Corpus ID: 204938100

Detecting Curve Text in the Wild: New Dataset and New Solution

@article{Yuliang2017DetectingCT,
  title={Detecting Curve Text in the Wild: New Dataset and New Solution},
  author={Liu Yu-liang and Jin Lian-wen and Zhang Shuaitao and Zhang Sheng},
  journal={arXiv: Computer Vision and Pattern Recognition},
  year={2017}
}
  • Liu Yu-liang, Jin Lian-wen, +1 author Zhang Sheng
  • Published 2017
  • Computer Science
  • arXiv: Computer Vision and Pattern Recognition
  • Scene text detection has been made great progress in recent years. The detection manners are evolving from axis-aligned rectangle to rotated rectangle and further to quadrangle. However, current datasets contain very little curve text, which can be widely observed in scene images such as signboard, product name and so on. To raise the concerns of reading curve text in the wild, in this paper, we construct a curve text dataset named CTW1500, which includes over 10k text annotations in 1,500… CONTINUE READING
    24 Citations

    Figures and Tables from this paper.

    Shape Robust Text Detection With Progressive Scale Expansion Network
    • 104
    • Highly Influenced
    • PDF
    Efficient and Accurate Arbitrary-Shaped Text Detection With Pixel Aggregation Network
    • 21
    • Highly Influenced
    • PDF
    A Multi-Object Rectified Attention Network for Scene Text Recognition
    • 82
    • PDF
    A Novel Method for Curved Scene Text Detection
    • Chao He, Junguo Lu
    • Computer Science
    • 2020 Chinese Control And Decision Conference (CCDC)
    • 2020
    A method for detecting text of arbitrary shapes in natural scenes that improves text spotting
    • 1
    • PDF
    Deep Multi-Scale Context Aware Feature Aggregation for Curved Scene Text Detection
    • 1
    HAM: Hidden Anchor Mechanism for Scene Text Detection

    References

    SHOWING 1-10 OF 26 REFERENCES
    Detecting Oriented Text in Natural Images by Linking Segments
    • 312
    • Highly Influential
    • PDF
    Detecting Text in Natural Image with Connectionist Text Proposal Network
    • 429
    • Highly Influential
    • PDF
    Deep Matching Prior Network: Toward Tighter Multi-oriented Text Detection
    • Yuliang Liu, Lianwen Jin
    • Computer Science
    • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
    • 2017
    • 176
    • Highly Influential
    • PDF
    Detecting and reading text in natural scenes
    • 412
    • Highly Influential
    • PDF
    Detecting text in natural scenes with stroke width transform
    • 1,333
    • Highly Influential
    • PDF
    Caffe: Convolutional Architecture for Fast Feature Embedding
    • 12,299
    • PDF
    Deep Direct Regression for Multi-oriented Scene Text Detection
    • 198
    • PDF
    Deep Residual Learning for Image Recognition
    • 53,640
    • PDF
    Detecting texts of arbitrary orientations in natural images
    • 518
    • PDF