Corpus ID: 19240646

SEE: Towards Semi-Supervised End-to-End Scene Text Recognition

@article{Bartz2017SEETS,
  title={SEE: Towards Semi-Supervised End-to-End Scene Text Recognition},
  author={Christian Bartz and Haojin Yang and Christoph Meinel},
  journal={ArXiv},
  year={2017},
  volume={abs/1712.05404}
}
  • Christian Bartz, Haojin Yang, Christoph Meinel
  • Published in AAAI 2017
  • Computer Science
  • Detecting and recognizing text in natural scene images is a challenging, yet not completely solved task. In recent years several new systems that try to solve at least one of the two sub-tasks (text detection and text recognition) have been proposed. In this paper we present SEE, a step towards semi-supervised neural networks for scene text detection and recognition, that can be optimized end-to-end. Most existing works consist of multiple deep neural networks and several pre-processing steps… 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 1-10 OF 18 CITATIONS

    Scene Text Detection and Recognition: The Deep Learning Era

    VIEW 4 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    ASTER: An Attentional Scene Text Recognizer with Flexible Rectification

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Adversarial Feature Enhancing Network for End-to-End Handwritten Paragraph Recognition

    VIEW 1 EXCERPT
    CITES BACKGROUND

    CRNN Based Jersey-Bib Number/Text Recognition in Sports and Marathon Images

    VIEW 2 EXCERPTS
    CITES METHODS

    Chinese Street View Text: Large-Scale Chinese Text Reading With Partially Supervised Learning

    VIEW 1 EXCERPT
    CITES METHODS

    Curved Text Detection in Natural Scene Images with Semi- and Weakly-Supervised Learning

    VIEW 1 EXCERPT
    CITES METHODS

    References

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

    End-to-End Interpretation of the French Street Name Signs Dataset

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Long Short-Term Memory

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Attention-Based Extraction of Structured Information from Street View Imagery

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Deep Residual Learning for Image Recognition

    VIEW 7 EXCERPTS
    HIGHLY INFLUENTIAL

    Robust Scene Text Recognition with Automatic Rectification

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

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

    VIEW 7 EXCERPTS
    HIGHLY INFLUENTIAL

    Reading Text in the Wild with Convolutional Neural Networks

    VIEW 8 EXCERPTS
    HIGHLY INFLUENTIAL

    Spatial Transformer Networks

    VIEW 10 EXCERPTS
    HIGHLY INFLUENTIAL