Hi,
I have the byte[] in YUV from the vuforia and i wanted to use that data to
perform OCR. It doesn't recognise the text correctly.
But when I convert that byte[] to bitmap and use it recognises. I tried the
byte[] of the RGB too but it didn't work.
this is the snippet.
setImage(byte[] ,
hi all,
maybe someone could help me with this?
Can someone give me full instructions how to compile tesseract from
the git repo under cygwin?
has someone tested that recently?
i also saw the language data isn't available on the git repo.
greetings and thanks,
simon
--
Simon Eigeldinger
Hi,
Have you got any ans to this problem, Please share.
Thanks
Mohsin
On Thursday, September 25, 2014 8:37:49 PM UTC+5:30, Amit Sharma wrote:
Hello Friends,
I am using Tesseract OCR for making simple recognizer. I am facing few
problem as added :
1. Don't able to recognize math equation
Have you tried
https://code.google.com/p/tesseract-ocr/downloads/detail?name=tesseract-ocr-3.02.equ.tar.gzcan=2q=
Math / equation detection module for Tesseract 3.02
try to use two laguages traineddata
l=eng+equ
and see if you get better results
Shree Devi Kumar
After SetImage call (tesseract api) function GetThresholdedImage and save
result (leptonica PIX) to disk.
If the output is wrong you did not set image data to tesseract correctly
(e.g. you need to change SetImage parameters).
Zdenko
On Wed, Oct 1, 2014 at 7:30 AM, Umresh umr...@myingage.com
I was able to build it. Do you need it to be from the git repo?
to get the language data, you can use curl and download it from the google
code site:
curl -L -o tesseract-ocr-3.02.tar.gz
https://tesseract-ocr.googlecode.com/files/tesseract-ocr-3.02.eng.tar.gz
I have included a shell script
hi,
thanks.
interesting. just compiled a static build and got 1 dll
(cygtesseract-3.dll size around 3592 kb) and tesseract.exe (around 84 kb).
last time in 2012 i kind of got a nearly 27 mb large exe (tesseract.exe).
without actually the other dlls.
but it seems to run without any problem.
i
7 matches
Mail list logo