A novel watermarking scheme based on the support vector machine is proposed. The watermark is embedded in the blue channel of a colour image. By applying the embedded extra reference watermark, the support vector machine is trained, and then the watermark can be extracted by the trained support vector machine. Owing to the good generalisation ability of the support vector machine, even when the watermarked image is heavily distorted the watermark can be successfully extracted. Experimental results show good robustness of the proposed scheme.
References
-
-
1)
-
C. Campbell
.
Kernel methods: a survey of current techniques.
Neurocomputing
,
63 -
84
-
2)
-
M. Kutter ,
F. Jordan ,
F. Bossen
.
Digital watermarking of color images using amplitude modulation.
J. Electron. Imaging
,
2 ,
326 -
332
-
3)
-
J.C. Christopher
.
A tutorial on support vector machines for pattern recognition.
Data Min. Knowl. Discov.
,
121 -
167
-
4)
-
V. Vapnik
.
(1995)
The nature of statistical learning theory.
-
5)
-
V.N. Vapnik
.
(1998)
Statistical learning theory.
-
6)
-
Y.Q. Shi ,
H. Sun
.
(1999)
Image and video compression for multimedia engineering: fundamentals, algorithms, and standards.
-
7)
-
P.T. Yu ,
H.-H. Tsai ,
J.-S. Lin
.
Digital watermarking based on neural networks for color images.
Signal Process.
,
663 -
671
-
8)
-
C.S. Shieh ,
H.C. Huang ,
F.H. Wang ,
J.S. Pan
.
Genetic watermarking based on transform-domain technique.
Pattern Recognit.
,
555 -
565
http://iet.metastore.ingenta.com/content/journals/10.1049/el_20040600
Related content
content/journals/10.1049/el_20040600
pub_keyword,iet_inspecKeyword,pub_concept
6
6