Hi Nick, I read the TrainingTesseract3 page again and yet still not too sure how to go about it correctly. Probably getting key concepts right first is a way to go. Sample text file(s), turn them into tiff images, each image represent a font? (max 64 of them) Then, we have box files as well. What's the relationship between image files and box files? Editing each box file seems not only time-consuming but error-prone, so, jTessBoxEditor seems a good tool to use. Also, how about handwriting files as sample files (which have been scanned as image files)? And can jTessBoxEditor be used for these sample files as well?
Once I get a good grasp about the above probably I should then proceed with the following" creating "unicharset, inttemp, normproto, pfftable". Thank you very much. Don On Tuesday, March 18, 2014 2:45:53 PM UTC-4, Nick White wrote: > > Hi Don, > > text2image is optional, if you don't use it you can just create the > images and boxes manually[0] (or with a tool like > jTessBoxEditor[1]). text2image isn't available for Windows, though > it isn't available at all in any released version - it will be > available in the upcoming 3.03 release (or SVN now), but even then > it's Linux only. > > Nick > > 0. > https://code.google.com/p/tesseract-ocr/wiki/TrainingTesseract3#Old_Manual_method > > 1. http://vietocr.sourceforge.net/training.html > > On Mon, Mar 17, 2014 at 02:48:45PM -0700, Don Li wrote: > > Hi all, > > > > I just installed tesseract (version 3.02) for Windows. From the > training > > documentation (https://code.google.com/p/tesseract-ocr/wiki/ > > TrainingTesseract3), it seems that text2image > > utility is a must for the training to happen. However, upon searching > my > > tesseract installation, I couldn't find text2image.exe file, nor do I > have a > > subdirectory named Training under my tesseract installation. Does it > mean we > > have to download text2image.exe separately from somewhere or my > installation > > is flawed? Most likely the former since the tesseract command line > utility is > > able to translate a test image into a text file albeit inaccurate. > > > > Please advise. > > > > Thanks. > > > > Don > > > > -- > > -- > > You received this message because you are subscribed to the Google > > Groups "tesseract-ocr" group. > > To post to this group, send email to > > [email protected]<javascript:> > > To unsubscribe from this group, send email to > > [email protected] <javascript:> > > For more options, visit this group at > > http://groups.google.com/group/tesseract-ocr?hl=en > > > > --- > > 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] <javascript:>. > > 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 post to this group, send email to [email protected] To unsubscribe from this group, send email to [email protected] For more options, visit this group at http://groups.google.com/group/tesseract-ocr?hl=en --- 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]. For more options, visit https://groups.google.com/d/optout.
