Tesseract OCR training gives APPLY_BOXES errors

Question

I train Tesseract 3 for the digital-7 font, and I get some errors in the output (from stderr):

APPLY_BOXES: boxfile line 35/I ((735,7860),(737,7890)): FAILURE! Couldn't find a matching blob 

and

 APPLY_BOXES: Unlabelled word at :Bounding box=(7523,-910)->(7549,-906) 

What do they mean?

I use the following command:

 tesseract eng.digital-7.exp0.tif eng.digital-7.exp0 nobatch box.train 

Answer 1

Double check the spacing between .tif characters: the first error can be caused by two characters too close and creating one bounding box (see also thread ).

The second error is a consequence of the first. I suppose.