In our DAS 2016 work - '<a href="data/publications/MultiLingualOCRforIndicScripts.pdf">Multilingual OCR for Indic Scripts</a>', a
comparison of the popular Devanagari OCRs with our OCR is presented. A dataset comprising of 100 scanned images of
printed documents were used <br>

<!--<br>
Please see <a href="https://docs.google.com/spreadsheets/d/1ZntZXuWSd1TvOQDammvLu_iDW5DxDoodACELseJZBJw/edit?usp=sharing">this</a> sheet for the detailed evaluation results OR <br>

The results can be downloaded <a href="Devanagari100_Performance_Comparison.xls">here</a> <br>

<br>
-->

the dataset used is available <a href="IIIT_Hindi_100.zip">here</a>
<br>

If you are using this dataset, please cite our paper
<pre>
@InProceedings{iiit_mocr,
  author    = "Mathew, Minesh and Singh, Ajeet  and Jawahar, C.~V.",
  title     = "Multilingual OCR for Indic Scripts",
  booktitle = "DAS",
  year      = "2016"
}
</pre>