Counterfeiting is a major concern for brand owners. Since printing is used to convey brands, brand owners should be able to analyze images of printed areas to gauge if the printing was performed by an authentic or a counterfeit printer/label converter. In this paper, we describe a system that uses a small set of pre-classified images (either authentic or counterfeit images from the same source) for initial training, and thereafter adaptively classifies and clusters images from multiple sources as they join the population to be classified. Authentic images and multiple sources of counterfeit images are identified, and secondary links between the non-compliant samples are provided. The system currently uses a set of 420 metrics which are filtered to a smaller set of features that can reliably describe our known set. This filtered set of features, or feature signature, is used for the search and clustering thereafter. We describe the use of this system to streamline and enhance investigations for a global brand protection program.
[1]
Adam Finkelstein,et al.
Fingerprinting Blank Paper Using Commodity Scanners
,
2009,
2009 30th IEEE Symposium on Security and Privacy.
[2]
Jan P. Allebach,et al.
Printer Forensics Using SVM Techniques
,
2005,
NIP & Digital Fabrication Conference.
[3]
Anil K. Jain,et al.
On image classification: city vs. landscape
,
1998,
Proceedings. IEEE Workshop on Content-Based Access of Image and Video Libraries (Cat. No.98EX173).
[4]
Gang Xiong,et al.
Forgery: ‘Fingerprinting’ documents and packaging
,
2005,
Nature.