1

Is there an OCR application which recognizes different areas of text on a page, and in different modes, e.g. outlines made out by other visual elements, or white-on-black vs black-on-white or even differences in hue - and outputs a document (say ODT or DOCX) with text placed in those areas, perhaps even arranged similarly to the arrangement on the page?

Specifically, something that in a screenshot of the following:

    T    HE#QUI   CK#BR
   O W   N     # F     O
  X   #  J     U M       
 P     E D#OVER  #       
 THE#LAZ Y     # D       
 O     G #     # #     #
 #     # ######   #####

would find both the strings "ABC" and the string "THE#QUICK#BROWN#FOX#UMPED#OVER#THE#LAZY#DOG############". And with support for other such pathologies.

License: Any; libre preferred.
Price: Any; gratis preferred.
Hardware: x86_64.
OS: Any popular one, with the order of preference being Linux, Windows, BSD, MacOS.

Your Answer

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

Browse other questions tagged or ask your own question.