I am having images from number plate of vehicles which isn't a standard
font. I have cropped images of characters in number plate. I tried the
following -
1. Created a grid of all images so tesseract can read them for training
and generated tif file for it.
2. Then i generated box files for the corresponding tif file and
corrected the box file for wrongly detected characters.
3. Then i tried generating - unicharset, font_properties,
shapeclustering, mftraining, cntraining.
4. At shapeclustering i am getting something like -
1. Bad properties for index 3, char ‘: 0,255 0,255 0,0 0,0 0,0
2. Bad properties for index 4, char J: 0,255 0,255 0,0 0,0 0,0
3. Bad properties for index 5, char l: 0,255 0,255 0,0 0,0 0,0
4. Bad properties for index 6, char I: 0,255 0,255 0,0 0,0 0,0
5. Bad properties for index 7, char .: 0,255 0,255 0,0 0,0 0,0
--
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 https://groups.google.com/group/tesseract-ocr.
To view this discussion on the web visit
https://groups.google.com/d/msgid/tesseract-ocr/0081046e-4481-4cde-af5c-097e1497c52d%40googlegroups.com.
For more options, visit https://groups.google.com/d/optout.
