Recently, methods based on deep learning have dominated the field of text recognition. With a large number of training data, most of them can achieve the state-of-the-art performances. However, it is hard to harvest and label sufficient text sequence images from the real scenes. To mitigate this issue, several methods to synthesize text sequence images were proposed, yet they usually need complicated preceding or follow-up steps. In this work, we present a method which is able to generate infinite training data without any auxiliary pre/post-process. We tackle the generation task as an image-to-image translation one and utilize conditional adversarial networks to produce realistic text sequence images in the light of the semantic ones. Some evaluation metrics are involved to assess our method and the results demonstrate that the caliber of the data is satisfactory. The code and dataset will be publicly available soon.

中文翻译：

---

生成用于识别的文本序列图像

近来，基于深度学习的方法已经主导了文本识别领域。借助大量的培训数据，大多数培训数据都可以达到最新水平。但是，很难从真实场景中收获和标记足够的文本序列图像。为了减轻这个问题，提出了几种合成文本序列图像的方法，但是它们通常需要复杂的先前或后续步骤。在这项工作中，我们提出了一种无需任何辅助的前/后处理即可生成无限训练数据的方法。我们将生成任务作为一种图像到图像的翻译解决，并利用条件对抗网络根据语义图像来生成逼真的文本序列图像。涉及一些评估指标来评估我们的方法，结果表明数据的质量令人满意。该代码和数据集将很快公开提供。