tesseract/doc/mftraining.1
2015-06-13 00:08:05 +02:00

95 lines
3.0 KiB
Groff

'\" t
.\" Title: mftraining
.\" 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 "MFTRAINING" "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"
mftraining \- feature training for Tesseract
.SH "SYNOPSIS"
.sp
mftraining \-U \fIunicharset\fR \-O \fIlang\&.unicharset\fR \fIFILE\fR\&...
.SH "DESCRIPTION"
.sp
mftraining takes a list of \&.tr files, from which it generates the files \fBinttemp\fR (the shape prototypes), \fBshapetable\fR, and \fBpffmtable\fR (the number of expected features for each character)\&. (A fourth file called Microfeat is also written by this program, but it is not used\&.)
.SH "OPTIONS"
.PP
\-U \fIFILE\fR
.RS 4
(Input) The unicharset generated by unicharset_extractor(1)
.RE
.PP
\-F \fIfont_properties_file\fR
.RS 4
(Input) font properties file, 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
*font_name* *italic* *bold* *fixed_pitch* *serif* *fraktur*
.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
*font_name* *xheight*
.fi
.if n \{\
.RE
.\}
.RE
.PP
\-D \fIdir\fR
.RS 4
Directory to write output files to\&.
.RE
.PP
\-O \fIFILE\fR
.RS 4
(Output) 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), shapeclustering(1), unicharset(5)
.sp
\m[blue]\fBhttps://github\&.com/tesseract\-ocr/tesseract/wiki/TrainingTesseract\fR\m[]
.SH "COPYING"
.sp
Copyright (C) Hewlett\-Packard Company, 1988 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)\&.