Corpus ID: 208637391

Chargrid-OCR: End-to-end Trainable Optical Character Recognition for Printed Documents using Instance Segmentation.

@article{Reisswig2019ChargridOCRET,
  title={Chargrid-OCR: End-to-end Trainable Optical Character Recognition for Printed Documents using Instance Segmentation.},
  author={C. Reisswig and Anoop R Katti and M. Spinaci and Johannes Hohne},
  journal={arXiv: Computer Vision and Pattern Recognition},
  year={2019}
}
  • C. Reisswig, Anoop R Katti, +1 author Johannes Hohne
  • Published 2019
  • Computer Science
  • arXiv: Computer Vision and Pattern Recognition
  • We present an end-to-end trainable approach for Optical Character Recognition (OCR) on printed documents. Specifically, we propose a model that predicts a) a two-dimensional character grid (\emph{chargrid}) representation of a document image as a semantic segmentation task and b) character boxes for delineating character instances as an object detection task. For training the model, we build two large-scale datasets without resorting to any manual annotation - synthetic documents with clean… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    References

    SHOWING 1-10 OF 32 REFERENCES
    Towards Unconstrained End-to-End Text Spotting
    • 20
    • PDF
    AON: Towards Arbitrarily-Oriented Text Recognition
    • 104
    • PDF
    Deep TextSpotter: An End-to-End Trainable Scene Text Localization and Recognition Framework
    • 121
    • PDF
    An End-to-End Trainable Neural Network for Image-Based Sequence Recognition and Its Application to Scene Text Recognition
    • 867
    • PDF
    Convolutional Character Networks
    • 22
    • PDF
    Robust, Simple Page Segmentation Using Hybrid Convolutional MDLSTM Networks
    • T. Breuel
    • Computer Science
    • 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR)
    • 2017
    • 17
    Chargrid: Towards Understanding 2D Documents
    • 42
    • PDF
    Binarization-free OCR for historical documents using LSTM networks
    • 12
    EAST: An Efficient and Accurate Scene Text Detector
    • 539
    • PDF
    Single Shot Text Detector with Regional Attention
    • 160
    • PDF