Scripting an OCR Scan?

[aw585 at lafn.org]

A google search on 

tesseract ocr orientation script

turns up some references to a debian package


tesseract-ocr-osd

package, and what looks like references to a presentation on this 
package.
(OSD in this context apparently being "Orientation and Script Detection".)

This is probably already installed on your system.

Looking at 'man tesseract', it looks to me like some of the
options for the '-psm' switch can either simply try to determine
orientation and alphabet in use, or try to apply the information
directly to ocr.
It looks like   '-psm 0'  will give information on page orientation.

Have you tried any of those '-psm'  settings yet?

Not having a working scanner or some sample output files,
I have nothing to test this with.

Regards,
Dallas E. Legan II
legan at acm.org / aw585 at lafn.org /
http://www.lafn.org/~aw585/index.html

---------------------------------------------
This message was sent using Endymion MailMan.
http://www.endymion.com/products/mailman/