Abstract
One of the factors limiting the performance of handwritten text recognition (HTR) for stenography is the small amount of annotated training data. To alleviate the problem of data scarcity, modern HTR methods often employ data augmentation. However, due to specifics of the stenographic script, such settings may not be directly applicable for stenography recognition. In this work, we study 22 classical augmentation techniques, most of which are commonly used for HTR of other scripts, such as Latin handwriting. Through extensive experiments, we identify a group of augmentations, including for example contained ranges of random rotation, shifts and scaling, that are beneficial to the use case of stenography recognition. Furthermore, a number of augmentation approaches, leading to a decrease in recognition performance, are identified. Our results are supported by statistical hypothesis testing. Links to the publicly available dataset and codebase are provided.
Abstract (translated)
手写文本识别(stenography)对于训读方法的性能限制之一是训练数据量的微小。为了缓解数据稀缺的问题,现代训读方法常常采用数据增强。然而,由于训读脚本的特殊性质,这些设置可能不能直接适用于stenography识别。在本研究中,我们研究了22种经典的增强技术,其中大多数用于其他脚本,如拉丁手写体。通过广泛的实验,我们识别了一种群体增强方法,包括例如随机旋转、位移和缩放的范围,对于stenography识别的应用有益。此外,我们识别了一些增强方法,导致识别性能下降。我们的结果受到了统计假设检验的支持。提供了公开可用的数据集和代码链接。
URL
https://arxiv.org/abs/2303.02761