On 30 June 2010 14:27, mukhiddin <[email protected]> wrote: > On page http://code.google.com/p/tesseract-ocr/wiki/TrainingTesseract > was written that program mftraining and cntraining can only take upto > 32 .tr files. Does it mean that i can't train tess mare than 32 > different fonts > I downloaded "Source training data for English" and trained tesseract. > But Tess still not recognize some text. That's why i want to add and > try to train for other fonts. When I tryed mftraining for 32 .tr files > I got error: "Ouch! number of protos = 513, vs max of 512!Segmentation > fault", but with 31 .tr files mftraining generated inttemp and > pffmtable.
In classify/intproto.h: change #define MAX_NUM_PROTOS 512 to something higher and recompile. -- <Leftmost> jimregan, that's because deep inside you, you are evil. <Leftmost> Also not-so-deep inside you. -- 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.
