1CNTRAINING(1) 2============= 3 4NAME 5---- 6cntraining - character normalization training for Tesseract 7 8SYNOPSIS 9-------- 10*cntraining* [-D 'dir'] 'FILE'... 11 12DESCRIPTION 13----------- 14cntraining takes a list of .tr files, from which it generates the 15*normproto* data file (the character normalization sensitivity 16prototypes). 17 18OPTIONS 19-------- 20-D 'dir':: 21 Directory to write output files to. 22 23SEE ALSO 24-------- 25tesseract(1), shapeclustering(1), mftraining(1) 26 27<https://tesseract-ocr.github.io/tessdoc/Training-Tesseract.html> 28 29COPYING 30------- 31Copyright (c) Hewlett-Packard Company, 1988 32Licensed under the Apache License, Version 2.0 33 34AUTHOR 35------ 36The Tesseract OCR engine was written by Ray Smith and his research groups 37at Hewlett Packard (1985-1995) and Google (2006-present). 38