There is some overlap between OCR and OMR, but the actual processing is different:
For OCR, the steps are roughly: * preprocess image * divide the page into columns and lines * recognize the text in each line * post-process with a language model For OMR, the steps are roughly: * preprocess image * align page image with template(s) * compute differences between template and image * decide whether those differences constitute an optical mark So, there are significant differences between the two problems. Still, OCRopus implements many algorithms that are potentially useful for building an OMR system. Outside of OCRopus, my research group has been developing tools that can also be used for OMR and voting systems, although our primary focus has been in the alignment and recognition of historical documents. Have a look at "Automated OCR Ground Truth Generation" and "Image Matching for Revision Detection in Printed Historical Documents" on http://pubs.iupr.org/ Tom On Sat, Nov 15, 2008 at 09:37, adamt <[EMAIL PROTECTED]> wrote: > > Greetings Gentlemen, i was wondering if i can build a voting system > using ocropus. The input is a paper template where a circle next to > the candidate name is darkened . The system has to recognize the dots > and calculate the votes. The reason i ask this is because i have to > know if this is doable using ocropus before getting more deep into it. > Any responses/suggestions are highly appreciated. Thank you. > > > --~--~---------~--~----~------------~-------~--~----~ You received this message because you are subscribed to the Google Groups "ocropus" group. To post to this group, send email to [email protected] To unsubscribe from this group, send email to [EMAIL PROTECTED] For more options, visit this group at http://groups.google.com/group/ocropus?hl=en -~----------~----~----~----~------~----~------~--~---
