TY - JOUR
T1 - Robust and secure image hashing via non-negative matrix factorizations
AU - Monga, Vishal
AU - Mihçak, M. Kivanç
N1 - Funding Information:
Manuscript received August 13, 2006; revised May 7, 2007. Part of this work was carried out while the authors were with Microsoft Research, Cryptography and Anti-Piracy Group, Redmond, WA. This work was supported by TÜBITAK under Career Award No. 106E117 and TÜBA-GEBİP Award. The associate editor coordinating the review of this manuscript and approving it for publication was Dr. Christian Cachin.
PY - 2007/9
Y1 - 2007/9
N2 - In this paper, we propose the use of non-negative matrix factorization (NMF) for image hashing. In particular, we view images as matrices and the goal of hashing as a randomized dimensionality reduction that retains the essence of the original image matrix while preventing intentional attacks of guessing and forgery. Our work is motivated by the fact that standard-rank reduction techniques, such as QR and singular value decomposition, produce low-rank bases which do not respect the structure (i.e., non-negativity for images) of the original data. We observe that NMFs have two very desirable properties for secure image hashing applications: 1) The additivity property resulting from the non-negativity constraints results in bases that capture local components of the image, thereby significantly reducing misclassification and 2) the effect of geometric attacks on images in the spatial domain manifests (approximately) as independent identically distributed noise on NMF vectors, allowing the design of detectors that are both computationally simple and, at the same time, optimal in the sense of minimizing error probabilities. Receiver operating characteristics analysis over a large image database reveals that the proposed algorithms significantly outperform existing approaches for image hashing.
AB - In this paper, we propose the use of non-negative matrix factorization (NMF) for image hashing. In particular, we view images as matrices and the goal of hashing as a randomized dimensionality reduction that retains the essence of the original image matrix while preventing intentional attacks of guessing and forgery. Our work is motivated by the fact that standard-rank reduction techniques, such as QR and singular value decomposition, produce low-rank bases which do not respect the structure (i.e., non-negativity for images) of the original data. We observe that NMFs have two very desirable properties for secure image hashing applications: 1) The additivity property resulting from the non-negativity constraints results in bases that capture local components of the image, thereby significantly reducing misclassification and 2) the effect of geometric attacks on images in the spatial domain manifests (approximately) as independent identically distributed noise on NMF vectors, allowing the design of detectors that are both computationally simple and, at the same time, optimal in the sense of minimizing error probabilities. Receiver operating characteristics analysis over a large image database reveals that the proposed algorithms significantly outperform existing approaches for image hashing.
UR - http://www.scopus.com/inward/record.url?scp=34548085689&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=34548085689&partnerID=8YFLogxK
U2 - 10.1109/TIFS.2007.902670
DO - 10.1109/TIFS.2007.902670
M3 - Article
AN - SCOPUS:34548085689
VL - 2
SP - 376
EP - 390
JO - IEEE Transactions on Information Forensics and Security
JF - IEEE Transactions on Information Forensics and Security
SN - 1556-6013
IS - 3
ER -