Robust image watermarking based on feature regions

Deng, C; Gao, X; Li, X; Tao, D

Robust image watermarking based on feature regions

Deng, C Gao, X Li, X Tao, D

Permalink

Publication Type:: Chapter
Citation:: 2011, 346 pp. 111 - 137
Issue Date:: 2011-05-09

Closed Access

	Filename	Description	Size
	2011001806OK.pdf	Published version	2.07 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Deng, C	en_US
dc.contributor.author	Gao, X	en_US
dc.contributor.author	Li, X	en_US
dc.contributor.author	Tao, D https://orcid.org/0000-0001-7225-5449	en_US
dc.date.issued	2011-05-09	en_US
dc.identifier.citation	2011, 346 pp. 111 - 137	en_US
dc.identifier.isbn	9783642195501	en_US
dc.identifier.uri	http://hdl.handle.net/10453/31440
dc.description.abstract	In image watermarking, binding the watermark synchronization with the local features has been widely used to provide robustness against geometric distortions as well as common image processing operations. However, in the existing schemes, the problems with random bending attack, nonisotropic scaling, general affine transformation, and combined attacks still remain difficult. In this chapter, we present and discuss the framework of the extraction and selection of the scale-space feature points. We then propose two robust image watermarking algorithms through synchronizing watermarking with the invariant local feature regions centered at feature points. The first algorithm conducts watermark embedding and detection in the affine covariant regions (ACRs). The second algorithm is combining the local circular regions (LCRs) with Tchebichef moments, and local Tchebichef moments (LTMs) are used to embed and detect watermark. These proposed algorithms are evaluated theoretically and experimentally, and are compared with two representative schemes. Experiments are carried out on a set of standard test images, and the preliminary results demonstrate that the developed algorithms improve the performance over these two representative image watermarking schemes in terms of robustness. Towards the overall robustness against geometric distortions and common image processing operations, the LTMs-based method has an advantage over the ACRs-based method. © 2011 Springer-Verlag Berlin Heidelberg.	en_US
dc.relation.isbasedon	10.1007/978-3-642-19551-8_4	en_US
dc.subject.classification	Artificial Intelligence & Image Processing	en_US
dc.title	Robust image watermarking based on feature regions	en_US
dc.type	Chapter
utslib.citation.volume	346	en_US
utslib.for	0801 Artificial Intelligence and Image Processing	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
utslib.copyright.status	closed_access
pubs.publication-status	Published	en_US
pubs.volume	346	en_US

Abstract:

In image watermarking, binding the watermark synchronization with the local features has been widely used to provide robustness against geometric distortions as well as common image processing operations. However, in the existing schemes, the problems with random bending attack, nonisotropic scaling, general affine transformation, and combined attacks still remain difficult. In this chapter, we present and discuss the framework of the extraction and selection of the scale-space feature points. We then propose two robust image watermarking algorithms through synchronizing watermarking with the invariant local feature regions centered at feature points. The first algorithm conducts watermark embedding and detection in the affine covariant regions (ACRs). The second algorithm is combining the local circular regions (LCRs) with Tchebichef moments, and local Tchebichef moments (LTMs) are used to embed and detect watermark. These proposed algorithms are evaluated theoretically and experimentally, and are compared with two representative schemes. Experiments are carried out on a set of standard test images, and the preliminary results demonstrate that the developed algorithms improve the performance over these two representative image watermarking schemes in terms of robustness. Towards the overall robustness against geometric distortions and common image processing operations, the LTMs-based method has an advantage over the ACRs-based method. © 2011 Springer-Verlag Berlin Heidelberg.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/31440