Abstract

Scene texts contain rich semantic information which may be used in many vision-based applications, and consequently detecting and recognizing scene texts have received increasing attention in recent years. In this paper, we first introduce the history and progress of scene text detection and recognition, and classify conventional methods in detail and point out their advantages as well as disadvantages. After that, we study these methods and illustrate the corresponding key issues and techniques, including loss function, multi-orientation, language model and sequence labeling. Finally, we describe commonly used benchmark datasets and evaluation protocols, based on which the performance of representative scene text detection and recognition methods are analyzed and compared.

中文翻译：

---

场景文本检测与识别的回顾

摘要

场景文本包含丰富的语义信息，可以在许多基于视觉的应用程序中使用，因此近年来，检测和识别场景文本已受到越来越多的关注。在本文中，我们首先介绍了场景文本检测和识别的历史和进展，并对传统方法进行了详细分类，并指出了它们的优缺点。之后，我们将研究这些方法并说明相应的关键问题和技术，包括损失函数，多方向，语言模型和序列标记。最后，我们描述了常用的基准数据集和评估协议，在此基础上对代表性场景文本检测和识别方法的性能进行了分析和比较。