Re: Create traineddata from different tif and box files

2011-06-01 Thread zdenko podobny
It it written on training doc[1]: "*…**each .tr filename must match an entry in the font_properties file, or mftraining will abort.*" So you could save your time if you read documentation. Zdenko [1] http://code.google.com/p/tesseract-ocr/wiki/TrainingTesseract3#font_properties_(new_in_3.01) On

Re: Create traineddata from different tif and box files

2011-06-01 Thread Holm Dressler
Hi there, OK, found it out by myself: here are the steps: 1. Create 01.tr with tesseract 01.tif 01 nobatch box.train 2. Create 02.tr with tesseract 02.tif 02 nobatch box.train 3. Create unicharset with: unicharset_extractor 01.box 02.box 4. Just copy it (maybe it is not necessary) cp unicharset 0

Re: Create traineddata from different tif and box files

2011-05-26 Thread zdenko podobny
On Thu, May 26, 2011 at 2:02 PM, Sarel van der Merwe wrote: > Hi, > > Do you know where i can locate the version 3 manual or reference guide > for Tesseract.. > > The I know is in download section (tessdoc-html-3.0.0-preview1.tar.gz) ;-) Maybe Jimmi will update it for 3.01 :-) Some good informati

Re: Create traineddata from different tif and box files

2011-05-26 Thread Sarel van der Merwe
Hi, Do you know where i can locate the version 3 manual or reference guide for Tesseract.. Thanks Sarel On Thu, May 26, 2011 at 1:33 PM, zdenko podobny wrote: > Hi, > Problem is that you use the latest version and you do not read the latest > manual [1]. If I correctly understood that Germa

Re: Create traineddata from different tif and box files

2011-05-26 Thread zdenko podobny
Hi, Problem is that you use the latest version and you do not read the latest manual [1]. If I correctly understood that German manual (via google translate), it is for version 3.00 so it do not follow changes in 3.01 version. Another "problem": 3.01 is not released yet. It is for developers and