A very good intro is here: http://www.danvk.org/2015/01/07/finding-blocks-of-text-in-an-image-using-python-opencv-and-numpy.html
However, in my case the "-n" option to "ocropus-nlbin" (as in http://www.danvk.org/2015/01/09/extracting-text-from-an-image-using-ocropus.html) did not work.
I have a similar problem: vertical text around the borders that needs to be ignored ...
On 16-Jun-15 4:41 PM, Everest wrote:
Hello I am working on a project dealing with document image. What I want to handle now is to remove the border noise from a whole scanned colored image. 'Cause I didn't get a document about this project, could anyone provide me with a explanation about how to apply a method to get the expected text area from a original image or binarized image? Thank you very much! -- You received this message because you are subscribed to the Google Groups "ocropus" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected] <mailto:[email protected]>. To post to this group, send email to [email protected] <mailto:[email protected]>. To view this discussion on the web visit https://groups.google.com/d/msgid/ocropus/bd7edf2c-82f5-4060-93fe-39fb4f86262c%40googlegroups.com <https://groups.google.com/d/msgid/ocropus/bd7edf2c-82f5-4060-93fe-39fb4f86262c%40googlegroups.com?utm_medium=email&utm_source=footer>. For more options, visit https://groups.google.com/d/optout.
-- Sachin Garg <[email protected]> Doctoral Student School of Policy, Government & Intl. Affairs George Mason University 3351 Fairfax Drive MS3B1, Arlington, VA 22201, USA Phone: +1-703-993-3787 Cell: +1-571-222-3216 -- You received this message because you are subscribed to the Google Groups "ocropus" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. To post to this group, send email to [email protected]. To view this discussion on the web visit https://groups.google.com/d/msgid/ocropus/55809D0C.3080202%40masonlive.gmu.edu. For more options, visit https://groups.google.com/d/optout.
