Text detection and recognition are essential components of a modern OCR
system. Most OCR approaches attempt to obtain accurate bounding boxes of text
at the detection stage, which is used as the input of the text recognition
stage. We observe that when using tight text bounding boxes as input, a text
recognizer frequently fails to achieve optimal performance due to the
inconsistency between bounding boxes and deep representations of text
recognition. In this paper, we propose Box Adjuster, a reinforcement
learning-based method for adjusting the shape of each text bounding box to make
it more compatible with text recognition models. Additionally, when dealing
with cross-domain problems such as synthetic-to-real, the proposed method
significantly reduces mismatches in domain distribution between the source and
target domains. Experiments demonstrate that the performance of end-to-end text
recognition systems can be improved when using the adjusted bounding boxes as
the ground truths for training. Specifically, on several benchmark datasets for
scene text understanding, the proposed method outperforms state-of-the-art text
spotters by an average of 2.0% F-Score on end-to-end text recognition tasks and
4.6% F-Score on domain adaptation tasks.

本文提出了一种名为 Box Adjuster 的基于强化学习的方法，用于调整每个文本边界框的形状以使其更与文本识别模型兼容。此外，当处理跨域问题时，该方法显著减少源域和目标域之间的分布不匹配。实验证明，使用调整后的边界框作为训练的基础可以提高端到端文本识别系统的性能。在多个场景文本理解基准数据集上，该方法的端到端文本识别任务的 F-Score 平均提高了 2.0％，域适应任务的 F-Score 平均提高了 4.6％，表现优于现有技术。