Any help would be greatly appreciated.

I would like to do something fairly simple and that's reduce the types of 
characters Tesseract looks for to be just AlphaNumeric, 0-9 a-z A-Z .  I'm 
using the very latest version 3.02.02. I want to do this because Tesseract 
is doing things like confusing M with |'U'| . Notice the pipe and single 
quotes. I'd like to remove any punctuation like that to reduce errors.

My first attempt was to

1) Edit the default eng.cub.lm and eng.cub.lm_ files in the tessdata 
directory.
2) Remove the non-AlphaNumeric punctuation characters.
3) Run combine_tessdata to generate a new eng.traineddata

Unfortunately this isn't working. Here's the directory listing and the 
output I get in red below.
C:\Program Files (x86)\Tesseract-OCR\tessdata_NoPunctuation>dir
 Volume in drive C has no label.
 Volume Serial Number is F0DD-A475

 Directory of C:\Program Files (x86)\Tesseract-OCR\tessdata_NoPunctuation

09/03/2014  11:43 AM    <DIR>          .
09/03/2014  11:43 AM    <DIR>          ..
09/03/2014  10:30 AM    <DIR>          configs
02/03/2012  02:47 AM        21,876,572 eng - Copy.jpg
02/03/2012  03:15 AM           171,918 eng.cube.bigrams
02/03/2012  03:15 AM                38 eng.cube.fold
09/03/2014  10:38 AM               137 eng.cube.lm
09/03/2014  10:38 AM               137 eng.cube.lm_
02/03/2012  03:15 AM           857,304 eng.cube.nn
02/03/2012  03:15 AM               254 eng.cube.params
02/03/2012  03:15 AM        13,020,078 eng.cube.size
02/03/2012  03:15 AM         2,444,187 eng.cube.word-freq
02/03/2012  03:15 AM               996 eng.tesseract_cube.nn
09/03/2014  11:46 AM                 0 eng.traineddata
09/03/2014  11:44 AM                 0 lang.traineddata
02/03/2012  03:15 AM        10,562,727 osd.traineddata
09/03/2014  10:30 AM    <DIR>          tessconfigs
              13 File(s)     48,934,348 bytes
               4 Dir(s)  666,501,136,384 bytes free

C:\Program Files 
(x86)\Tesseract-OCR\tessdata_NoPunctuation>combine_tessdata eng.
Combining tessdata files
Error opening unicharset file
Error combining tessdata files into eng.traineddata

C:\Program Files (x86)\Tesseract-OCR\tessdata_NoPunctuation>


 


-- 
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].
To post to this group, send email to [email protected].
Visit this group at http://groups.google.com/group/tesseract-ocr.
To view this discussion on the web visit 
https://groups.google.com/d/msgid/tesseract-ocr/b2356fd1-be8c-45c7-9f18-afa2a459eef9%40googlegroups.com.
For more options, visit https://groups.google.com/d/optout.

Reply via email to