Scene Text Detection and Recognition: The Deep Learning Era

被引:179
|
作者
Long, Shangbang [1 ]
He, Xin [2 ]
Yao, Cong [3 ]
机构
[1] Carnegie Mellon Univ, Sch Comp Sci, Machine Learning Dept, Pittsburgh, PA 15213 USA
[2] ByteDance Ltd, Beijing, Peoples R China
[3] MEGVII Inc Face, Beijing, Peoples R China
关键词
Scene text; Optical character recognition; Detection; Recognition; Deep learning; Survey; OBJECT DETECTION; NEURAL-NETWORK; IMAGES; LOCALIZATION; EXTRACTION; VIDEO;
D O I
10.1007/s11263-020-01369-0
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
With the rise and development of deep learning, computer vision has been tremendously transformed and reshaped. As an important research area in computer vision, scene text detection and recognition has been inevitably influenced by this wave of revolution, consequentially entering the era of deep learning. In recent years, the community has witnessed substantial advancements in mindset, methodology and performance. This survey is aimed at summarizing and analyzing the major changes and significant progresses of scene text detection and recognition in the deep learning era. Through this article, we devote to: (1) introduce new insights and ideas; (2) highlight recent techniques and benchmarks; (3) look ahead into future trends. Specifically, we will emphasize the dramatic differences brought by deep learning and remaining grand challenges. We expect that this review paper would serve as a reference book for researchers in this field. Related resources are also collected in our Github repository (https://github.com/Jyouhou/SceneTextPapers).
引用
收藏
页码:161 / 184
页数:24
相关论文
共 50 条
  • [1] Scene Text Detection and Recognition: The Deep Learning Era
    Shangbang Long
    Xin He
    Cong Yao
    [J]. International Journal of Computer Vision, 2021, 129 : 161 - 184
  • [2] Scene text detection and recognition with advances in deep learning: a survey
    Liu, Xiyan
    Meng, Gaofeng
    Pan, Chunhong
    [J]. INTERNATIONAL JOURNAL ON DOCUMENT ANALYSIS AND RECOGNITION, 2019, 22 (02) : 143 - 162
  • [3] Scene text detection and recognition with advances in deep learning: a survey
    Xiyan Liu
    Gaofeng Meng
    Chunhong Pan
    [J]. International Journal on Document Analysis and Recognition (IJDAR), 2019, 22 : 143 - 162
  • [4] Arabic Scene Text Recognition in the Deep Learning Era: Analysis on a Novel Dataset
    Hassan, Heba
    El-Mahdy, Ahmed
    Hussein, Mohamed E.
    [J]. IEEE ACCESS, 2021, 9 : 107046 - 107058
  • [5] Deep Metric Learning for Scene Text Detection
    Zhu, Qi-Hai
    Zhu, Rui
    Li, Ning
    Yang, Yu-Bin
    [J]. 2017 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC), 2017, : 1025 - 1029
  • [6] Urdu-Text Detection and Recognition in Natural Scene Images Using Deep Learning
    Arafat, Syed Yasser
    Iqbal, Muhammad Javed
    [J]. IEEE ACCESS, 2020, 8 : 96787 - 96803
  • [7] Deep Learning Based Scene Text Detection: A Survey
    Jiang, Wei
    Zhang, Chong-Sheng
    Yin, Xu-Cheng
    [J]. Tien Tzu Hsueh Pao/Acta Electronica Sinica, 2019, 47 (05): : 1152 - 1161
  • [8] A Novel Scene Text Recognition Method Based on Deep Learning
    Wang, Maosen
    Niu, Shaozhang
    Gao, Zhenguang
    [J]. CMC-COMPUTERS MATERIALS & CONTINUA, 2019, 60 (02): : 781 - 794
  • [9] Scene Text Recognition Based on Deep Learning: A Brief Survey
    Chen, Yuxin
    Shao, Yunxue
    [J]. 2019 IEEE 11TH INTERNATIONAL CONFERENCE ON COMMUNICATION SOFTWARE AND NETWORKS (ICCSN 2019), 2019, : 688 - 693
  • [10] Deep learning for detection of text polarity in natural scene images
    Perepu, Pavan Kumar
    [J]. NEUROCOMPUTING, 2021, 431 : 1 - 6