https://tesseract-ocr.github.io/tessdoc/ImproveQuality.html
Algorithm responsible for providing OCR results for "inverted images" is not reliable in tesseracrt >=4 (or LSTM engine only?)... Zdenko št 1. 10. 2020 o 21:55 Jean-Marc Spaggiari <jean-m...@spaggiari.org> napísal(a): > I was curious as why it works super well for some white and black, and not > at all for others. I will try the invertion. > > Thanks, > > JMS > > Le jeudi 1 octobre 2020 à 12 h 59 min 09 s UTC-4, Lorenzo Blz a écrit : > >> Invert the image. >> >> >> >> Il gio 1 ott 2020, 14:58 Jean-Marc Spaggiari <jean...@spaggiari.org> ha >> scritto: >> >>> Hi, >>> >>> I'm playing around with Tesseract to try to do some OCR on screen >>> captures. >>> >>> My picture looks like this: >>> [image: name.png] >>> >>> But is recognized like this: >>> Eglise Chrétienne Evangélique de >>> sy oan 8)=1= >>> >>> Place Je Me Souviens, Laval, QC H7L 1T9, >>> ‘Tate lale| >>> >>> Long lines are fine, but short are definitely not. So I tried to split >>> the picture per line. The last line now looks like this: >>> [image: text_0277.png] >>> >>> But "tesseract filename.png out" gives me an empty output file without >>> any text in it. Long lines are still fine even when there is just one line >>> per file. Any idea why? >>> >>> Thanks, >>> >>> JMS >>> >>> -- >>> 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 tesseract-oc...@googlegroups.com. >>> To view this discussion on the web visit >>> https://groups.google.com/d/msgid/tesseract-ocr/9488a325-b90b-4bd4-ad2e-ecabe6801b24n%40googlegroups.com >>> <https://groups.google.com/d/msgid/tesseract-ocr/9488a325-b90b-4bd4-ad2e-ecabe6801b24n%40googlegroups.com?utm_medium=email&utm_source=footer> >>> . >>> >> -- > 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 tesseract-ocr+unsubscr...@googlegroups.com. > To view this discussion on the web visit > https://groups.google.com/d/msgid/tesseract-ocr/65b00f49-1951-4338-b8da-0c94d01be305n%40googlegroups.com > <https://groups.google.com/d/msgid/tesseract-ocr/65b00f49-1951-4338-b8da-0c94d01be305n%40googlegroups.com?utm_medium=email&utm_source=footer> > . > -- 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 tesseract-ocr+unsubscr...@googlegroups.com. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/CAJbzG8zM4WLYQYkAOug3TS%2B_4aDgGsO4SRwshxG-hp-phEuG9Q%40mail.gmail.com.
