Scene Text Recognition with Sliding Convolutional Character Models

@article{Yin2017SceneTR,
  title={Scene Text Recognition with Sliding Convolutional Character Models},
  author={Fei Yin and Yi-Chao Wu and Xu-Yao Zhang and Cheng-Lin Liu},
  journal={CoRR},
  year={2017},
  volume={abs/1709.01727}
}
Scene text recognition has attracted great interests from the computer vision and pattern recognition community in recent years. State-of-the-art methods use concolutional neural networks (CNNs), recurrent neural networks with long short-term memory (RNN-LSTM) or the combination of them. In this paper, we investigate the intrinsic characteristics of text recognition, and inspired by human cognition mechanisms in reading texts, we propose a scene text recognition method with character models on… CONTINUE READING
  • GitHub repos referencing this paper

    • caeno-ten-descriptions

      Scripts and data files associated with our paper describing ten new species of Caenorhabditis

  • Presentations referencing similar topics