This demo allows the user to compute the HPS and VPS distance of a CPS pattern.
This can be used to detect what class of printers was used to generate the analyzed document.
The output gives the computed HPS and VPS distances (in [inch]) and also the image
with the extracted dots.
Computation of HPS and VPS distances
More information CPS codes (a.k.a. tracking dots, yellow dots) can be found on the website of
the Electronic Frontier Foundation
For further details please refer to:
J. van Beusekom, M. Schreyer, T. M. Breuel:
Automatic Counterfeit Protection System Code Classification
J. S. Tweedy. Class characteristics of counterfeit protection system codes of color laser copiers. Journal of the American Society of Questioned Document Examiners, 4(2):5366, 2001
- Please make sure that the file is not larger than 50MByte!
- Please use PNG files as input and do not convert the scanned file into JPEG format (JPEG artifacts may destroy the tiny yellow dots)
- Using a resolution of 600 dpi results in mostly clearly visible dots (do not use less than 300dpi)
- Depending on the size and the content of the page, processing may take up to five minutes, so please be patient :-)
- Results are cached as the computation of the VPS and HPS distances is expensive
You can either submit an image through the form interface, or you can
submit it programmatically through HTTP.
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):
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 'firstname.lastname@example.org;type=image/png;resolution=300' 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.).