http://code.google.com/p/tesseract-ocr/wiki/TrainingTesseract3
 says:

An alternative to multi-page tiffs is to create many single-page tiffs for
> a single font, and then you must cat together the tr files for each font
> into several single-font tr files. In any case, the input tr files to
> mftraining must each contain a single font.


I tried to concatenate the multiple tr files for multiple images, all in
the same font, to create a single tr file for one font. This is on Windows
7 and I used the copy command as follows:


> copy san.sanskrit2003.exp0001.tr + san.sanskrit2003.exp007.tr +
> san.sanskrit2003.exp012.tr + san.sanskrit2003.exp000.tr +
> san.sanskrit2003.exp001.tr + san.sanskrit2003.exp002.tr +
> san.sanskrit2003.exp003.tr + san.sanskrit2003.exp004.tr +
> san.sanskrit2003.exp005.tr + san.sanskrit2003.exp006.tr +
> san.sanskrit2003.exp008.tr + san.sanskrit2003.exp009.tr +
> san.sanskrit2003.exp010.tr + san.sanskrit2003.exp011.tr +
> san.sanskrit2003.exp013.tr + san.sanskrit2003.exp014.tr +
> san.sanskrit2003.exp015.tr + san.sanskrit2003.exp016.tr +
> san.sanskrit2003.exp017.tr       san.sanskrit2003.tr
>


> copy san.sanskrit2003b.exp020.tr + san.sanskrit2003b.exp021.tr +
> san.sanskrit2003b.exp022.tr + san.sanskrit2003b.exp023.tr
> san.sanskrit2003b.tr
>


> copy san.unknown.exp00000001.tr san.unknown.tr


This created 3 tr files and I ran shapeclustering with the same, but got
the following error:


> shapeclustering -F san.font_properties -U unicharset san.sanskrit2003.tr
> san.sanskrit2003b.tr san.unknown.tr
>


> Reading san.sanskrit2003.tr ...
> Bad format in tr file, reading fontname, unichar
> Reading san.sanskrit2003b.tr ...
> Bad format in tr file, reading fontname, unichar
> Reading san.unknown.tr ...
> Testing feature weight 1:(40,56):32
> Total miss
> Testing feature weight 1:(40,56):32
> Total miss


I
s this feature supported in 3.02? I am using the windows version on Win7.

-- 
-- 
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 unsubscribe from this group and stop receiving emails from it, send an email 
to [email protected].
For more options, visit https://groups.google.com/groups/opt_out.


Reply via email to