[accessiblelinux] help using gimp for OCR
- From: <aerospace1028@xxxxxxxxxxx>
- To: <accessiblelinux@xxxxxxxxxxxxx>
- Date: Mon, 10 Aug 2009 09:14:51 -0400
greetings,
Is anyone here familiar with using gimp (or any other image processor) to clean
up scanned pages for OCR? I'm trying to find a way to enhance some scanned
text for better OCR results (in this case infty-reader, but in the future I
want to try ocropus, teseract and a couple other linux OCR engines).
I followed the directions from http://www.gimp.org/tutorials/Basic_Batch/ and
created a "batch-unsharp-mask.csm" file and ran gimp from the command line as
suggested. I've experimented with the radius, amount and threshold values, but
the enhanced image always comes out worse than the unenhanced image. Does
anyone know if there's a different filter that would work better for text
images? or what values would sharpen a 600 dpi black and white image?
Also, I can't find the list of functions and their descriptions that the
tutorial refers to. I want to also make a batch script to roatate images 180
degrees for the upsidedown pages.
Thanks in advance for any help you can provide:-)
_________________________________________________________________
Get your vacation photos on your phone!
http://windowsliveformobile.com/en-us/photos/default.aspx?&OCID=0809TL-HM
Other related posts:
