tesseract/doc/wordlist2dawg.1.xml

47 lines
1.9 KiB
XML
Raw Normal View History

<?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>wordlist2dawg</refentrytitle>
<manvolnum>1</manvolnum>
<refmiscinfo class="source">&nbsp;</refmiscinfo>
<refmiscinfo class="manual">&nbsp;</refmiscinfo>
</refmeta>
<refnamediv>
<refname>wordlist2dawg</refname>
<refpurpose>convert a wordlist to a DAWG for Tesseract</refpurpose>
</refnamediv>
<refsynopsisdiv id="_synopsis">
<simpara><emphasis role="strong">wordlist2dawg</emphasis> <emphasis>WORDLIST</emphasis> <emphasis>DAWG</emphasis> <emphasis>lang.unicharset</emphasis></simpara>
</refsynopsisdiv>
<refsect1 id="_description">
<title>DESCRIPTION</title>
<simpara>wordlist2dawg(1) converts a wordlist to a Directed Acyclic
Word Graph (DAWG) for use with Tesseract.</simpara>
<simpara>The wordlists are split into two: one with high frequency
words, and one with the rest.</simpara>
</refsect1>
<refsect1 id="_options">
<title>OPTIONS</title>
<simpara><emphasis>WORDLIST</emphasis>
A plain text file in UTF-8, one word per line</simpara>
<simpara><emphasis>DAWG</emphasis>
The output DAWG to write</simpara>
<simpara><emphasis>lang.unicharset</emphasis>
The unicharset of the language. This is the unicharset
generated by mftraining(1)</simpara>
</refsect1>
<refsect1 id="_see_also">
<title>SEE ALSO</title>
<simpara>tesseract(1), mftraining(1)</simpara>
<simpara><ulink url="http://code.google.com/p/tesseract-ocr/wiki/TrainingTesseract3">http://code.google.com/p/tesseract-ocr/wiki/TrainingTesseract3</ulink></simpara>
</refsect1>
<refsect1 id="_copying">
<title>COPYING</title>
<simpara>Copyright (c) 2006 Google, Inc.
Licensed under the Apache License, Version 2.0</simpara>
</refsect1>
</refentry>