'\" t
.\"     Title: text2image
.\"    Author: [see the "AUTHOR" section]
.\" Generator: DocBook XSL Stylesheets vsnapshot <http://docbook.sf.net/>
.\"      Date: 03/26/2024
.\"    Manual: \ \&
.\"    Source: \ \&
.\"  Language: English
.\"
.TH "TEXT2IMAGE" "1" "03/26/2024" "\ \&" "\ \&"
.\" -----------------------------------------------------------------
.\" * 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"
text2image \- generate OCR training pages\&.
.SH "SYNOPSIS"
.sp
\fBtext2image\fR \-\-text \fIFILE\fR \-\-outputbase \fIPATH\fR \-\-fonts_dir \fIPATH\fR [OPTION]
.SH "DESCRIPTION"
.sp
text2image(1) generates OCR training pages\&. Given a text file it outputs an image with a given font and degradation\&.
.SH "OPTIONS"
.PP
\fI\-\-text FILE\fR
.RS 4
File name of text input to use for creating synthetic training data\&. (type:string default:)
.RE
.PP
\fI\-\-outputbase FILE\fR
.RS 4
Basename for output image/box file (type:string default:)
.RE
.PP
\fI\-\-fontconfig_tmpdir PATH\fR
.RS 4
Overrides fontconfig default temporary dir (type:string default:/tmp)
.RE
.PP
\fI\-\-fonts_dir PATH\fR
.RS 4
If empty it use system default\&. Otherwise it overrides system default font location (type:string default:)
.RE
.PP
\fI\-\-font FONTNAME\fR
.RS 4
Font description name to use (type:string default:Arial)
.RE
.PP
\fI\-\-writing_mode MODE\fR
.RS 4
Specify one of the following writing modes\&.
\fIhorizontal\fR
: Render regular horizontal text\&. (default)
\fIvertical\fR
: Render vertical text\&. Glyph orientation is selected by Pango\&.
\fIvertical\-upright\fR
: Render vertical text\&. Glyph orientation is set to be upright\&. (type:string default:horizontal)
.RE
.PP
\fI\-\-tlog_level INT\fR
.RS 4
Minimum logging level for tlog() output (type:int default:0)
.RE
.PP
\fI\-\-max_pages INT\fR
.RS 4
Maximum number of pages to output (0=unlimited) (type:int default:0)
.RE
.PP
\fI\-\-degrade_image BOOL\fR
.RS 4
Degrade rendered image with speckle noise, dilation/erosion and rotation (type:bool default:true)
.RE
.PP
\fI\-\-rotate_image BOOL\fR
.RS 4
Rotate the image in a random way\&. (type:bool default:true)
.RE
.PP
\fI\-\-strip_unrenderable_words BOOL\fR
.RS 4
Remove unrenderable words from source text (type:bool default:true)
.RE
.PP
\fI\-\-ligatures BOOL\fR
.RS 4
Rebuild and render ligatures (type:bool default:false)
.RE
.PP
\fI\-\-exposure INT\fR
.RS 4
Exposure level in photocopier (type:int default:0)
.RE
.PP
\fI\-\-resolution INT\fR
.RS 4
Pixels per inch (type:int default:300)
.RE
.PP
\fI\-\-xsize INT\fR
.RS 4
Width of output image (type:int default:3600)
.RE
.PP
\fI\-\-ysize INT\fR
.RS 4
Height of output image (type:int default:4800)
.RE
.PP
\fI\-\-margin INT\fR
.RS 4
Margin round edges of image (type:int default:100)
.RE
.PP
\fI\-\-ptsize INT\fR
.RS 4
Size of printed text (type:int default:12)
.RE
.PP
\fI\-\-leading INT\fR
.RS 4
Inter\-line space (in pixels) (type:int default:12)
.RE
.PP
\fI\-\-box_padding INT\fR
.RS 4
Padding around produced bounding boxes (type:int default:0)
.RE
.PP
\fI\-\-char_spacing DOUBLE\fR
.RS 4
Inter\-character space in ems (type:double default:0)
.RE
.PP
\fI\-\-underline_start_prob DOUBLE\fR
.RS 4
Fraction of words to underline (value in [0,1]) (type:double default:0)
