As was mentioned earlier, for higher performance you should consider using the "fast" models instead of the "best" models. Other than that, analyzing the performance of the outliers to see what makes them different may give you some clues, performance is always going to depend to some degree on the image content.
Tom -- You received this message because you are subscribed to the Google Groups "tesseract-ocr" group. To unsubscribe from this group and stop receiving emails from it, send an email to tesseract-ocr+unsubscr...@googlegroups.com. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/a12a200c-c7a1-4680-bf48-4504ba5e4d11n%40googlegroups.com.
