Use different font. This font even confuses me, if you haven't pointed it out I would have thought that this is lower case j. Try using some common font, see what are the fonts originally trained. If you insist on using this font then retrain Tesseract to recognize it.
In my opinion false spaces and mixed up letter case here and there are very minor mistakes and you should not worry about them so much. I thing that a simple program can process the output to make it perfect - you can check the words in a database, try to remove spaces and see if the concatenated pieces complete a word, etc. -- 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/72bb4faa-171e-4e8f-8630-5fd9270b6964%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
