> > . > > *#section 1. (plus) I have a quesiton about a bash script you gave me* > > > *In the bash scripts* > > > 1. what is the criterion about extracting 100-120 lines ??? I have no idea. >
Only 3 pages are processed by tesstrain.sh for making box/tiff files, so it will be about 120 lines of text. > > > <https://lh3.googleusercontent.com/-umf8fjIxrRs/WpwVQ34I54I/AAAAAAAAMzk/fbNY98yYffUQMQCUZulJN6CjOlAeOLLnQCLcBGAs/s1600/3.PNG> > > > > > 2. The number of iterations is 300 > > > <https://lh3.googleusercontent.com/--nO7LjyyORU/WpwScJNdZ5I/AAAAAAAAMzM/Im61zAMhUeYjS94P7tlY0Pfk9UWfkwoIgCLcBGAs/s1600/1.PNG> > > why? ... Is it possible to change this number??? > Yes, you can change it. This is the recommended number, see training wiki details for finetuning. > 3. Why you using one font .... is it possible to increase font of (count > and sort ) = lots of fonts ??? (ex. Baekmuk.Dotum.. > I was only testing. You can use lots of fonts and experiment. > > > > <https://lh3.googleusercontent.com/-Cn7WAQTjKD8/WpwS8C1bxvI/AAAAAAAAMzU/KZxzjiYozmUpU0KjNCJKPGLaLXjUnjlXQCLcBGAs/s1600/2.PNG> > > > ---------------------------------------------------------------------------------------------------------------------------------------- > *#section 2. have a relation with this page > "https://github.com/tesseract-ocr/tesseract/issues/1172 > <https://github.com/tesseract-ocr/tesseract/issues/1172>"* > > > > 4. In tesseract/training folder , "language-spcific.sh" and "your > bashscript" you gave me have no relationship??? > > I think that they are share fonts ?..... So I think that I have to change > "language-specific.sh" to use "your bashscript" you gave me > > Am I right? or False? > You can specify the fonts via command line, then language_specific.sh does not need to be changed. > > 5. Someone made a *lstmf file by using this way .(attached) > > > <https://lh3.googleusercontent.com/-NSzaNNu6fQs/WpwXSXFjkfI/AAAAAAAAMz0/FCkrlDZfafEK6iWOHCRNQGwFAT3CHLO2gCLcBGAs/s1600/6.PNG> > > I don't know. > > Is it the same as using "tesstran.sh"???? > > Is it right ? (by tesseract 4.0) > > > > > ------------------------------------------------------------------------------------------------------------------------------------------------- > > *# section 3. > https://groups.google.com/forum/#!topic/tesseract-ocr/QrEC7IWnwnY > <https://groups.google.com/forum/#!topic/tesseract-ocr/QrEC7IWnwnY>* > > > 6. In my situation. to finely tune kor.traineddata which is existing made > by Google > > I 'm not concerd about "word list" . It doesnt' matter to me??? > You can then not use the word list as part of command. > Am I right or false?? > > > <https://lh3.googleusercontent.com/-r3JIF2854V8/WpwZ34diJvI/AAAAAAAAM0A/JDmzSM-ecDkMZFmuS4-ea5FgC2CIV533ACLcBGAs/s1600/8.PNG> > If you run that script with one font as an experiment, then you will know how it works. > > > I want to your reply .... > I wait .. In advance I really thank U very much. > > > -- > You received this message because you are subscribed to the Google Groups > "tesseract-ocr" group. > To unsubscribe from this group and stop receiving emails from it, send an > email to [email protected]. > To post to this group, send email to [email protected]. > Visit this group at https://groups.google.com/group/tesseract-ocr. > To view this discussion on the web visit > https://groups.google.com/d/msgid/tesseract-ocr/5570a96c-1daf-44d6-a03d-c928a4200069%40googlegroups.com > <https://groups.google.com/d/msgid/tesseract-ocr/5570a96c-1daf-44d6-a03d-c928a4200069%40googlegroups.com?utm_medium=email&utm_source=footer> > . > For more options, visit https://groups.google.com/d/optout. > -- You received this message because you are subscribed to the Google Groups "tesseract-ocr" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. To post to this group, send email to [email protected]. Visit this group at https://groups.google.com/group/tesseract-ocr. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/CAG2NduW%2BDpjOHDs%2B%2BoKU0FnR88spSuYkJZ%3Dq3vRqYJye_Yzw6w%40mail.gmail.com. For more options, visit https://groups.google.com/d/optout.
