CycleAugment: Efficient data augmentation strategy for handwritten text recognition in historical document images

Predicting the sequence pattern of the handwritten text images is a challenging problem due to various writing styles, insufficient training data, and also background noise appearing in the text images. The architecture of the combination between convolutional neural network (CNN) and recurrent neur...

Full description

Bibliographic Details

Published in:	Engineering and Applied Science Research
Main Authors:	Sarayut Gonwirat, Olarik Surinta
Format:	Article
Language:	English
Published:	Khon Kaen University 2022-07-01
Subjects:	convolutional recurrent neural network handwritten text recognition data augmentation deep learning training strategy
Online Access:	https://ph01.tci-thaijo.org/index.php/easr/article/view/246869/168297