Radon/Ridgelet Signature for Image Authentication (MA-L1)

Author(s) : Zhen Yao (Dept. of Computer Science, University of Warwick, UK) Nasir Rajpoot (Dept. of Computer Science, University of Warwick, UK)

Abstract : In this paper, we describe a content-based image signature for authentication using the ridgelet transform. The signature is extracted from the Radon domain and entropy coded with 1D wavelet transform, which is essentially the so-called ``ridgelet transform''. Unlike traditional authentication signatures, it has the ability to localise tampering at a high resolution, robust to content-preserving manipulations such as compression and allows a progressive authentication.

Menu