Abstract
We study the problem of extracting text instance contour information from images and use it to assist scene text detection. We propose a novel and effective framework for this and experimentally demonstrate that: (1) A CNN that can be effectively used to extract instance-level text contour from natural images. (2) The extracted contour information can be used for better scene text detection. We propose two ways for learning the contour task together with the scene text detection: (1) as an auxiliary task and (2) as multi-task cascade. Extensive experiments with different benchmark datasets demonstrate that both designs improve the performance of a state-of-the-art scene text detector and that a multi-task cascade design achieves the best performance.
Abstract (translated)
我们研究了从图像中提取文本实例轮廓信息的问题，并用它来辅助场景文本检测。我们为此提出了一个新颖有效的框架，并通过实验证明：（1）CNN可以有效地用于从自然图像中提取实例级文本轮廓。 （2）提取的轮廓信息可用于更好的场景文本检测。我们提出了两种学习轮廓任务的方法以及场景文本检测：（1）作为辅助任务和（2）作为多任务级联。使用不同基准数据集的大量实验表明，这两种设计都可以提高现有技术的场景文本检测器的性能，并且多任务级联设计可以实现最佳性能。
URL
https://arxiv.org/abs/1809.03050
