|
ИСТИНА |
Войти в систему Регистрация |
ИПМех РАН |
||
Handwritten text generation and strikethrough characters augmentationстатья Исследовательская статья
- Авторы: Shonenkov A.V., Karachev D.K., Novopoltsev M.Y., Potanin M.S., Dimitrov D.V., Chertok A.V.
- Журнал: Computer Optics
- Том: 46
- Номер: 3
- Год издания: 2022
- Первая страница: 455
- Последняя страница: 464
- DOI: 10.18287/2412-6179-co-1049
- Аннотация: We introduce two data augmentation techniques, which, used with a Resnet-BiLSTM-CTC network, significantly reduce Word Error Rate and Character Error Rate beyond best-reported results on handwriting text recognition tasks. We apply a novel augmentation that simulates strikethrough text (HandWritten Blots) and a handwritten text generation method based on printed text (StackMix), which proved to be very effective in handwriting text recognition tasks. StackMix uses weakly-supervised framework to get character boundaries. Because these data augmentation techniques are independent of the network used, they could also be applied to enhance the performance of other networks and approaches to handwriting text recognition. Extensive experiments on ten handwritten text datasets show that HandWritten Blots augmentation and StackMix significantly improve the quality of handwriting text recognition models.
- Добавил в систему: Димитров Денис Валерьевич
Прикрепленные файлы
| № | Имя | Описание | Имя файла | Размер | Добавлен |
|---|---|---|---|---|---|
| 1. | Полный текст | Текст статьи | Handwritten_text_generation_and_strikethrough_characters_au… | 1,3 МБ | 27 августа 2022 [DimitrovDV] |