Handwritten OCR w/ confidence scores

Hello everyone,

I am currently looking for suggestions to implement a handwritten unstructured invoice parsing pipeline.

What open-source models do you recommend for handwritten ocr/parsing?
I have tried EaysOCR, Qwen, Intern-MPO, LayoutLM but they all seem to achieve poor results with handwritten invoices.

The idea is to find an open-source alternative to Textract OCR, so that I can fine-tune it when Textract performs poorly.

Thank you!

1 Like

It seems that some people are training Qwen 2 and Llama 3 Vision for handwritten characters. These models are high-performance, so they might work. Also, Microsoft’s Florence 2 and Google’s Paligemma 2 are also high-performance. I don’t know if they are suitable for handwritten character OCR…