Tesseract (in google) was develop and extended in google book (OCR) project and it work best on straight clean line of text. So it tend to skip graphics and noise. Your input is full graphics. Therefore in this case you need to do your own page layout analyze and send only text regions (without border) to tesseract. Other option is to remove graphics element before sending image to tesseract.
Zdenko ne 3. 11. 2019 o 17:08 Leena <[email protected]> napísal(a): > Any help please. > > On Monday, 1 July 2019 12:37:45 UTC+5:30, Leena wrote: >> >> Dear Developer, >> >> Attached code, input image and output file that is used to extract text >> from input image. Used tessract OCR to extract the text from flow diagram, >> but not getting text of each box, few are extracted. Please analyse and >> suggest changes to get full text. >> >> Thanks >> > -- > 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 view this discussion on the web visit > https://groups.google.com/d/msgid/tesseract-ocr/7be9b4b1-7e81-475e-b4da-ee743d90a1e7%40googlegroups.com > <https://groups.google.com/d/msgid/tesseract-ocr/7be9b4b1-7e81-475e-b4da-ee743d90a1e7%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 [email protected]. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/CAJbzG8z4fRonaUJXgs8osrhJQyv470ou1zwWjhBac4E6E4aCtw%40mail.gmail.com.
