Combination of multiple aligned recognition outputs using WFST and LSTM

@article{Azawi2015CombinationOM,
  title={Combination of multiple aligned recognition outputs using WFST and LSTM},
  author={Mayce Ibrahim Ali Al Azawi and Marcus Liwicki and Thomas M. Breuel},
  journal={2015 13th International Conference on Document Analysis and Recognition (ICDAR)},
  year={2015},
  pages={31-35}
}
The contribution of this paper is a new strategy of integrating multiple recognition outputs of diverse recognizers. Such an integration can give higher performance and more accurate outputs than a single recognition system. The problem of aligning various Optical Character Recognition (OCR) results lies in the difficulties to find the correspondence on character, word, line, and page level. These difficulties arise from segmentation and recognition errors which are produced by the OCRs… CONTINUE READING
4 Citations
10 References
Similar Papers

References

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

Binary Codes Capable of Correcting Deletions, In­ sertions, and Reversals,

  • V. Levenshtein
  • Soviet P hysics-Doklady,
  • 1966

Similar Papers

Loading similar papers…