Re: [tesseract-ocr] Losing accuracy when training tessearct on fonts it already is trained on

Basically of 2000 characters about 1/4 of them fail this way. I've tried char_spacing from 1 all the way up to 10 doesn't seem to matter really. When we use the same text and print it with 1.25 spacing and manually make the tiff we only get 5-20 fails. Is there something I could be missing he

[tesseract-ocr] Is there any indicatator show the last result recognized by Tesseract is from frequent words list?

Hello, I have make my own train data and add the frequent words list to enhance the recognizing rate. I wonder if there is a indicator to know that the last result recognized by Tesseract is from one word of frequent words list or not ? Please give me a hand, Thanks a lot!! -- You receiv

Re: [tesseract-ocr] Version 3.03 windows compilation

What about to have a look at project page[1] ;-)? [1] https://code.google.com/p/tesseract-ocr/ Zdenko On Mon, Aug 25, 2014 at 5:43 PM, Cristovão Oliveira < cristovao.olive...@alidata.com.pt> wrote: > Hi everyone, > > I don't see version 3.03 to download (even source code to compile myself) > o

[tesseract-ocr] Version 3.03 windows compilation

Hi everyone, I don't see version 3.03 to download (even source code to compile myself) on Project Page. Anyone have a compiled 3.03 version for windows? Tanks in advance. -- You received this message because you are subscribed to the Google Groups "tesseract-ocr" group. To unsubscribe from t

Re: [tesseract-ocr] Re: Not able to compile tesseract with opencv and qt

I got this error when I tried to include threading in my project. I came here to get solution for the similar problem. I had used "using namespace std;" I commented "using namespace std;" and then also the problem was not resolved. While compiling, I had included the two flags -std=c++0x and -

[tesseract-ocr] 3.04

Hi Zdenko, I notice that https://code.google.com/p/tesseract-ocr/source/browse/configure.ac?spec=svn524ee27f019b1ab2ea6a536b1dc335b9ef78fad7&r=524ee27f019b1ab2ea6a536b1dc335b9ef78fad7 shows tesseract version as 3.04 Please let us know the git command to clone the 3.04.0 version. You may wan

Re: [tesseract-ocr] Losing accuracy when training tessearct on fonts it already is trained on

On Fri, Aug 22, 2014 at 12:42:21PM -0700, Thomas Bruno wrote: > Is this common when training from text2image output? > > > APPLY_BOXES: boxfile line 5364/748 ((1488,893),(1532,6)): FAILURE! Couldn't > find a matching blob > > FAIL! Yes, there will be some of these. Check the proportion of faili