There's a branch that is based on 4.0, check it out here: https://github.com/charlesw/tesseract/tree/feature/321-Tesseract-4
On Thursday, February 20, 2020 at 4:30:13 PM UTC+2, Justin Yeh wrote: > > Sorry, I forgot to mention that I was using C# with Visual Studio 2015 to > create an OCR application. > > Right now, all I can get from Nuget is tesseract 3.3.0. > > I found this <https://github.com/tesseract-ocr/tesseract/releases>online but > I am not sure how to reference it in my current C# project. > > Justin Yeh於 2020年2月20日星期四 UTC+8下午9時31分55秒寫道： >> >> Take this attached image for example, seems like Tesseract 3.3.0 >> (downloaded from nuget) cannot recognize few characters correctly: such as >> 8 and B, or 5 and Z, or 0 and O etc... >> >> Is there any way that I could get string from image more accurately? or >> ... How do I avoid this kind of misinterpretation from tesseract? I have >> tried to make them in bold size but the result is the same.... >> >> Any advice is welcome here. Thanks in advance!!!! >> > -- 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/ef91eb02-4b31-4147-8569-3ab7f703d677%40googlegroups.com.
