​Forwarding update by Ray.
-- Forwarded message --
From: theraysmith
Date: Wed, Jul 12, 2017 at 5:55 AM
Subject: Re: [tesseract-ocr/tesseract] Tag a new version for LSTM 4.0 (#995)
To: tesseract-ocr/tesseract
I'm about
I have problem with tesseract training with font i created. After whole
process of generating bunch of tesseract files and combining them, my
tesseract reads all "7" as "?". Font ha both chars.
I created unicharambigs file containing:
v1
1 ? 1 7 1
It's saved in Vi in unix
Hi, I know that for Legacy tesseract, the input image will be binarized in
preprocessing.
I wonder if it is the same for Tesseract 4.0 with LSTM? In other words: is
the input image to LSTM is black and white or grayscaled/colored? Thanks!
--
You received this message because you are
Can you explain how you get just the bounding box coordinates for the
recognized/detected table?
I have it popping up in a window using ViewerDebugger so I know it's doing
it and it has the information, I just don't know how to get it. I need just
the coordinates of the table it found so that I
4 matches
Mail list logo