Yes, the letters are not only adjacent, but connected, as in a typical legible signatures (English), or in a handwritten (cursive) historical document. One of the links in my original post addresses this kind of handwritten document.
On Fri, Feb 3, 2012 at 7:18 AM, Merve Temizer <[email protected]> wrote: > Hello, > Are the letters adjacent to each other in words? > If not, > Tesseract is successfull on recognizing handwriting. > There are little problems for example if you write "lt" tesseract might > understand "H". > Thus i looked for a way and explored that, with support of opencv, it is > possible to have single letter images. > And give the letters to tesseract one by one. > I have some more idea about how to exceed recognition problems which is > useful if one can say the program the language of text. > I have not an implementation because i used to need a adjacent text > recognizer and could not find a solution for it yet. > > 2012/2/1 Pohorsky, Steve <[email protected]> > > This is addressed to those of you that are students at a university or >> those who work with students. >> >> >> >> I have a specific OCR task that likely involves some experimentation. It >> involves OCR of the cursive handwriting of a single individual. Based on >> what I have done with tesseract and what I have read in this forum, the >> task likely involves training tesseract on the handwriting of that >> individual, either based on whole words or based on individual characters. >> >> >> >> >> >> Here is my >> >> Request: >> >> * If anybody has recommendations about how to OCR cursive handwriting or >> thinks it is not feasible, please reply to this post. >> >> * If anybody wants to discuss the practical details of doing this task, >> funding an internship or project, please email me directly at >> [email protected] >> >> >> >> Background: >> >> The following posts may provide perspective: >> >> >> http://groups.google.com/group/tesseract-ocr/browse_thread/thread/62c9cd7db19742c7/8704b25ed6eb9fdc?hl=en&lnk=gst&q=julha#8704b25ed6eb9fdc >> >> >> >> >> http://groups.google.com/group/tesseract-ocr/browse_thread/thread/f04c5f68094f74c2/1b2fe53ca9bb5456?hl=en&lnk=gst&q=handwriting+words#1b2fe53ca9bb5456 >> >> >> >> >> >> This communication, including any attachments, may contain information >> that is proprietary, privileged, confidential or legally exempt from >> disclosure. If you are not a named addressee, you are hereby notified that >> you are not authorized to read, print, retain a copy of or disseminate any >> portion of this communication without the consent of the sender and that >> doing so may be unlawful. If you have received this communication in error, >> please immediately notify the sender via return e-mail and delete it from >> your system. >> >> -- >> You received this message because you are subscribed to the Google >> Groups "tesseract-ocr" 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/tesseract-ocr?hl=en >> > > -- > You received this message because you are subscribed to the Google > Groups "tesseract-ocr" 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/tesseract-ocr?hl=en > -- You received this message because you are subscribed to the Google Groups "tesseract-ocr" 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/tesseract-ocr?hl=en
