Hi, Many times even if the image looks quite good in visual it may bbe something that tesseract cann't handle at pixel level. Look at the boxes tesseract creates for more details. Command : tesseract ImageName OutputHtmlName hocr
On Thursday, 26 October 2017 14:59:06 UTC+5:30, no reply wrote: > > i have very clear image (85.png) with two digits which tessaract fails to > recognize > all other images are recognized without problems, i.e. 00.png > > c:\Program Files (x86)\Tesseract-OCR>tesseract.exe c:\Temp\85.png stdout > > c:\Program Files (x86)\Tesseract-OCR>tesseract.exe c:\Temp\00.png stdout > 00 > > c:\Program Files (x86)\Tesseract-OCR>tesseract.exe --version > tesseract 3.05.01 > leptonica-1.74.1 > libgif 4.1.6(?) : libjpeg 8d (libjpeg-turbo 1.5.0) : libpng 1.6.20 : > libtiff 4.0.6 : zlib 1.2.8 : libwebp 0.4.3 : libopenjp2 2.1.0 > > is it a bug? > > -- 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/62c1326e-8cfc-4280-b4ef-6ef9d488079c%40googlegroups.com. For more options, visit https://groups.google.com/d/optout.
