Greetings, I've tried to follow the procedure identified in the Wiki (http:// code.google.com/p/tesseract-ocr/wiki/TrainingTesseract) to train Tesseract but I'm apparently doing something out of order.
I didn't generate the box files. I instead downloaded the ones available for eng. I tried running the command "tesseract fontfile.tif junk nobatch box.train" but received an error about the eng.unicharset file not being found; so I skipped a few steps and created the unicharset file from the collection of box files and .TIF images. Now it returns a different error: "Error: 1 classes in inttemp while unicharset contains 108 unichars." It appears that inttemp is dependent on the .tr files produced by the training process--which is dependent on inttemp. I've left everything stock so I can get through the whole thing before I begin to optimize. Any help would be greatly appreciated. --Ray --~--~---------~--~----~------------~-------~--~----~ 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 -~----------~----~----~----~------~----~------~--~---