.RE
.PP
\fI\-\-underline_continuation_prob DOUBLE\fR
.RS 4
Fraction of words to underline (value in [0,1]) (type:double default:0)
.RE
.PP
\fI\-\-render_ngrams BOOL\fR
.RS 4
Put each space\-separated entity from the input file into one bounding box\&. The ngrams in the input file will be randomly permuted before rendering (so that there is sufficient variety of characters on each line)\&. (type:bool default:false)
.RE
.PP
\fI\-\-output_word_boxes BOOL\fR
.RS 4
Output word bounding boxes instead of character boxes\&. This is used for Cube training, and implied by \-\-render_ngrams\&. (type:bool default:false)
.RE
.PP
\fI\-\-unicharset_file FILE\fR
.RS 4
File with characters in the unicharset\&. If \-\-render_ngrams is true and \-\-unicharset_file is specified, ngrams with characters that are not in unicharset will be omitted (type:string default:)
.RE
.PP
\fI\-\-bidirectional_rotation BOOL\fR
.RS 4
Rotate the generated characters both ways\&. (type:bool default:false)
.RE
.PP
\fI\-\-only_extract_font_properties BOOL\fR
.RS 4
Assumes that the input file contains a list of ngrams\&. Renders each ngram, extracts spacing properties and records them in output_base/[font_name]\&.fontinfo file\&. (type:bool default:false)
.RE
.SH "USE THESE FLAGS TO OUTPUT ZERO\-PADDED, SQUARE INDIVIDUAL CHARACTER IMAGES"
.PP
\fI\-\-output_individual_glyph_images BOOL\fR
.RS 4
If true also outputs individual character images (type:bool default:false)
.RE
.PP
\fI\-\-glyph_resized_size INT\fR
.RS 4
Each glyph is square with this side length in pixels (type:int default:0)
.RE
.PP
\fI\-\-glyph_num_border_pixels_to_pad INT\fR
.RS 4
Final_size=glyph_resized_size+2*glyph_num_border_pixels_to_pad (type:int default:0)
.RE
.SH "USE THESE FLAGS TO FIND FONTS THAT CAN RENDER A GIVEN TEXT"
.PP
\fI\-\-find_fonts BOOL\fR
.RS 4
Search for all fonts that can render the text (type:bool default:false)
.RE
.PP
\fI\-\-render_per_font BOOL\fR
.RS 4
If find_fonts==true, render each font to its own image\&. Image filenames are of the form output_name\&.font_name\&.tif (type:bool default:true)
.RE
.PP
\fI\-\-min_coverage DOUBLE\fR
.RS 4
If find_fonts==true, the minimum coverage the font has of the characters in the text file to include it, between 0 and 1\&. (type:double default:1)
.RE
.sp
Example Usage: ``` text2image \-\-find_fonts \e \-\-fonts_dir /usr/share/fonts \e \-\-text \&.\&./langdata/hin/hin\&.training_text \e \-\-min_coverage \&.9 \e \-\-render_per_font \e \-\-outputbase \&.\&./langdata/hin/hin \e |& grep raw | sed \-e \fIs/ :\&.*/" \e\e/g\fR | sed \-e \fIs/^/ "/\fR >\&.\&./langdata/hin/fontslist\&.txt ```
.SH "SINGLE OPTIONS"
.PP
\fI\-\-list_available_fonts BOOL\fR
.RS 4
List available fonts and quit\&. (type:bool default:false)
.RE
.SH "HISTORY"
.sp
text2image(1) was first made available for tesseract 3\&.03\&.
.SH "RESOURCES"
.sp
Main web site: \m[blue]\fBhttps://github\&.com/tesseract\-ocr\fR\m[] Information on training tesseract LSTM: \m[blue]\fBhttps://tesseract\-ocr\&.github\&.io/tessdoc/TrainingTesseract\-4\&.00\&.html\fR\m[]
.SH "SEE ALSO"
.sp
tesseract(1)
.SH "COPYING"
.sp
Copyright (C) 2012 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)\&.