English

CITlab ARGUS for Arabic Handwriting

Computer Vision and Pattern Recognition 2014-12-19 v1 Neural and Evolutionary Computing

Abstract

In the recent years it turned out that multidimensional recurrent neural networks (MDRNN) perform very well for offline handwriting recognition tasks like the OpenHaRT 2013 evaluation DIR. With suitable writing preprocessing and dictionary lookup, our ARGUS software completed this task with an error rate of 26.27% in its primary setup.

Keywords

Cite

@article{arxiv.1412.6061,
  title  = {CITlab ARGUS for Arabic Handwriting},
  author = {Gundram Leifert and Roger Labahn and Tobias Strauß},
  journal= {arXiv preprint arXiv:1412.6061},
  year   = {2014}
}

Comments

http://www.nist.gov/itl/iad/mig/upload/OpenHaRT2013_SysDesc_CITLAB.pdf

R2 v1 2026-06-22T07:37:19.902Z