pyrox.dev / nixpkgs
lol
fork atom

nixos/testing: Improve quality of OCR

First of all, we're now using ImageMagick to improve the screenshot so
that Tesseract has an esier time to recognize the text. The resulting
image of this post-processing is a scaled up black-and-white version
with the backgrounds almost entirely removed and the text edges a bit
blurred, so the screen shots now more or less resemble an image from a
scanner rather. This is what Tesseract is trained for by default.

As mentioned in the previous commit we now also use Tesseract 4, which
further improves the quality of text recognition.

I've spent countless hours just to test different postprocessing
variants and testing what works best for our tests and this is the one
that worked best so far. It's certainly not perfect and I'd like to
avoid the scaling step but we're way better off than before.

In addition to this, the OCR process is now done without an intermediate
file, solely using pipes.

I've tested this using the following VM tests which have OCR enabled:

* nixos/tests/chromium.nix -A stable
* nixos/tests/emacs-daemon.nix
* nixos/tests/installer.nix -A luksroot
* nixos/tests/lightdm.nix
* nixos/tests/plasma5.nix
* nixos/tests/sddm.nix

All of the tests still succeed and comparing some of the recognition
results to the earlier results it now also detects a lot more text than
before this commit.

Signed-off-by: aszlig <aszlig@redmoonstudios.org>

aszlig a443bdc0 7b5263e1

options
unified split
Changed files
+14 -9
nixos
lib
test-driver
Machine.pm
testing.nix
+11 -7
nixos/lib/test-driver/Machine.pm 
···

       
542

       
542

       
 

       
    $self->nest("performing optical character recognition", sub {


     

       
543

       
543

       
 

       
        my $tmpbase = Cwd::abs_path(".")."/ocr";


     

       
544

       
544

       
 

       
        my $tmpin = $tmpbase."in.ppm";


     

       
545

       

       
-

       
        my $tmpout = "$tmpbase.ppm";


     

       
546

       
545

       
 

       



     

       
547

       
546

       
 

       
        $self->sendMonitorCommand("screendump $tmpin");


     

       
548

       

       
-

       
        system("ppmtopgm $tmpin | pamscale 4 -filter=lanczos > $tmpout") == 0


     

       
549

       

       
-

       
            or die "cannot scale screenshot";


     

       

       
547

       
+

       



     

       

       
548

       
+

       
        my $magickArgs = "-filter Catrom -density 72 -resample 300 "


     

       

       
549

       
+

       
                       . "-contrast -normalize -despeckle -type grayscale "


     

       

       
550

       
+

       
                       . "-sharpen 1 -posterize 3 -negate -gamma 100 "


     

       

       
551

       
+

       
                       . "-blur 1x65535";


     

       

       
552

       
+

       
        my $tessArgs = "-c debug_file=/dev/null --psm 11 --oem 2";


     

       

       
553

       
+

       



     

       

       
554

       
+

       
        $text = `convert $magickArgs $tmpin tiff:- | tesseract - - $tessArgs`;


     

       

       
555

       
+

       
        my $status = $? >> 8;


     

       
550

       
556

       
 

       
        unlink $tmpin;


     

       
551

       

       
-

       
        system("tesseract $tmpout $tmpbase") == 0 or die "OCR failed";


     

       
552

       

       
-

       
        unlink $tmpout;


     

       
553

       

       
-

       
        $text = read_file("$tmpbase.txt");


     

       
554

       

       
-

       
        unlink "$tmpbase.txt";


     

       

       
557

       
+

       



     

       

       
558

       
+

       
        die "OCR failed with exit code $status" if $status != 0;


     

       
555

       
559

       
 

       
    });


     

       
556

       
560

       
 

       
    return $text;


     

       
557

       
561

       
 

       
}
+3 -2
nixos/lib/testing.nix 
···

       
93

       
93

       
 

       



     

       
94

       
94

       
 

       
      vms = map (m: m.config.system.build.vm) (lib.attrValues nodes);


     

       
95

       
95

       
 

       



     

       
96

       

       
-

       
      ocrProg = tesseract.override { enableLanguages = [ "eng" ]; };


     

       

       
96

       
+

       
      ocrProg = tesseract_4.override { enableLanguages = [ "eng" ]; };


     

       
97

       
97

       
 

       



     

       
98

       
98

       
 

       
      # Generate onvenience wrappers for running the test driver


     

       
99

       
99

       
 

       
      # interactively with the specified network, and for starting the


     
···

       
111

       
111

       
 

       
          vms=($(for i in ${toString vms}; do echo $i/bin/run-*-vm; done))


     

       
112

       
112

       
 

       
          wrapProgram $out/bin/nixos-test-driver \


     

       
113

       
113

       
 

       
            --add-flags "''${vms[*]}" \


     

       
114

       

       
-

       
            ${lib.optionalString enableOCR "--prefix PATH : '${ocrProg}/bin'"} \


     

       

       
114

       
+

       
            ${lib.optionalString enableOCR


     

       

       
115

       
+

       
              "--prefix PATH : '${ocrProg}/bin:${imagemagick}/bin'"} \


     

       
115

       
116

       
 

       
            --run "testScript=\"\$(cat $out/test-script)\"" \


     

       
116

       
117

       
 

       
            --set testScript '$testScript' \


     

       
117

       
118

       
 

       
            --set VLANS '${toString vlans}'