Re: [tesseract-ocr] Re: seven segment display - 4.0 traineddata

Hey Dominik, Is ssd.traineddata working for you? Are you getting decimal point? On Saturday, April 20, 2019 at 6:59:36 PM UTC+5:30, Dominik Helleberg wrote: > > thx will give it a try! > Cheers > Dominik > > Am Do., 18. Apr. 2019 um 14:52 Uhr schrieb Shree Devi Kumar < > shree...@gmail.com >: >

[tesseract-ocr] Tesseract not recognizing ancient language's code

Hey, I have been trying to train tesseract4 for an ancient language but it seems it can not recognize its code 'xsa' which is Sabaean Language [user@laptop tesstraining]$ tesstrain.sh --fonts_dir ./sabaean_fonts --lang xsa --linedata_only --noextract_font_properties --langdata_dir

[tesseract-ocr] Supplying a different DPI param per page

If you have a multipage tif file is it possible that each page has a different DPI? If so, is there a way to extract the DPI values and then supply those as parameters for each page when you need to OCR images then produce an hOCR? -- You received this message because you are subscribed to