Most state-of-the-art text detection methods are specific to horizontal text in Latin scripts and are not fast enough for real-time applications. We introduce Segment Linking (SegLink), an oriented text detection method. The main idea is to decompose text into two locally detectable elements, namely segments and links. A segment is an oriented bounding box that covers a part of a word or text line; A link connects two adjacent segments, indicating that they belong to the same word or line. Both elements are detected densely at multiple scales by an end-to-end trained, fully-convolutional neural network. Final detections are the combinations of segments that are connected by links. Compared with previous methods, our method improves along the dimensions of accuracy, speed and ease of training. It achieves an f-measure of 75.0% on the standard ICDAR 2015 Incidental (Challenge 4) benchmark, outperforming the previous best by a large margin. It runs at over 20 FPS on 512x512 input images. In addition, our method is able to detect non-Latin text in long lines.

本研究提出了一个用于文本检测的新方法SegLink，利用基于全卷积神经网络的定向框和框连接两个局部检测元素来检测文本，并在传统的ICDAR2015任务上取得了较好的检测效果，同时可用于非拉丁文的检测。

通过连结线段检测自然图像中的方向文本