Re: [tesseract-ocr] Tesseract 4's LSTM classifier

The only public information regarding LSTM that has been shared by Google/Ray is linked from the following pages: https://github.com/tesseract-ocr/tesseract/wiki/4.0-with-LSTM https://github.com/tesseract-ocr/docs/tree/master/das_tutorial2016

[tesseract-ocr] Python \ OpenCv \ Tesseract stdin

I have been unable to find an example where through Python an OpenCv image could be passed to Tesseract via stdin (as opposed to writing the image to a file and then passing tesseract the file path). Here is the code I have so far but it throws an error. import cv2 import numpy import

[tesseract-ocr] Tesseract 4's LSTM classifier

Hello, I am resubmitting a question that's been denied from the tesseract-dev list. Simply put, I am interested in exploring the actual structure (the layer layout) of the LSTM classifier which Tesseract 4 uses, ideally including some insight on previous designs that have been tested and the

[tesseract-ocr] Re: Blacklist and whitelist

Issue 751 has been reported. On Wednesday, March 8, 2017 at 1:50:46 AM UTC-6, Hieu Nguyen wrote: > > Same issue here, does anyone figure out how to solve this? > > On Tuesday, February 28, 2017 at 1:36:10 AM UTC+7, Alex Grishin wrote: >> >>

[tesseract-ocr] Re: using tesseract 4 on a C# project

It seems more complicated than initially thought. I think it's best to ask tesseract.net developer to update the project. On Monday, March 6, 2017 at 11:07:09 AM UTC-6, El Fakir Zakaria wrote: > > Tried to follow git's wiki and used this command : > cppan --build