Take the 2-minute tour ×
MathOverflow is a question and answer site for professional mathematicians. It's 100% free, no registration required.

I am in the process of scanning a large collection of handwritten notes. They consist of diagrams and formulae with a relatively small proportion of actual words. Of course it would be hopeless to get an OCR program to digest the diagrams or formulae, but it would be useful if I could get one to find and transcribe enough of the words to build an index. Has anyone tried this kind of thing?

share|improve this question
2  
Tangentially related: meta.math.stackexchange.com/questions/3731/… (It is not entirely hopeless to get OCR to digest formulae.) –  Willie Wong Apr 30 '12 at 8:08
3  
Use wetware. It needn't even be grad students: ordinary MSc students work fine for this. They will transcribe most of the formulas too, though usually not the diagrams. –  Zsbán Ambrus Apr 30 '12 at 9:21
1  
I thought MSc students are also grad students, by definition. Anyway, if you do opt for "wetware", be sparing... :) –  Felix Goldberg Apr 30 '12 at 11:29
3  
The question is specific to mathematics because OCR systems use heuristics that may well break if the words are interspersed between non-words. If many people had used many different systems then they would probably have information about which systems were more or less affected by this issue. But perhaps the relevant experiments have not been done yet. –  Neil Strickland Apr 30 '12 at 13:47
2  
This is much more suited to stack overflow, voting to close. –  Igor Rivin Apr 30 '12 at 17:49
show 3 more comments

3 Answers

I recommend www.inftyreader.org. They have a trial version, with long enough trial period to do a big project. I've used InftyReader on a flakey old laptop and it did a pretty good job for a math book reissue. It took about half an hour or so to do each 40 page bundle of the disassembled book. It made systematic errors in the tex, many of which I was able to correct with some awk commands, but of course I still had to go through the whole thing tediously. I was not going for perfection, but just for something editable, and I think it came out better than required for this purpose.

share|improve this answer
3  
The notes are handwritten I assume the book was not. –  quid May 1 '12 at 1:09
4  
While I am very happy to have learned about the existence of InftyReader, I can confirm that it was not able to digest my handwritten notes. –  Neil Strickland May 1 '12 at 7:43
add comment

To supplement Bob Terrell's post, here is an example from InftyReader.

Snippet from an input image, scanned at 600dpi:


  Input
Snippet from output of the corresponding LaTeX produced by InftyReader:
  LaTeX Output
It's not perfect—$\partial z \partial \bar{z}$ becomes $\partial z k$—but it's pretty impressive!

share|improve this answer
3  
Did you try it with something handwritten, too? This iw what the question seems to be about. –  quid May 1 '12 at 1:11
1  
@quid: No. I am less interested in the question Neil posed than I am in learning what this neat software can do. InftyReader is designed to work on scanned images of printed mathematics, not handwriting. –  Joseph O'Rourke May 1 '12 at 1:44
add comment

I am searching for an OCR too to save my handwritten M.Sc notes. So far I have come to realize that I might have to learn LaTeX or a TeX software to write and compile notes into postscript or pdfs of all my notes. But learning LaTeX is a big challenge. Its like learning a big programming language to master it will take time.

share|improve this answer
1  
It's really not that bad. You use the basics 90% of the time, and they don't take more than an hour to learn. –  Charles Nov 15 '12 at 17:47
2  
This is not an answer to the original question –  Yemon Choi Nov 15 '12 at 19:57
    
Read question again. I dont think there are OCR software out there that will actually extract text from image files of handwritten text. Tried a couple of online OCR's and tesseract software. No Success so far. They are all designed to extract text from either Typewritten/Printed material or handwritten characters entered directly into a computer interface using a digital pen or a mouse. –  Fazal Karim Nov 21 '12 at 10:02
    
Some that are there like SimpleOCR need to learn your handwritting before converting. The results in my case were highly discouraging. –  Fazal Karim Nov 21 '12 at 11:56
    
Hi Fazal: I don't disagree with what you have written, but as Yemon points out, your post is not an answer to the original question, whereas MathOverflow is very specifically a Q&A site. –  Theo Johnson-Freyd Jun 25 '13 at 3:16
add comment

Your Answer

 
discard

By posting your answer, you agree to the privacy policy and terms of service.

Not the answer you're looking for? Browse other questions tagged or ask your own question.