Is there any software (preferably backed by open-source components) for extracting textual product information from scanned retailer's product catalogs (i.e. bitmaps).

And what is the name of the technical sub-discipline that looks into these types of problems: they presumably require OCR plus some higher-level guided image analysis.

Here is a sample input:

enter image description here

  • I would call that a flyer rather than a catalogue - catalogue is mainly text something like UPC - vendor code - name - size - price - unit price - extra codes usually whereas a flyer is graphics with sale prices. – Nick Dickinson-Wilde Jul 19 '14 at 17:45
  • @NickWilde Yes, please feel free to edit (as I am not a native speaker). – Drux Jul 20 '14 at 18:48

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.