From Code to Community: Sponsoring The Perl and Raku Conference 2025 Learn more

LEOCHARRE / Image-OCR-Tesseract-1.26 / bin / ocr 

            

              
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
—
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123

              
#!/usr/bin/perl
use strict;
use base 'LEOCHARRE::CLI';
use Cwd;
our $VERSION = sprintf "%d.%02d", q$Revision: 1.7 $ =~ /(\d+)/g;
use Image::OCR::Tesseract 'get_ocr';
my $o = gopts('bl:vdh');
$Image::OCR::Tesseract::DEBUG=1 if $o->{d};
sub usage {q{ocr [OPTION]... FILE...
Read an image as text and output to stdout.
   -b          blowup (useful for small images)
   -d          debug
   -h          help
   -l string   language
   -v          version
Try 'man ocr' for more information.
}}
my $images = argv_aspaths();
$images and scalar @$images or die("Missing path to image files.\n");
IMAGE: for my $abs_image (@$images){ ### Getting OCR %
   if ($o->{b}){ # blowup
      my $_abs_image = $abs_image;
      $_abs_image=~s/(\.\w{1,5})$/_tmp$1/ or die;
      require File::Which;
      system( 
         File::Which::which('convert'), $abs_image, 
         #'-resize','1500x1500',
         '-contrast', '-normalize','-colorspace','Gray',$_abs_image) == 0 or die($?);
      $abs_image = $_abs_image;
   }
   my $ocr;
    
   if( $ocr = get_ocr($abs_image,undef, $o->{l}) ){
      if ($o->{b}){ 
         unlink $abs_image;
      }
      print $ocr;
      next IMAGE;
   }
   warn("nothing inside $abs_image?\n");
   if ($o->{b}){
      unlink $abs_image;
   }
}
exit;
__END__
=pod
=head1 NAME
ocr - perform ocr on an image and output text to stdout
=head1 DESCRIPTION
This is just an interface to make it quick an easy to get ocr output from an image file.
No matter what image type you provide, imagemagick convert is called to turn it into the format
for tesseract.
=head1 USAGE
ocr [OPTION]... FILE...
   -b          blowup (useful for small images)
   -d          debug
   -h          help
   -l string   language
   -v          version
=head2 EXAMPLE USAGE
   ocr ./image.jpg > ./savetext.txt
   ocr ./image.png
   ocr ./image1.jpg ./image2.jpg > ./alltext.txt
   ocr ./image*jpg
=head1 SEE ALSO
Image::OCR::Tesseract - parent package
tesseract - look up google ocr project
convert - from ImageMagick suite.
=head1 COPYRIGHT
Copyright (c) 2010 Leo Charre. All rights reserved.
=head1 LICENSE
This package is free software; you can redistribute it and/or modify it under the same terms as Perl itself, i.e., under the terms of the "Artistic License" or the "GNU General Public License".
=head1 DISCLAIMER
This package is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
See the "GNU General Public License" for more details.
=cut
~                                                                                                  
~                                                                                                  
~                                                                                                  
~                                                                                                  
~