Recently, scene text detection has received significant attention due to its
wide application. However, accurate detection in complex scenes of multiple
scales, orientations, and curvature remains a challenge. Numerous detection
methods adopt the Vatti clipping (VC) algorithm for multiple-instance training
to address the issue of arbitrary-shaped text. Yet we identify several bias
results from these approaches called the "shrinked kernel". Specifically, it
refers to a decrease in accuracy resulting from an output that overly favors
the text kernel. In this paper, we propose a new approach named Expand Kernel
Network (EK-Net) with expand kernel distance to compensate for the previous
deficiency, which includes three-stages regression to complete instance
detection. Moreover, EK-Net not only realize the precise positioning of
arbitrary-shaped text, but also achieve a trade-off between performance and
speed. Evaluation results demonstrate that EK-Net achieves state-of-the-art or
competitive performance compared to other advanced methods, e.g., F-measure of
85.72% at 35.42 FPS on ICDAR 2015, F-measure of 85.75% at 40.13 FPS on CTW1500.

在本文中，我们提出了一种名为 Expand Kernel Network (EK-Net) 的新方法，该方法通过采用扩展内核距离解决了现有方法中存在的偏差问题，包括三阶段回归完成实例检测。此外，EK-Net 不仅可以实现任意形状文本的精确定位，还能在性能和速度之间取得平衡。评估结果表明，与其他先进方法相比，EK-Net 在 ICDAR 2015 上以 35.42 FPS 的 F-measure 为 85.72%，在 CTW1500 上以 40.13 FPS 的 F-measure 为 85.75%。