mirror of
https://github.com/tesseract-ocr/tesseract.git
synced 2024-11-24 02:59:07 +08:00
58e06c8c45
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@670 d0cd1f9f-072b-0410-8dd7-cf729c803f20
41 lines
1.7 KiB
XML
41 lines
1.7 KiB
XML
<?xml version="1.0" encoding="UTF-8"?>
|
|
<!DOCTYPE refentry PUBLIC "-//OASIS//DTD DocBook XML V4.5//EN" "http://www.oasis-open.org/docbook/xml/4.5/docbookx.dtd">
|
|
<?asciidoc-toc?>
|
|
<?asciidoc-numbered?>
|
|
<refentry lang="en">
|
|
<refmeta>
|
|
<refentrytitle>ambiguous_words</refentrytitle>
|
|
<manvolnum>1</manvolnum>
|
|
<refmiscinfo class="source"> </refmiscinfo>
|
|
<refmiscinfo class="manual"> </refmiscinfo>
|
|
</refmeta>
|
|
<refnamediv>
|
|
<refname>ambiguous_words</refname>
|
|
<refpurpose>generate sets of words Tesseract is likely to find ambiguous</refpurpose>
|
|
</refnamediv>
|
|
<refsynopsisdiv id="_synopsis">
|
|
<simpara><emphasis role="strong">ambiguous_words</emphasis> [-l lang] <emphasis>TESSDATADIR</emphasis> <emphasis>WORDLIST</emphasis> <emphasis>AMBIGUOUSFILE</emphasis></simpara>
|
|
</refsynopsisdiv>
|
|
<refsect1 id="_description">
|
|
<title>DESCRIPTION</title>
|
|
<simpara>ambiguous_words(1) runs Tesseract in a special mode, and for each word
|
|
in word list, produces a set of words which Tesseract thinks might be
|
|
ambiguous with it. <emphasis>TESSDATADIR</emphasis> must be set to the absolute path of
|
|
a directory containing <emphasis>tessdata/lang.traineddata</emphasis>.</simpara>
|
|
</refsect1>
|
|
<refsect1 id="_see_also">
|
|
<title>SEE ALSO</title>
|
|
<simpara>tesseract(1)</simpara>
|
|
</refsect1>
|
|
<refsect1 id="_copying">
|
|
<title>COPYING</title>
|
|
<simpara>Copyright (C) 2012 Google, Inc.
|
|
Licensed under the Apache License, Version 2.0</simpara>
|
|
</refsect1>
|
|
<refsect1 id="_author">
|
|
<title>AUTHOR</title>
|
|
<simpara>The Tesseract OCR engine was written by Ray Smith and his research groups
|
|
at Hewlett Packard (1985-1995) and Google (2006-present).</simpara>
|
|
</refsect1>
|
|
</refentry>
|