The use of robust watermarks for attack characterisation is an area of considerable potential which has been largely overlooked to date. The authors extend their earlier work on accurate attack characterisation using a double watermarking technique to include a larger library of attacks. It is shown that the complexity of the double watermarking technique can be reduced with only a very small performance penalty. A further reduction in the algorithm complexity can be achieved by removing the thresholding process from the watermark estimation procedure. Analysis of the nature and location of the characterisation errors for the above methods is also presented.
|Translated title of the contribution||Image tamper detection and classification using Support Vector Machines|
|Pages (from-to)||322 - 328|
|Number of pages||7|
|Journal||IEE Proceedings-Vision, Image and Signal Processing|
|Publication status||Published - Aug 2004|
Bibliographical notePublisher: Institution of Electrical Engineers (IEE)
Rose publication type: Journal article
Sponsorship: This work is supported by Motorola, the Metropolitan
Police and EPSRC grant GR=M81885.