Great stuff, I've managed to get hold of the paper, thanks. I've had a look at the documentation on this page: http://tesseract-ocr.repairfaq.org/tess_variables_all.html
With the text I'm trying to recognise, I can be quite sure of the x height, but tesseract sometimes interprets a small bit of noise as a character. So if I tell tesseract to ignore potential characters with an x-height of below 15 pixels, it might improve accuracy for me. It looks like the variable I need to change is: textord_min_xheight although it seems the default value is 10 and I'm sure tesseract has interpreted blobs of around 5 pixels as characters, as mentioned above. Anyway, I'll have a play with it! Thanks for the reply. Paul. --~--~---------~--~----~------------~-------~--~----~ 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 -~----------~----~----~----~------~----~------~--~---
