012032 . DOI: 10.1088/1742-6596/2182/1/012032 Scopus РИНЦ OpenAlex
Identifiers:
| Scopus: | 2-s2.0-85127653702 |
| Elibrary: | 48425940 |
| OpenAlex: | W4220725187 |