DocumentCode
3351205
Title
A geometrically-resilient surf-based image fingerprinting scheme
Author
Gigaud, Guillaume ; Moulin, Pierre
Author_Institution
Beckman Inst., Coord. Sci. Lab., & ECE Dept., Univ. of Illinois, Urbana, IL, USA
fYear
2010
fDate
26-29 Sept. 2010
Firstpage
3669
Lastpage
3672
Abstract
Traitor-tracing (aka fingerprinting) has received much attention as a possible solution for protecting media copyrights. However, all the current schemes for image and video lack robustness against geometric attacks. We propose a novel semi-blind algorithm that can cope with such attacks. The algorithm uses compressed SURF features as side information in order to estimate and invert the geometric attack. Moreover the algorithm is highly robust against cropping and additive white noise.
Keywords
copyright; data compression; feature extraction; fingerprint identification; image coding; image watermarking; multimedia computing; white noise; SURF feature compression; additive white noise; fingerprint identification; geometrically-resilient SURF-based image fingerprinting scheme; media copyright protection; semiblind algorithm; traitor-tracing; Decoding; Feature extraction; Fingerprint recognition; Image coding; Pixel; Robustness; Transforms; Copyright Protection; Data Compression; Feature Extraction; Fingerprint Identification; Image Processing;
fLanguage
English
Publisher
ieee
Conference_Titel
Image Processing (ICIP), 2010 17th IEEE International Conference on
Conference_Location
Hong Kong
ISSN
1522-4880
Print_ISBN
978-1-4244-7992-4
Electronic_ISBN
1522-4880
Type
conf
DOI
10.1109/ICIP.2010.5652507
Filename
5652507
Link To Document