Re: Training procedure

Thanks Zdenko. The errors are not so stupid, taking into account that human mind can't embrace everything )) -- Dmitri 2011/6/21 Zdenko Podobný : > I know there is one bug in 3.00 (already fixed in svn for 3.01 version) that > "works" on linux but not windows [1]. patch is included in that iss

Re: Training procedure

I know there is one bug in 3.00 (already fixed in svn for 3.01 version) that "works" on linux but not windows [1]. patch is included in that issue if needed also with explanation why it has problem on Linux/Mac and not Windows. If possible I suggest to use recent revision of source code (589)

Re: Training procedure

As far as I know tesseract is developed (or at least tested) on Ubuntu :-). Windows version is port ;-) BTW: this is a stupid bug/feature: you can fix it by renaming file 'spa.cour.g4.tr' to 'spa.cour.exp4.tr'. See comment in source code [1]. This worked for tesseract 3.01 (revision ) on Mandr

Re: Training procedure

Curious. It's not the first time I see platform-related discrepancies in Tesseract's results. Nice to find out the root of it... Don't have time to conduct a full-blown research, though. Anybody knows anything? Warm regards, Dmitri Silaev www.CustomOCR.com On Tue, Jun 21, 2011 at 10:04 AM, Es

Re: Training procedure

2011/6/21 zdenko podobny > > PS: it worked on windows XP with tesseract 3.00 > > It's true. I've tested on Win XP and it worked. ¿Tesseract was tested on Linux Based operating systems? regards, Esteban. -- You received this message because you are subscribed to the Google Groups "tesseract-oc

Re: Training procedure

I have tried with tesseract 3.00 in Fedora 14 and Ubuntu 11.04. Which commands you have used? Maybe I must to try on XP or Windows 7... 2011/6/21 zdenko podobny > what OS you use and which tesseract version? > > Zdenko > > PS: it worked on windows XP with tesseract 3.00 > > On Tue, Jun 21, 201

Re: Training procedure

what OS you use and which tesseract version? Zdenko PS: it worked on windows XP with tesseract 3.00 On Tue, Jun 21, 2011 at 3:17 PM, Esteban Bordón wrote: > Sorry, I forgot attach it. Anyway font_properties is used from v 3.01 and I > am using v 3.00 > > cheers, > Esteban. > > 2011/6/21 zdenko

Re: Training procedure

Sorry, I forgot attach it. Anyway font_properties is used from v 3.01 and I am using v 3.00 cheers, Esteban. 2011/6/21 zdenko podobny > If you got error on font_properties file, send also font_properties ;-) > > Zdenko > > On Tue, Jun 21, 2011 at 2:45 PM, Esteban Bordón wrote: > >> For exampl

Re: Training procedure

If you got error on font_properties file, send also font_properties ;-) Zdenko On Tue, Jun 21, 2011 at 2:45 PM, Esteban Bordón wrote: > For example using these files provides in > http://tesseract-ocr.googlecode.com/files/boxtiff-2.01.spa.tar.gz and the > command lines bellow > > *]$ tesseract

Re: Training procedure

You have to show us your training images, resulted box files and all used command lines. Warm regards, Dmitri Silaev www.CustomOCR.com On Mon, Jun 20, 2011 at 8:04 PM, Esteban Bordón wrote: > Hi all! > > I'm working on a project that wants to digitize judicial expedients. We want > to use te

Training procedure

Hi all! I'm working on a project that wants to digitize judicial expedients. We want to use tesseract but we haven't had great results. I think that if I train tesseract very specifically for the kind of font that the expedients uses we could increase the positive results but I couldn't trained my

Re: General information about training procedure

The English box and tiff files are available on the downloads page : here .Ray. On Fri, Mar 27, 2009 at 12:20 AM, bergheil wrote: > > Hello, where I can find an example of a good training? I need to > understand what's is wrong i

Re: General information about training procedure

Hello, where I can find an example of a good training? I need to understand what's is wrong in my training. Bye On 24 Mar, 18:39, bergheil wrote: > Hi Ray, > I have more than 30 samples, there is only 1 font and I have more than > 5-10 samples for each char. I got "APPLY" box only for 1-2 box fi

Re: General information about training procedure

Hi Ray, I have more than 30 samples, there is only 1 font and I have more than 5-10 samples for each char. I got "APPLY" box only for 1-2 box files, I have excluded those from training. If is possible to attach a tiff sample in this forum I will show you the font that I use. Bye On 24 Mar, 15:43,

Re: General information about training procedure

You might need more samples. The training process usually uses a minimum of 5-10 samples of each character in each font.Did you get any errors from applybox? See Important under Run Tesseract for Training. Ray. On Tue, Mar 24, 2009 at 2:32 AM, bergheil wrote: > > Hello, nobody can please explain

Re: General information about training procedure

Hello, nobody can please explain me what is wrong in my training process? Please help me. On 20 Mar, 08:38, bergheil wrote: > Ciao a tutti, > I'm building a training for recogninze the cmc7 fonts (only numbers > and chars /^>! ). > I have used for training an openoffice file with 3 lines of font

General information about training procedure

Ciao a tutti, I'm building a training for recogninze the cmc7 fonts (only numbers and chars /^>! ). I have used for training an openoffice file with 3 lines of fonts wrote by myself and 8 file with the real document to recognize (bank check). After the training tesseract recognize the whole openof

Need Training procedure to train 7-segment display digits

Hi all, I'm using Tesseract ocr to recognize 7-segment digits from a meter image. there are around 12 digits, 4 digits in each line(total 3 rows). I wrote a program in c# .net using Tessnet2.dll in the program with tessdata as "Eng". out of the 12 digits i'm able to get the 10 digits c