mirror of
https://github.com/tesseract-ocr/tesseract.git
synced 2024-11-25 19:49:04 +08:00
dfb81e163e
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@484 d0cd1f9f-072b-0410-8dd7-cf729c803f20
60 lines
2.8 KiB
XML
60 lines
2.8 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>unicharset_extractor</refentrytitle>
|
|
<manvolnum>1</manvolnum>
|
|
<refmiscinfo class="source"> </refmiscinfo>
|
|
<refmiscinfo class="manual"> </refmiscinfo>
|
|
</refmeta>
|
|
<refnamediv>
|
|
<refname>unicharset_extractor</refname>
|
|
<refpurpose>extract unicharset from Tesseract boxfiles</refpurpose>
|
|
</refnamediv>
|
|
<refsynopsisdiv id="_synopsis">
|
|
<simpara><emphasis role="strong">unicharset_extractor</emphasis> <emphasis>FILE</emphasis>…</simpara>
|
|
</refsynopsisdiv>
|
|
<refsect1 id="_description">
|
|
<title>DESCRIPTION</title>
|
|
<simpara>Tesseract needs to know the set of possible characters it can output.
|
|
To generate the unicharset data file, use the unicharset_extractor
|
|
program on the same training pages bounding box files as used for
|
|
clustering:</simpara>
|
|
<literallayout class="monospaced">unicharset_extractor fontfile_1.box fontfile_2.box ...</literallayout>
|
|
<simpara>Tesseract needs to have access to character properties isalpha,
|
|
isdigit, isupper, islower, ispunctuation. This data must be encoded
|
|
in the unicharset data file. Each line of this file corresponds to
|
|
one character. The character in UTF-8 is followed by a hexadecimal
|
|
number representing a binary mask that encodes the properties. Each
|
|
bit corresponds to a property. If the bit is set to 1, it means that
|
|
the property is true. The bit ordering is (from least significant bit
|
|
to most significant bit): isalpha, islower, isupper, isdigit,
|
|
ispunctuation.
|
|
(See unicharset(5))</simpara>
|
|
<simpara>If your system supports the wctype functions, these values will be set
|
|
automatically by unicharset_extractor and there is no need to edit the
|
|
unicharset file. On some older systems (eg Windows 95), the unicharset
|
|
file must be edited by hand to add these property description codes.</simpara>
|
|
<simpara><emphasis role="strong">NOTE</emphasis> The unicharset file must be regenerated whenever inttemp, normproto
|
|
and pffmtable are generated (i.e. they must all be recreated when the box
|
|
file is changed) as they have to be in sync. This is made easier than in
|
|
previous versions by running unicharset_extractor before mftraining and
|
|
cntraining, and giving the unicharset to mftraining.</simpara>
|
|
</refsect1>
|
|
<refsect1 id="_see_also">
|
|
<title>SEE ALSO</title>
|
|
<simpara>tesseract(1), unicharset(5)</simpara>
|
|
</refsect1>
|
|
<refsect1 id="_history">
|
|
<title>HISTORY</title>
|
|
<simpara>unicharset_extractor first appeared in Tesseract 2.00.</simpara>
|
|
</refsect1>
|
|
<refsect1 id="_copying">
|
|
<title>COPYING</title>
|
|
<simpara>Copyright © 2006, Google Inc.
|
|
Licensed under the Apache License, Version 2.0</simpara>
|
|
</refsect1>
|
|
</refentry>
|