Reading Text in the Wild with Convolutional Neural Networks

@article{Jaderberg2015ReadingTI,
  title={Reading Text in the Wild with Convolutional Neural Networks},
  author={Max Jaderberg and K. Simonyan and A. Vedaldi and Andrew Zisserman},
  journal={International Journal of Computer Vision},
  year={2015},
  volume={116},
  pages={1-20}
}
  • Max Jaderberg, K. Simonyan, +1 author Andrew Zisserman
  • Published 2015
  • Computer Science
  • International Journal of Computer Vision
  • In this work we present an end-to-end system for text spotting—localising and recognising text in natural scene images—and text based image retrieval. [...] Key Method For the recognition and ranking of proposals, we train very large convolutional neural networks to perform word recognition on the whole proposal region at the same time, departing from the character classifier based systems of the past.Expand Abstract
    Towards End-to-End Text Spotting with Convolutional Recurrent Neural Networks
    75
    Learning with Weak Annotations for Text in the Wild Detection and Recognition
    Deep Neural Network for Semantic-based Text Recognition in Images
    2
    Reading Scene Text in Deep Convolutional Sequences
    152
    Towards End-to-End Text Spotting in Natural Scenes
    2
    STN-OCR: A single Neural Network for Text Detection and Text Recognition
    32
    Review network for scene text recognition
    3
    A Multi-task Network for Localization and Recognition of Text in Images
    Visual Attention Models for Scene Text Recognition
    30

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 78 REFERENCES
    Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition
    490
    End-to-end text recognition with convolutional neural networks
    667
    Deep Features for Text Spotting
    462
    End-to-end scene text recognition
    719
    Using text-spotting to query the world
    43
    Scene Text Recognition using Higher Order Language Priors
    419
    Supervised mid-level features for word image representation
    80