Hi! Is there currently a way to perform incremental training, perhaps using the "default.model" as a base and then recognize page by page, each time correcting the errors and incrementally training the base cmodel?
By checking the "Training" instruction page and seeing what the current code can do, the farthest I got was "retrain=1 ocropus trainseg <cmodel> <bookdir>", but I got the impression it just replaced the old cmodel. I'm trying to figure out a set-up for scanning shopping receipts, and perhaps in addition to incremental cmodel training, I could need language modeling too. Maybe, if the classifier won't do good enough alone, I could use some generic word list as a base and then add character sequences (those receipts might have cut-off words of product names) and theirs statistics to it, again by incremental training. That language modeling might be another story, but cmodel training would be a start. Thanks! --~--~---------~--~----~------------~-------~--~----~ You received this message because you are subscribed to the Google Groups "ocropus" 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/ocropus?hl=en -~----------~----~----~----~------~----~------~--~---
