1AMBIGUOUS_WORDS(1) 2================== 3:doctype: manpage 4 5NAME 6---- 7ambiguous_words - generate sets of words Tesseract is likely to find ambiguous 8 9SYNOPSIS 10-------- 11*ambiguous_words* [-l lang] 'TESSDATADIR' 'WORDLIST' 'AMBIGUOUSFILE' 12 13DESCRIPTION 14----------- 15ambiguous_words(1) runs Tesseract in a special mode, and for each word 16in word list, produces a set of words which Tesseract thinks might be 17ambiguous with it. 'TESSDATADIR' must be set to the absolute path of 18a directory containing 'tessdata/lang.traineddata'. 19 20SEE ALSO 21-------- 22tesseract(1) 23 24COPYING 25------- 26Copyright \(C) 2012 Google, Inc. 27Licensed under the Apache License, Version 2.0 28 29AUTHOR 30------ 31The Tesseract OCR engine was written by Ray Smith and his research groups 32at Hewlett Packard (1985-1995) and Google (2006-present). 33