[tesseract-ocr] Re: Training Tesseract to recognize technical drawings

I would hazard to guess this is a pretty Tough Problem and will need a little bit more in depth approach than Tesseract's current scope. Something like a separate text-detector well generalized to finding text in local area that would be robust against the angle variation finding the text, figu

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

t; https://github.com/tesseract-ocr/docs/tree/master/das_tutorial2016 > > https://github.com/tesseract-ocr/tesseract/wiki/Technical-Documentation > > ShreeDevi > > भजन - कीर्तन - आरती @ http://bhajans.ramparivar.com &g

[tesseract-ocr] Tesseract 4's LSTM classifier

d the results their implementation achieved, yet very little of this informations seems to appear in the Wiki or the source documents. Can somebody please point me towards this kind of information? With best regards, Milan Troller -- You received this message because you are subscribed to the G

Re: Integrating tesseract into Qt (C++ project)

Windows 7, and using QT Creator. On Thursday, August 23, 2012 8:17:07 PM UTC+2, zdenop wrote: > > What OS + IDE are you using? > -- > Zdenko > > On Thu, Aug 23, 2012 at 7:30 PM, Milan >wrote: > >> Thank you all for the answers. >> >> Zdenko I have a r

Re: Integrating tesseract into Qt (C++ project)

write... Thank you in advance. Milan [1]https://github.com/zdenop/qt-box-editor On Wednesday, August 22, 2012 9:19:56 PM UTC+2, zdenop wrote: > > On Wed, Aug 22, 2012 at 6:38 AM, Andres >wrote: > >> Yes, it is possible. >> >> You have 2 choices: >> >>

Integrating tesseract into Qt (C++ project)

on button "OCR" (or w/e), and I get the output file lets say in the folder where the image is. Kinda new with using open source projects and implementing them into my application so I would really appreciate any help. Thank you in advance. Milan -- You received this message becau

Re: Approach for training Tesseract with a new language and/font faces

Ray Smith píše v Po 01. 06. 2009 v 22:01 -0700: > I have added a clarification to the training wiki that might explain > this better. > Ray. > Thanks for clarifying. Milan -- Milan Knizek knizek (dot) confy (at) volny (dot) cz http://www.milan-knizek.net - About linux and photog

Re: image depth

age with an alpha channel. You can strip the alpha channel by: $ convert input.tif -alpha off output.tif BTW, to find out more info about image, use: $ identify -verbose input.tif br, Milan Knizek knizek (dot) confy (at) volny (dot) cz http://www.milan-knizek.net - About linux and photogr