Forms recognition software

[knuha]

Does anybody know any software that can read scanned paper forms (questionnaires) and decipher the information in them. I have about 110,000 forms that I need to extract data from. These forms are scanned as TIFF-files. The forms have alignment-marks that help orientation. I must be able to define names for the different fields on the form and then let the software decipher their content. Most of these fields are simple ticked/not ticked fields, but some of them are handwritten numbers. I would (of course) prefer free software, but low cost commercial SW is also of interest. This is a part of a non-commercial research project. And for those of you who wander, the forms are already scanned and read by a commercial Windows system. But the quality is low and I would like to try this with Linux software.

Knut

[oz]

I can't answer the question directly, but here are a couple of sites you can check that might have something for you:

Windows and OS X Software Alternatives | Linux App Finder

The table of equivalents / replacements / analogs of Windows software in Linux. (Official site of the table)

[Marsolin]

It sounds like you need to use an OCR software package to create text files from the scans and then run those text files through a script to look for the data that you want. I'd suggest trying a few pages through one of the OCR programs to see if the data you want is being recognized correctly.