mirror of
https://github.com/tesseract-ocr/tesseract.git
synced 2024-11-30 23:49:05 +08:00
58e06c8c45
git-svn-id: https://tesseract-ocr.googlecode.com/svn/trunk@670 d0cd1f9f-072b-0410-8dd7-cf729c803f20
95 lines
3.0 KiB
Groff
95 lines
3.0 KiB
Groff
'\" t
|
|
.\" Title: shapeclustering
|
|
.\" Author: [see the "AUTHOR" section]
|
|
.\" Generator: DocBook XSL Stylesheets v1.75.2 <http://docbook.sf.net/>
|
|
.\" Date: 02/09/2012
|
|
.\" Manual: \ \&
|
|
.\" Source: \ \&
|
|
.\" Language: English
|
|
.\"
|
|
.TH "SHAPECLUSTERING" "1" "02/09/2012" "\ \&" "\ \&"
|
|
.\" -----------------------------------------------------------------
|
|
.\" * 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"
|
|
shapeclustering \- shape clustering training for Tesseract
|
|
.SH "SYNOPSIS"
|
|
.sp
|
|
shapeclustering \-D \fIoutput_dir\fR \-U \fIunicharset\fR \-O \fImfunicharset\fR \-F \fIfont_props\fR \-X \fIxheights\fR \fIFILE\fR\&...
|
|
.SH "DESCRIPTION"
|
|
.sp
|
|
shapeclustering(1) takes extracted feature \&.tr files (generated by tesseract(1) run in a special mode from box files) and produces a file \fBshapetable\fR and an enhanced unicharset\&. This program is still experimental, and is not required (yet) for training Tesseract\&.
|
|
.SH "OPTIONS"
|
|
.PP
|
|
\-U \fIFILE\fR
|
|
.RS 4
|
|
The unicharset generated by unicharset_extractor(1)\&.
|
|
.RE
|
|
.PP
|
|
\-D \fIdir\fR
|
|
.RS 4
|
|
Directory to write output files to\&.
|
|
.RE
|
|
.PP
|
|
\-F \fIfont_properties_file\fR
|
|
.RS 4
|
|
(Input) font properties file, where each line is of the following form, where each field other than the font name is 0 or 1:
|
|
.sp
|
|
.if n \{\
|
|
.RS 4
|
|
.\}
|
|
.nf
|
|
\*(Aqfont_name\*(Aq \*(Aqitalic\*(Aq \*(Aqbold\*(Aq \*(Aqfixed_pitch\*(Aq \*(Aqserif\*(Aq \*(Aqfraktur\*(Aq
|
|
.fi
|
|
.if n \{\
|
|
.RE
|
|
.\}
|
|
.RE
|
|
.PP
|
|
\-X \fIxheights_file\fR
|
|
.RS 4
|
|
(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? ]
|
|
.sp
|
|
.if n \{\
|
|
.RS 4
|
|
.\}
|
|
.nf
|
|
\*(Aqfont_name\*(Aq \*(Aqxheight\*(Aq
|
|
.fi
|
|
.if n \{\
|
|
.RE
|
|
.\}
|
|
.RE
|
|
.PP
|
|
\-O \fIFILE\fR
|
|
.RS 4
|
|
The output unicharset that will be given to combine_tessdata(1)\&.
|
|
.RE
|
|
.SH "SEE ALSO"
|
|
.sp
|
|
tesseract(1), cntraining(1), unicharset_extractor(1), combine_tessdata(1), unicharset(5)
|
|
.sp
|
|
\m[blue]\fBhttp://code\&.google\&.com/p/tesseract\-ocr/wiki/TrainingTesseract3\fR\m[]
|
|
.SH "COPYING"
|
|
.sp
|
|
Copyright (C) Google, 2011 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)\&.
|