'\" t
.\"     Title: unicharset_extractor
.\"    Author: [see the "AUTHOR" section]
.\" Generator: DocBook XSL Stylesheets v1.78.1 <http://docbook.sf.net/>
.\"      Date: 06/12/2015
.\"    Manual: \ \&
.\"    Source: \ \&
.\"  Language: English
.\"
.TH "UNICHARSET_EXTRACTOR" "1" "06/12/2015" "\ \&" "\ \&"
.\" -----------------------------------------------------------------
.\" * Define some portability stuff
.\" -----------------------------------------------------------------
.\" ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.\" http://bugs.debian.org/507673
.\" http://lists.gnu.org/archive/html/groff/2009-02/msg00013.html
.\" ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.ie \n(.g .ds Aq \(aq
.el       .ds Aq '
.\" -----------------------------------------------------------------
.\" * set default formatting
.\" -----------------------------------------------------------------
.\" disable hyphenation
.nh
.\" disable justification (adjust text to left margin only)
.ad l
.\" -----------------------------------------------------------------
.\" * MAIN CONTENT STARTS HERE *
.\" -----------------------------------------------------------------
.SH "NAME"
unicharset_extractor \- extract unicharset from Tesseract boxfiles
.SH "SYNOPSIS"
.sp
\fBunicharset_extractor\fR \fI[\-D dir]\fR \fIFILE\fR\&...
.SH "DESCRIPTION"
.sp
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:
.sp
.if n \{\
.RS 4
.\}
.nf
unicharset_extractor fontfile_1\&.box fontfile_2\&.box \&.\&.\&.
.fi
.if n \{\
.RE
.\}
.sp
The unicharset will be put into the file \fIdir/unicharset\fR, or simply \fI\&./unicharset\fR if no output directory is provided\&.
.sp
Tesseract also needs to have access to character properties isalpha, isdigit, isupper, islower, ispunctuation\&. all of this auxilury data and more is encoded in this file\&. (See unicharset(5))
.sp
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\&.
.sp
\fBNOTE\fR 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\&.
.SH "SEE ALSO"
.sp
tesseract(1), unicharset(5)
.sp
\m[blue]\fBhttps://github\&.com/tesseract\-ocr/tesseract/wiki/TrainingTesseract\fR\m[]
.SH "HISTORY"
.sp
unicharset_extractor first appeared in Tesseract 2\&.00\&.
.SH "COPYING"
.sp
Copyright (C) 2006, Google Inc\&. Licensed under the Apache License, Version 2\&.0
.SH "AUTHOR"
.sp
The Tesseract OCR engine was written by Ray Smith and his research groups at Hewlett Packard (1985\-1995) and Google (2006\-present)\&.