Scene Text Detection with Inception Text Proposal Generation Module

被引:1
|
作者
Zhang, Hang [1 ,2 ]
Liu, Jiahang [1 ]
Chen, Tieqiao [1 ,2 ]
机构
[1] Chinese Acad Sci, Xian Inst Opt & Precis Mech, Xian 710119, Shaanxi, Peoples R China
[2] Univ Chinese Acad Sci, Beijing 100049, Peoples R China
来源
ICMLC 2019: 2019 11TH INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND COMPUTING | 2019年
关键词
Text detection; convolutional neural network; region proposal network; natural images;
D O I
10.1145/3318299.3318373
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Most scene text detection methods based on deep learning are difficult to locate texts with multi-scale shapes. The challenges of scale robust text detection lie in two aspects: 1) scene text can be diverse and usually exists in various colors, fonts, orientations, languages, and scales in natural images. 2) Most existing detectors are difficult to locate text with large scale change. We propose a new Inception-Text module and adaptive scale scaling test mechanism for multi-oriented scene text detection. the proposed algorithm enhances performance significantly, while adding little computation. The proposed method can flexibly detect text in various scales, including horizontal, oriented and curved text. The proposed algorithm is evaluated on three recent standard public benchmarks, and show that our proposed method achieves the state-of-the-art performance on several benchmarks. Specifically, it achieves an F-measure of 93.3% on ICDAR2013, 90.47% on ICDAR2015 and 76.08%(1) on ICDAR2017 MLT.
引用
收藏
页码:456 / 460
页数:5
相关论文
共 50 条
  • [21] Find More Accurate Text Boundary for Scene Text Detection
    Pan, Runqiu
    Li, Zezhou
    Zhu, Anna
    2022 26TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2022, : 1421 - 1427
  • [22] CentripetalText: An Efficient Text Instance Representation for Scene Text Detection
    Sheng, Tao
    Chen, Jie
    Lian, Zhouhui
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021), 2021, 34
  • [23] Video Scene Text Frames Categorization for Text Detection and Recognition
    Qin, Longfei
    Shivakumara, Palaiahnakote
    Lu, Tong
    Pal, Umapada
    Tan, Chew Lim
    2016 23RD INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2016, : 3886 - 3891
  • [24] Using of Attention for Scene Text Detection
    Wang Y.
    Gu X.
    Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics, 2021, 33 (12): : 1908 - 1915
  • [25] Review of Scene Text Detection and Recognition
    Han Lin
    Peng Yang
    Fanlong Zhang
    Archives of Computational Methods in Engineering, 2020, 27 : 433 - 454
  • [26] Summary of Scene Text Detection and Recognition
    Qin, Yao
    Zhang, Zhi
    PROCEEDINGS OF THE 15TH IEEE CONFERENCE ON INDUSTRIAL ELECTRONICS AND APPLICATIONS (ICIEA 2020), 2020, : 85 - 89
  • [27] Scene text detection and recognition: a survey
    Naiemi, Fatemeh
    Ghods, Vahid
    Khalesi, Hassan
    MULTIMEDIA TOOLS AND APPLICATIONS, 2022, 81 (14) : 20255 - 20290
  • [28] Scene Text Detection with Scribble Line
    Zhang, Wenqing
    Qiu, Yang
    Liao, Minghui
    Zhang, Rui
    Wei, Xiaolin
    Bai, Xiang
    DOCUMENT ANALYSIS AND RECOGNITION, ICDAR 2021, PT IV, 2021, 12824 : 79 - 94
  • [29] Elite Loss for scene text detection
    Zhao, Xu
    Zhao, Chaoyang
    Guo, Haiyun
    Zhu, Yousong
    Tang, Ming
    Wang, Jinqiao
    NEUROCOMPUTING, 2019, 333 : 284 - 291
  • [30] A Fast Method for Scene Text Detection
    Fang, Qing
    Yang, Yanping
    Chen, Yali
    Yao, Xiaoyu
    COMPUTER VISION, PT I, 2017, 771 : 738 - 747