Recently, segmentation-based methods are quite popular in scene text detection, which mainly contain two steps: text kernel segmentation and expansion. However, the segmentation process only considers each pixel independently, and the expansion process is difficult to achieve a favorable accuracy-speed trade-off. In this paper, we propose a context-aware and boundary-guided network (CBN) to tackle these problems. In CBN, a basic text detector is first used to predict initial segmentation results. Then, we propose a context-aware module to enhance text kernel feature representations, which considers both global and local contexts. Finally, we introduce a boundary-guided module to expand enhanced text kernels adaptively with only the pixels on the contours, which not only obtains accurate text boundaries but also keeps high speed, especially on high-resolution output maps. In particular, with a lightweight backbone, the basic detector equipped with our proposed CBN achieves state-of-the-art results on several popular benchmarks, and our proposed CBN can be plugged into several segmentation-based methods. Code will be available on https://github.com/XiiZhao/cbn.pytorch.

近年来，基于分割的方法在场景文本检测中非常流行，主要包含两个步骤：文本内核分割和扩展。然而，分割过程仅独立地考虑每个像素，并且扩展过程难以实现有利的精度与速度权衡。在本文中，我们提出了一种上下文感知和边界引导网络（CBN）来解决这些问题。在 CBN 中，首先使用基本文本检测器来预测初始分割结果。然后，我们提出了一个上下文感知模块来增强文本内核特征表示，该模块考虑了全局和局部上下文。最后，我们引入了一个边界引导模块，仅使用轮廓上的像素自适应地扩展增强文本内核，不仅获得准确的文本边界，而且保持高速，尤其是在高分辨率输出地图上。特别是，凭借轻量级主干网，配备我们提出的 CBN 的基本检测器在几个流行的基准测试中实现了最先进的结果，并且我们提出的 CBN 可以插入到几种基于分割的方法中。代码将在 https://github.com/XiiZhao/cbn.pytorch 上提供。