 |
Document Security - Line Orientation |
Here we provide an on-line demo of our line orientation check for document security checks.
For further details please refer to:
J. van Beusekom, F. Shafait, T. M. Breuel:
Automatic Line Orientation Measurement for Questioned Document Examination, Int. Workshop on Computational Forensics, The Hague, Netherlands, 2009.
Notes:
- This demo is a visualization of the results of line orientation measurements. The following steps are run:
- The input image binarized (using a global threshold of 128)
- The input image is deskewed
- The text-lines are extracted
- Statistics of the rotation angles of the text-lines are extracted
- The highlighting of the lines is done according to their level of suspiciousness defined by the statistics of the rotation angles
- The colors in the resulting image describe the degree of suspiciousness:
- red lines have a rotation angle that is outside of the 99.7% confidence interval
- orange lines have a rotation angle that is inside the 99.7% confidence interval
- green-orange lines have a rotation angle that is inside the 95% confidence interval
- green lines have a rotation angle that is inside the 68% confidence interval
You can either submit an image through the form interface, or you can
submit it programmatically through HTTP.
Form Interface
If you do not have an image at hand or want to try some of our images, try one of these (note that results are cached, so this is faster than using a new image):
Programmatic Interface
To submit your image programmatically, you can simply POST to this URL; the
image should be a parameter named "imagefile".
From the command line, you can do this using:
curl -D header.out -F 'imagefile=@input.jpg;type=image/jpeg' http://demo-madm.dfki.uni-kl.de/line-orientation/index.php > output.png
You can also do this easily using the HTTP implementation in your favorite
programming language (C#, Python, Java, Perl, etc.).