OCR graph paper

Question

I would like to take a pdf of a scanned graph paper notebook (with handwriting) and turn it into a text file.

How can I do this?

Thanks

Answer 1

Check out an OCR library, like OCRopus. I don't think it takes PDF, so you may have to convert it to a TIFF or JPEG first.

Answer 2

If it is the notebook as a PDF file you could e-mail it to a gmail account and then gmail allows you to "view" the PDF from within your browser as an HTML file. Still the pages remain images.

If you would like the text out of it OCR might work but it may also be uncapable of getting the text out of it.

Answer 3

There are OCR libraries that convert typing (OCRopus, tesseract, etc.)

There are also Java based handwriting libraries. I am not sure if OCRopus has that ability, one library I was looking into to do handwriting recognition was:

Online Video

Java Neural Networks

Conceivably you could take the pdf, convert it into a tiff if need be (according to the software), and it would give you something..

Good luck!