华东师范大学学报(自然科学版) ›› 2018, Vol. 2018 ›› Issue (5): 1-16.doi: 10.3969/j.issn.1000-5641.2018.05.001

• 综述论文 •    下一篇

基于深度学习的场景文字检测研究进展

余若男, 黄定江, 董启文   

  1. 华东师范大学 数据科学与工程学院, 上海 200062
  • 收稿日期:2018-06-27 出版日期:2018-09-25 发布日期:2018-09-26
  • 通讯作者: 黄定江,男,教授,研究方向为机器学习与人工智能及其在计算金融等跨领域中大数据的解析和应用.E-mail:djhuang@dase.ecnu.edu.cn. E-mail:djhuang@dase.ecnu.edu.cn
  • 作者简介:余若男,女,硕士研究生,研究方向为深度学习与目标检测.E-mail:yrn130814232@163.com.
  • 基金资助:
    国家自然科学基金(11501204);国家自然科学基金广东省联合项目(U1711262)

Survey on scene text detection based on deep learning

YU Ruo-nan, HUANG Ding-jiang, DONG Qi-wen   

  1. School of Data Science and Engineering, East China Normal University, Shanghai 200062, China
  • Received:2018-06-27 Online:2018-09-25 Published:2018-09-26

摘要: 在大数据驱动应用的背景下,随着计算机硬件性能的提高,基于深度学习的目标检测和图像分割算法冲破了传统算法的瓶颈,成为当前计算机视觉领域的主流算法.而场景文字检测任务受到目标检测和图像分割算法发展的影响,近年来也有了极大的突破.这篇综述的目的主要有3个方面:介绍近5年场景文字检测工作进展;比较分析先进算法的优点及不足;总结该领域相关的基准数据集和评价方法.

关键词: 文字检测, 深度学习, 自然场景, 目标检测, 图像分割

Abstract: With improvements in computer hardware performance, object detection, and image segmentation algorithms (based on deep learning) have broken the bottlenecks posed by traditional algorithms in big data-driven applications and become the mainstream algorithms in the field of computer vision. In this context, scene text detection algorithms have made great breakthroughs in recent years. The objectives of this survey are three-fold:introduce the progress of scene text detection over the past 5 years, compare and analyze the advantages and limitations of advanced algorithms, and summarize the relevant benchmark datasets and evaluation methods in the field.

Key words: text detection, deep learning, natural scene, object detection, image segmentation

中图分类号: