mirror of
https://github.com/tesseract-ocr/tesseract.git
synced 2024-11-24 11:09:06 +08:00
103 lines
3.5 KiB
XML
103 lines
3.5 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">
|
|
<refentryinfo>
|
|
<title>MFTRAINING(1)</title>
|
|
</refentryinfo>
|
|
<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 <emphasis role="strong">inttemp</emphasis> (the shape prototypes), <emphasis role="strong">shapetable</emphasis>, and <emphasis role="strong">pffmtable</emphasis>
|
|
(the number of expected features for each character). (A fourth file
|
|
called Microfeat is also written by this program, but it is not used.)</simpara>
|
|
</refsect1>
|
|
<refsect1 id="_options">
|
|
<title>OPTIONS</title>
|
|
<variablelist>
|
|
<varlistentry>
|
|
<term>
|
|
-U <emphasis>FILE</emphasis>
|
|
</term>
|
|
<listitem>
|
|
<simpara>
|
|
(Input) The unicharset generated by unicharset_extractor(1)
|
|
</simpara>
|
|
</listitem>
|
|
</varlistentry>
|
|
<varlistentry>
|
|
<term>
|
|
-F <emphasis>font_properties_file</emphasis>
|
|
</term>
|
|
<listitem>
|
|
<simpara>
|
|
(Input) font properties file, each line is of the following form, where each field other than the font name is 0 or 1:
|
|
</simpara>
|
|
<literallayout class="monospaced">*font_name* *italic* *bold* *fixed_pitch* *serif* *fraktur*</literallayout>
|
|
</listitem>
|
|
</varlistentry>
|
|
<varlistentry>
|
|
<term>
|
|
-X <emphasis>xheights_file</emphasis>
|
|
</term>
|
|
<listitem>
|
|
<simpara>
|
|
(Input) x heights file, each line is of the following form, where xheight is calculated as the pixel x height of a character drawn at 32pt on 300 dpi. [ That is, if base x height + ascenders + descenders = 133, how much is x height? ]
|
|
</simpara>
|
|
<literallayout class="monospaced">*font_name* *xheight*</literallayout>
|
|
</listitem>
|
|
</varlistentry>
|
|
<varlistentry>
|
|
<term>
|
|
-D <emphasis>dir</emphasis>
|
|
</term>
|
|
<listitem>
|
|
<simpara>
|
|
Directory to write output files to.
|
|
</simpara>
|
|
</listitem>
|
|
</varlistentry>
|
|
<varlistentry>
|
|
<term>
|
|
-O <emphasis>FILE</emphasis>
|
|
</term>
|
|
<listitem>
|
|
<simpara>
|
|
(Output) The output unicharset that will be given to combine_tessdata(1)
|
|
</simpara>
|
|
</listitem>
|
|
</varlistentry>
|
|
</variablelist>
|
|
</refsect1>
|
|
<refsect1 id="_see_also">
|
|
<title>SEE ALSO</title>
|
|
<simpara>tesseract(1), cntraining(1), unicharset_extractor(1), combine_tessdata(1),
|
|
shapeclustering(1), unicharset(5)</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>
|