Tightness-Aware Evaluation Protocol for Scene Text Detection

@article{Liu2019TightnessAwareEP,
  title={Tightness-Aware Evaluation Protocol for Scene Text Detection},
  author={Yuliang Liu and Lianwen Jin and Zecheng Xie and Canjie Luo and Shuaitao Zhang and Lele Xie},
  journal={2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2019},
  pages={9604-9612}
}
  • Yuliang Liu, Lianwen Jin, +3 authors Lele Xie
  • Published in
    IEEE/CVF Conference on…
    2019
  • Computer Science
  • Evaluation protocols play key role in the developmental progress of text detection methods. There are strict requirements to ensure that the evaluation methods are fair, objective and reasonable. However, existing metrics exhibit some obvious drawbacks: 1) They are not goal-oriented; 2) they cannot recognize the tightness of detection methods; 3) existing one-to-many and many-to-one solutions involve inherent loopholes and deficiencies. Therefore, this paper proposes a novel evaluation protocol… CONTINUE READING

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

    Citations

    Publications citing this paper.
    SHOWING 1-4 OF 4 CITATIONS

    ICDAR2019 Robust Reading Challenge on Arbitrary-Shaped Text - RRC-ArT

    TedEval: A Fair Evaluation Metric for Scene Text Detectors

    VIEW 2 EXCERPTS
    CITES BACKGROUND

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 32 REFERENCES

    PixelLink: Detecting Scene Text via Instance Segmentation

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    ICDAR 2015 competition on Robust Reading

    VIEW 11 EXCERPTS
    HIGHLY INFLUENTIAL

    ICDAR 2013 Robust Reading Competition

    VIEW 8 EXCERPTS
    HIGHLY INFLUENTIAL

    Object count/area graphs for the evaluation of object detection and segmentation algorithms

    VIEW 11 EXCERPTS
    HIGHLY INFLUENTIAL

    ICDAR 2003 robust reading competitions

    VIEW 7 EXCERPTS
    HIGHLY INFLUENTIAL

    The Pascal Visual Object Classes Challenge: A Retrospective

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    An anchor-free region proposal network for Faster R-CNN-based text detection approaches

    Rotation-Sensitive Regression for Oriented Scene Text Detection

    TextBoxes++: A Single-Shot Oriented Scene Text Detector