Cumulant-based image fingerprints

A fingerprinting is related to cryptographic hash functions. In contrast to cryptographic hash functions this robust digest is sensitive only to perceptual change. Minor changes, which are not affecting the perception, do not result in a different fingerprint. This technique is used in content-based retrieval, content monitoring, and content filtering. In this paper we present a cumulant-based image fingerprinting method. Cumulants are typically used in signal processing and image processing, e.g. for blind source separation or Independent Component Analysis (ICA). From an image with reduced dimensions we calculate cumulants as an initial feature vector. This feature vector is transformed into an image fingerprint. The theoretical advantages of cumulants are verified in experiments evaluating robustness (e.g. against operations like lossy compression, scaling and cropping) and discriminability. The results show an improved performance our method in comparison to existing methods.

[1]  Laurenz Wiskott,et al.  CuBICA: independent component analysis by simultaneous third- and fourth-order cumulant diagonalization , 2004, IEEE Transactions on Signal Processing.

[2]  Ankur Datta,et al.  Novel feature vector for image authentication , 2003, 2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698).

[3]  F. A. DeCosta,et al.  Neural network recognition of textured images using third order cumulants as functional links , 1992, [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[4]  Benoit M. Macq,et al.  Geometrically invariant watermarking using feature points , 2002, IEEE Trans. Image Process..

[5]  Benoit M. Macq,et al.  A robust soft hash algorithm for digital image signature , 2003, Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429).

[6]  Zhi Ding,et al.  FIR channel estimation through generalized cumulant slice weighting , 2004, IEEE Transactions on Signal Processing.

[7]  Reda R. Gharieb,et al.  Nonlinear cumulant based adaptive filter for simultaneous removal of Gaussian and impulsive noises in images , 2001, 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221).

[8]  Ton Kalker,et al.  Affine transform resilient image fingerprinting , 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..

[9]  Jean-Marc Boucher,et al.  Unsupervised segmentation of radar images using wavelet decomposition and cumulants , 1994, Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing.

[10]  Jitendra K. Tugnait,et al.  Time delay estimation with unknown spatially correlated Gaussian noise , 1991, [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing.

[11]  Shih-Fu Chang,et al.  A robust content based digital signature for image authentication , 1996, Proceedings of 3rd IEEE International Conference on Image Processing.

[12]  Georgios B. Giannakis,et al.  Image motion estimation algorithms using cumulants , 1995, IEEE Trans. Image Process..

[13]  G. Krieger,et al.  Higher-order statistics of natural images and their exploitation by operators selective to intrinsic dimensionality , 1997, Proceedings of the IEEE Signal Processing Workshop on Higher-Order Statistics.

[14]  Chun-Shien Lu,et al.  Robust mesh-based hashing for copy detection and tracing of images , 2004, 2004 IEEE International Conference on Multimedia and Expo (ICME) (IEEE Cat. No.04TH8763).

[15]  T. E. Hall,et al.  Stochastic Image Modeling Using Cumulants With Application To Predictive Image Coding , 1989, Workshop on Higher-Order Spectral Analysis.

[16]  Jerry M. Mendel,et al.  Tutorial on higher-order statistics (spectra) in signal processing and system theory: theoretical results and some applications , 1991, Proc. IEEE.

[17]  Jitendra K. Tugnait,et al.  Identification of linear stochastic systems via second- and fourth-order cumulant matching , 1987, IEEE Trans. Inf. Theory.