<div dir="ltr"><div>I found one recent paper that surveys a few methods and looks like a decent starting point.<br></div><div><br></div><div>2021
Handwritten Kazakh and Russian (HKR) database for text recognition
</div><div><a href="https://link.springer.com/article/10.1007/s11042-021-11399-6">https://link.springer.com/article/10.1007/s11042-021-11399-6</a></div><div><br></div><div>In that paper, they survey a few methods for OCR and suggest this performs the best in their experiments -- Attention-Based Fully Gated CNN-BGRU for Russian Handwritten Text:<br><a href="https://www.mdpi.com/2313-433X/6/12/141">https://www.mdpi.com/2313-433X/6/12/141</a></div><div><br></div><div>The HKR Data<br></div><div><a href="https://github.com/abdoelsayed2016/HKR_Dataset">https://github.com/abdoelsayed2016/HKR_Dataset</a></div><div><br></div><div>Other datasets that may be relevant if needed<br></div><div><a href="https://github.com/GregVial/CoMNIST">https://github.com/GregVial/CoMNIST</a></div><div><a href="https://www.kaggle.com/datasets/constantinwerner/cyrillic-handwriting-dataset">https://www.kaggle.com/datasets/constantinwerner/cyrillic-handwriting-dataset</a></div><div><br></div><div>- Nick<br></div></div><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">On Wed, Jul 13, 2022 at 8:07 AM Predrag Punosevac <<a href="mailto:predragp@andrew.cmu.edu">predragp@andrew.cmu.edu</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div dir="auto">Are you looking for an OCR scanner, a softer recognition, or a human who can read Cyrillic alphabet letters? Which Cyrillic alphabet are you interested in? Russian, Bulgarian, Serbian or something else. They are not 100% isomorphic due to the difference in phonetics and legacy reasons. <div dir="auto"><br></div><div dir="auto">Predrag </div></div><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">On Wed, Jul 13, 2022, 7:49 AM Artur Dubrawski <<a href="mailto:awd@cs.cmu.edu" target="_blank">awd@cs.cmu.edu</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div dir="ltr">Team,<div><br></div><div>I need guidance regarding OCR capabilities, particularly for the Cirrylic alphabet lettering. If we can read forms filled with handwritten text from images or scans, we could create a societally important research opportunity, expanding our impact in healthcare.</div><div><br></div><div>Let me know your thoughts please. </div><div><br></div><div>Cheers</div><div>Artur</div><div><br></div></div>
</blockquote></div>
</blockquote></div>