2016-12-05 03:41:37 +08:00
|
|
|
<?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">
|
|
|
|
|
<refentryinfo>
|
|
|
|
|
<title>CNTRAINING(1)</title>
|
|
|
|
|
</refentryinfo>
|
|
|
|
|
<refmeta>
|
|
|
|
|
<refentrytitle>cntraining</refentrytitle>
|
|
|
|
|
<manvolnum>1</manvolnum>
|
|
|
|
|
<refmiscinfo class="source"> </refmiscinfo>
|
|
|
|
|
<refmiscinfo class="manual"> </refmiscinfo>
|
|
|
|
|
</refmeta>
|
|
|
|
|
<refnamediv>
|
|
|
|
|
<refname>cntraining</refname>
|
|
|
|
|
<refpurpose>character normalization training for Tesseract</refpurpose>
|
|
|
|
|
</refnamediv>
|
|
|
|
|
<refsynopsisdiv id="_synopsis">
|
|
|
|
|
<simpara><emphasis role="strong">cntraining</emphasis> [-D <emphasis>dir</emphasis>] <emphasis>FILE</emphasis>…</simpara>
|
|
|
|
|
</refsynopsisdiv>
|
|
|
|
|
<refsect1 id="_description">
|
|
|
|
|
<title>DESCRIPTION</title>
|
|
|
|
|
<simpara>cntraining takes a list of .tr files, from which it generates the
|
|
|
|
|
<emphasis role="strong">normproto</emphasis> data file (the character normalization sensitivity
|
|
|
|
|
prototypes).</simpara>
|
|
|
|
|
</refsect1>
|
|
|
|
|
<refsect1 id="_options">
|
|
|
|
|
<title>OPTIONS</title>
|
|
|
|
|
<variablelist>
|
|
|
|
|
<varlistentry>
|
|
|
|
|
<term>
|
|
|
|
|
-D <emphasis>dir</emphasis>
|
|
|
|
|
</term>
|
|
|
|
|
<listitem>
|
|
|
|
|
<simpara>
|
|
|
|
|
Directory to write output files to.
|
|
|
|
|
</simpara>
|
|
|
|
|
</listitem>
|
|
|
|
|
</varlistentry>
|
|
|
|
|
</variablelist>
|
|
|
|
|
</refsect1>
|
|
|
|
|
<refsect1 id="_see_also">
|
|
|
|
|
<title>SEE ALSO</title>
|
|
|
|
|
<simpara>tesseract(1), shapeclustering(1), mftraining(1)</simpara>
|
|
|
|
|
<simpara><ulink url="https://github.com/tesseract-ocr/tesseract/wiki/TrainingTesseract">https://github.com/tesseract-ocr/tesseract/wiki/TrainingTesseract</ulink></simpara>
|
|
|
|
|
</refsect1>
|
|
|
|
|
<refsect1 id="_copying">
|
|
|
|
|
<title>COPYING</title>
|
|
|
|
|
<simpara>Copyright (c) Hewlett-Packard Company, 1988
|
|
|
|
|
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>
|
