The task is to convert questionnaires filled in with pen on paper into records (output could be a csv file or excel sheet, in a database or the like) for analysis.

I have tried to find a solution on the web, but all that turns up is companies that would like to sell us a scanner+software. All we really need is the software part.

The program should be able to recognize a form, and there by know where each field is. For fields with check boxes, it will recognize which fields are filled in. In text fields it will try to recognize the text and display the result, as the text will be handwritten, it is not expected to be perfect.

The user would get each form up on the screen and can verify the contents. The program highlights each field on the form as the user tabs through it.

I know this exists in combination with a scanner, but does it exist as standalone software?

The software can be open source or commercial, hopefully a license will be less than USD200, but it is not a hard limit. Platform is windows or linux (if mac is the only option, then that will be ok as well).

If it is of any importance we use a Konica Minolta BizHub 454 (printer/scanner name from memory).

  • The program should be able to recognize a form, and there by know where each field is Is that completely free-form, or are you OK if you have to predefine forms in the software (this form contains these fields in these positions)? It does not sound very useful to me if everything is undetermined, you would want to make sure that the correct data ends up in the correct field names ...
    – user416
    Oct 27 '15 at 10:30
  • It is of course ok to have to tell the software where each forms fields are before handling the forms, and that there need to be markers of the forms so that it can aligned is also ok. If the program requires the forms to be generated from it (and not e.g. word) is also ok.
    – Bent
    Oct 27 '15 at 10:53

If you are about to create a survey, check out SDAPS which is an acronym for "Scripts for data acquisition with paper based surveys".

The workflow is depicted here: sdaps workflow

The feature list is impressive:

  • Open Source Software; use and modify it as you like (subject to the GPLv3+/LPPLv1.3c+) Optical mark recognition (OMR) from scanned data Imports most formats including PDF and even photographs (version 1.1.7)

  • OpenDocument text (ODT) for creating questionnaires

  • LaTeX class for creating questionnaires Supports any paper size Multipage questionnaires, both simplex and duplex printing (up to 9999 pages with "code128" and "qr" style) Different kinds of questions:

    • A mark type question (a score)
    • A choice of many, that may also include freeform fields
    • Freeform fields
    • The LaTeX class also supports more compact matrix configurations for these.
  • Creation of PDF reports for printout

    • Also supports creating reports of only partial result sets with arbitrary filters
  • Export of data to CSV files for further analysis (excluding image data)

  • Import of additional results from other sources. With this it is for example possible to merge data aquired via a webpage at a later point. A GUI application to check the recognition and correct errors Written in Python using a modular and extensible design

The code is in Python and available here: https://github.com/sdaps/sdaps

There is a GUI which allows the user to "correct" the OCR. gui

  • That definitly looks promising. I'll have a look into it, thanks.
    – Bent
    Oct 27 '15 at 13:34

My experience with OCR of scanned paper documents is that when it comes to OCR quality (correctness) nothing beats FineReader (software) as such. It does have a GUI for correcting OCR results and exporting scan result in a variety of formats.


You can convert digital and handwritten surveys to Excel using DocuClipper

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

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