Contour Pattern Recognition with MNIST Dataset Научная публикация
| Сборник | 2022 Dynamics of Systems, Mechanisms and Machines (Dynamics) Сборник, IEEE. 2022. 4 c. ISBN 9781665465274. |
||||
|---|---|---|---|---|---|
| Вых. Данные | Год: 2022, Номер статьи : 10014982, Страниц : DOI: 10.1109/dynamics56256.2022.10014982 | ||||
| Ключевые слова | component, formatting, style, styling | ||||
| Авторы |
|
||||
| Организации |
|
Информация о финансировании (1)
| 1 | Российский научный фонд | 22-11-20019 |
Реферат:
We train a convolutional neural network for handwritten digits from the MNIST dataset. The aim the paper is to test the network for extremal datasets. Actually, we take digits contours as the validating set. The recognition accuracy is expectedly reduced, since the interior of an image carries significant information for the classifier. To obtain the contour of a MNIST -digit, we use the Canny detector and methods of mathematical morphology. The decreasing of the network accuracy may be treated as a part of information which is contained in the interior of handwritten digits.
Библиографическая ссылка:
Kaplun V.
, Shevlyakov A.N.
Contour Pattern Recognition with MNIST Dataset
В сборнике 2022 Dynamics of Systems, Mechanisms and Machines (Dynamics). – IEEE., 2022. – ISBN 9781665465274. DOI: 10.1109/dynamics56256.2022.10014982 Scopus OpenAlex
Contour Pattern Recognition with MNIST Dataset
В сборнике 2022 Dynamics of Systems, Mechanisms and Machines (Dynamics). – IEEE., 2022. – ISBN 9781665465274. DOI: 10.1109/dynamics56256.2022.10014982 Scopus OpenAlex
Даты:
| Опубликована online: | 18 янв. 2023 г. |
Идентификаторы БД:
| Scopus: | 2-s2.0-85147660494 |
| OpenAlex: | W4317418457 |