CITlab ARGUS for Arabic Handwriting
arXiv:1412.6061v16 citations
Originality Synthesis-oriented
AI Analysis
This work addresses handwriting recognition for Arabic script, presenting a competitive result on a specific benchmark.
The paper tackled offline Arabic handwriting recognition using multidimensional recurrent neural networks (MDRNN) and achieved an error rate of 26.27% on the OpenHaRT 2013 evaluation DIR task with preprocessing and dictionary lookup.
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.