Consider this case. The first image represents my input. Note the lefthand border area.
Using ScrollView to view the detected blobs, Tesseract is grouping that left hand border with the 'J' Seen more easily here ... Tesseract then recognises this shape as an 'F' which you can sort of see how it could. The baseline has been detected quite well, so I assume the anti-skewing is working. I wonder if this is to do with the distance between the 'J' and this border. I have a list of all the Tesseract configuration values but they are not documented all that well and not enough to know whether this is a case that can be solved with a configuration tweak. I was surprised the size of the apparent 'F' is quite a bit bigger than the rest of the height. Cheers -- 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/9ec9d279-8d5a-4f1b-aa61-1ba053ea1f54%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
