Boosting scene character recognition by learning canonical forms of glyphs

@article{Wang2019BoostingSC,
  title={Boosting scene character recognition by learning canonical forms of glyphs},
  author={Yizhi Wang and Zhouhui Lian and Yingmin Tang and Jianguo Xiao},
  journal={International Journal on Document Analysis and Recognition (IJDAR)},
  year={2019},
  pages={1-11}
}
  • Yizhi Wang, Zhouhui Lian, +1 author Jianguo Xiao
  • Published in
    International Journal on…
    2019
  • Computer Science
  • As one of the fundamental problems in document analysis, scene character recognition has attracted considerable interests in recent years. But the problem is still considered to be extremely challenging due to many uncontrollable factors including glyph transformation, blur, noisy background, uneven illumination, etc. In this paper, we propose a novel methodology for boosting scene character recognition by learning canonical forms of glyphs, based on the fact that characters appearing in scene… CONTINUE READING

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 31 REFERENCES

    Histograms of oriented gradients for human detection

    • Navneet Dalal, Bill Triggs
    • Computer Science
    • 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)
    • 2005
    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    ASTER: An Attentional Scene Text Recognizer with Flexible Rectification

    VIEW 1 EXCERPT

    AON: Towards Arbitrarily-Oriented Text Recognition

    VIEW 1 EXCERPT

    An End-to-End Trainable Neural Network for Image-Based Sequence Recognition and Its Application to Scene Text Recognition

    VIEW 2 EXCERPTS

    Focusing Attention: Towards Accurate Text Recognition in Natural Images

    VIEW 1 EXCERPT

    Learning Spatially Embedded Discriminative Part Detectors for Scene Character Recognition

    VIEW 2 EXCERPTS

    Image-to-Image Translation with Conditional Adversarial Networks

    VIEW 1 EXCERPT