A comparison of 1D and 2D LSTM architectures for the recognition of handwritten Arabic

@inproceedings{Yousefi2015ACO,
  title={A comparison of 1D and 2D LSTM architectures for the recognition of handwritten Arabic},
  author={Mohammad Reza Yousefi and Mohammad Reza Soheili and Thomas M. Breuel and Didier Stricker},
  booktitle={DRR},
  year={2015}
}
In this paper, we present an Arabic handwriting recognition method based on recurrent neural network. We use the Long Short Term Memory (LSTM) architecture, that have proven successful in different printed and handwritten OCR tasks. Applications of LSTM for handwriting recognition employ the two-dimensional architecture to deal with the variations in both vertical and horizontal axis. However, we show that using a simple pre-processing step that normalizes the position and baseline of letters… CONTINUE READING
Highly Cited
This paper has 20 citations. REVIEW CITATIONS
14 Citations
39 References
Similar Papers

Citations

Publications citing this paper.
Showing 1-10 of 14 extracted citations

References

Publications referenced by this paper.
Showing 1-10 of 39 references

A Comprehensive Survey on Image Binarization Techniques

  • N. Chaki, S. H. Shaikh, K. Saeed
  • [Exploring Image Binarization Techniques, Studies…
  • 2014

Similar Papers

Loading similar papers…