Hi, trying to retrain, which means to improve a character model, I thought it would be helpful to have access to the bboxes of each line for adding more trainig data from almost good recognized lines.
I also found this mentioned in a documentation titled OCRopus Intermediate Disk Format. This would allow for correcting the bboxes, which may be less cumbersome than to edit the rseg image files to get new training data. But may be there is a better way to achieve this? At least by setting debug=minsize I get only the bbox width and height for each character. If the output would be the same as for Tesseract box files - which has the character itself at the beginning of a line followed by x0 y0 x1 y1 values - this would - I thought - even allow to use some immediately already existing bbox editor to adapt boundaries. Cheers, Georg M --~--~---------~--~----~------------~-------~--~----~ 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 -~----------~----~----~----~------~----~------~--~---
