A novel text structure feature extractor for Chinese scene text detection and recognition

Xiaohang Ren, Kai Chen, Xiaokang Yang, Yi Zhou, Jianhua He, Jun Sun

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Scene text information extraction plays an important role in many computer vision applications. Unlike most existing text extraction algorithms for English texts, in this paper, we focus on Chinese texts, which are more complex in stroke and structure. To tackle this challenging problem, we propose a novel convolutional neural network (CNN) based text structure feature extractor for Chinese texts. Each Chinese character contains its specific types and combination of text structure components, which is rarely seen in backgrounds. Thus, different from the features only applicable to one text extraction stage (text detection or text recognition), the text structure component feature is suitable for both Chinese text detection and recognition. A text structure component detector (TSCD) layer is designed to detect the large amount of component types, which is the most challenging part of extracting text structure component features. Through statistical classification various types of text structure component are detected by their specially designed convolutional units in the TSCD layer. With the TSCD layer, the CNN has improvements in the accuracy and uniqueness of text feature description. In the evaluation, both text detection and recognition algorithms based on the proposed text structure feature extractor achieve state-of-the-art results in two datasets.

Original languageEnglish
Title of host publication2016 23rd International Conference on Pattern Recognition, ICPR
PublisherIEEE
Pages3380-3385
Number of pages6
ISBN (Electronic)978-1-5090-4847-2
DOIs
Publication statusPublished - 13 Apr 2017
Event23rd International Conference on Pattern Recognition: ICPR 2016 - Cancun, Mexico
Duration: 4 Dec 20168 Dec 2016

Conference

Conference23rd International Conference on Pattern Recognition
CountryMexico
CityCancun
Period4/12/168/12/16

Bibliographical note

-

Fingerprint Dive into the research topics of 'A novel text structure feature extractor for Chinese scene text detection and recognition'. Together they form a unique fingerprint.

  • Research Output

    • 2 Conference contribution

    A novel entropy-based graph signature from the average mixing matrix

    Bai, L., Rossi, L., Cui, L. & Hancock, E. R., 13 Apr 2017, 2016 23rd International Conference on Pattern Recognition, ICPR. IEEE, p. 1339-1344 6 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Open Access
    File
  • A transitive aligned Weisfeiler-Lehman subtree kernel

    Bai, L., Rossi, L., Cui, L. & Hancock, E. R., 13 Apr 2017, 2016 23rd International Conference on Pattern Recognition, ICPR. IEEE, p. 396-401 6 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Open Access
    File
  • Cite this

    Ren, X., Chen, K., Yang, X., Zhou, Y., He, J., & Sun, J. (2017). A novel text structure feature extractor for Chinese scene text detection and recognition. In 2016 23rd International Conference on Pattern Recognition, ICPR (pp. 3380-3385). IEEE. https://doi.org/10.1109/ICPR.2016.7900156