mirror of
https://github.com/tesseract-ocr/tesseract.git
synced 2024-12-24 15:47:48 +08:00
95 lines
3.0 KiB
Groff
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)\&.
|