i am also interested in using tesseract ocr for e-pub conversion of some of scanned books that i have; i used python for auto correction and also a dictionary is required for updating auto correction of mistakes like யஈன
regards rnk On Wednesday, 28 September 2016 07:04:15 UTC+5:30, rkvsraman wrote: > > > Hello, > > > I am testing the tamil data set and i am getting following issue > > பெயர் is getting recognised as டுபயர் > > and யான as யஈன > > I created the following unicharambigs file but it isnt helping. > > v2 > டுப பெ 1 > ஈ ா 1 > > I tried both 1 and 0 as type indicator but no use > > I have attached source text, image and OCred text > > I tested it with original tam.traineddata too with same result. > > > > Any suggestions? > > > -- 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/ec5ddeef-6c94-4117-8129-4171ea13406b%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
