mirror of
https://github.com/tesseract-ocr/tesseract.git
synced 2025-01-07 10:17:50 +08:00
0759ee7e17
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@482 d0cd1f9f-072b-0410-8dd7-cf729c803f20
43 lines
1.7 KiB
XML
43 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>mftraining</refentrytitle>
|
|
<manvolnum>1</manvolnum>
|
|
<refmiscinfo class="source"> </refmiscinfo>
|
|
<refmiscinfo class="manual"> </refmiscinfo>
|
|
</refmeta>
|
|
<refnamediv>
|
|
<refname>mftraining</refname>
|
|
<refpurpose>feature training for Tesseract</refpurpose>
|
|
</refnamediv>
|
|
<refsynopsisdiv id="_synopsis">
|
|
<simpara>mftraining -U <emphasis>unicharset</emphasis> -O <emphasis>lang.unicharset</emphasis> <emphasis>FILE</emphasis>…</simpara>
|
|
</refsynopsisdiv>
|
|
<refsect1 id="_description">
|
|
<title>DESCRIPTION</title>
|
|
<simpara>mftraining takes a list of .tr files, from which it generates the
|
|
files inttemp (the shape prototypes) and pffmtable (the number of
|
|
expected features for each character). (A third file called Microfeat
|
|
is also written by this program, but it is not used.)</simpara>
|
|
</refsect1>
|
|
<refsect1 id="_options">
|
|
<title>OPTIONS</title>
|
|
<simpara><emphasis>-U</emphasis> FILE
|
|
The unicharset generated by unicharset_extractor</simpara>
|
|
<simpara><emphasis>-O</emphasis> FILE
|
|
The output unicharset that will be given to combine_tessdata.</simpara>
|
|
</refsect1>
|
|
<refsect1 id="_see_also">
|
|
<title>SEE ALSO</title>
|
|
<simpara>tesseract(1), cntraining(1), unicharset_extractor(1), combine_tessdata(1)</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>
|
|
</refentry>
|