Welcome to the new Linux Foundation Forum!

OCR and data capture software

Hello.

First of all I want to apologize for my bad English.

I need a software like Kofax Capture, ABBYY Flexicapture or Anydoc Captureit but it must run on Linux.

The main features of this software are:

- a good OCR and a good ICR

- reads barcode and QR code

- cleans the documents

- classification of documents according to content (through rules)

- ...

Anyone knows any software, please?

I've seen 2 threads about OCR but I want more than OCR (I want a data capture software). I don't want to use a online version as user Dimonline suggests.

Thanks and sorry for my English again.

Comments

  • There are several different mobile apps that offer what you've requested, but I've yet to see anyone offer it all together in one app.

    Google Goggles is the closest, although not the best.

    There is a mobile commerce solution known as Mobio that can track data too.

    Then there is http://www.scanme.com being developed.

    You may want to talk to John Harrison there...
  • Thanks mclpro but it isn't that I need. Sorry, I haven't explained very well.

    I want to scan a lot of documents and use a data capture software (as Kofax) to classify these. This software must capture other kinds of documents (for example mails) but the main documents are scanned documents. The features of the software are that I've said in the first post.

    I want a application for computer (with Linux as OS), not mobile.

    I hope I have explained myself better than before.

    Thanks
  • mclpro wrote:
    There are several different mobile apps that offer what you've requested, but I've yet to see anyone offer it all together in one app.

    Google Goggles is the closest, although not the best.

    There is a mobile commerce solution known as Mobio that can track data too.

    Then there is http://www.scanme.com being developed.

    You may want to talk to John Harrison there...
    thank you for the info for scan me software
  • OCR engines: Tesseract, cuneiform. Others are English-only, so I did not used them.

    GUI: for tesseract - FeedReeader, for cuneiform - YAGF and other.

    But these OCRs are worse than FineReader, so if you have bought FineReader, you can use wine to use it (wine does not support scanning, so you need scan to pdf with xsane and OCR this pdf with FineReader, and don't save results to .doc - OpenOffice have problems with docs generated by FineReader).
  • Ephesoft offers this in Linux. Document Capture and OCR with configurable plugins and customizable scripts: http://ephesoft.com/linux-edition
Sign In or Register to comment.