[accessiblelinux] OCR questions

  • From: <aerospace1028@xxxxxxxxxxx>
  • To: <accessiblelinux@xxxxxxxxxxxxx>
  • Date: Mon, 31 Aug 2009 14:38:34 -0400

greetings,
I am preparing to attempt optical character recognition in linux.  I consulted 
apt-cache and determined that my distribution of Ubuntu offers gocr, ocrad and 
tesseract (there are a couple other OCR engines that refer to KDE, but I 
ignored them).  I am also awair of ocropus, but that would require compilation 
from source.

In looking at the documentation for the three OCR engines, ocrad claims to 
provide a layout analyzer for column formatting.  Does this mean that I can 
scan two pages of a book simaltanious (by laying it flat across the scanner) 
and ocrad will put the content of the right-hand page after that of the left?

If this is not the case, are there any programs available for linux that can 
seperate double-page scans?

thank you:-)
_________________________________________________________________
Hotmail® is up to 70% faster. Now good news travels really fast. 
http://windowslive.com/online/hotmail?ocid=PID23391::T:WLMTAGL:ON:WL:en-US:WM_HYGN_faster:082009

Other related posts:

  • » [accessiblelinux] OCR questions - aerospace1028