Hi all I'm a neophyte in Tesseract.
Currently I'm using tesseract 3.0.5, I'm using it with the Italian language and newspaper pages in pdf format. I'm converting pdf to png (with Imagemagick) with 300 and 600 dpi, following all these suggestions https://github.com/tesseract-ocr/tesseract/wiki/ImproveQuality It works quite well, but it makes some errors. So what I would like to do is improving OCR recognition adding some specific examples, i.e. the sentences in which it makes some errors. Is it possible? A sort of active learning.... I went through this one http://pretius.com/how-to-prepare-training-files-for-tesseract-ocr-and-improve-characters-recognition/ and I succeded in creating a new traineddata file.... but then I discovered that it is not possible updating the existing traineddata file for the Italian language... One should make the entire training whit all the pngs and boxes files. Is there a way of doing this sort of updating/improving? Maybe with Tesseract 4? Thanks in advance Lorenza -- 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/ecb07096-debc-4c23-8677-6e50fb1d2ea5%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
