Corpus ID: 139102754

TextCohesion: Detecting Text for Arbitrary Shapes

@article{Wu2019TextCohesionDT,
  title={TextCohesion: Detecting Text for Arbitrary Shapes},
  author={Weijia Wu and Jici Xing and Hong Zhou},
  journal={ArXiv},
  year={2019},
  volume={abs/1904.12640}
}
  • Weijia Wu, Jici Xing, Hong Zhou
  • Published in ArXiv 2019
  • Computer Science
  • In this paper, we propose a pixel-wise method named TextCohesion for scene text detection, which splits a text instance into five key components: a Text Skeleton and four Directional Pixel Regions. [...] Key Method A confidence scoring mechanism is designed to filter characters that are similar to text. Our method can integrate text contexts intensively when backgrounds are complex. Experiments on two curved challenging benchmarks demonstrate that TextCohesion outperforms state-of-the-art methods, achieving the…Expand Abstract

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

    Figures, Tables, and Topics from this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 46 REFERENCES

    EAST: An Efficient and Accurate Scene Text Detector

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Scene Text Detection with Supervised Pyramid Context Network

    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL

    Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Character Region Awareness for Text Detection

    Mask R-CNN With Pyramid Attention Network for Scene Text Detection

    Towards Robust Curve Text Detection With Conditional Spatial Expansion

    Arbitrary-Oriented Scene Text Detection via Rotation Proposals

    VIEW 1 EXCERPT

    Cascaded Segmentation-Detection Networks for Text-Based Traffic Sign Detection

    VIEW 1 EXCERPT