AEU - International Journal of Electronics and Communications
Employing intelligence in the embedding and decoding stages of a robust watermarking system
Introduction
Digital watermarking has gained significant popularity within the research community in recent years due to its considerable advantages over the traditional data hiding techniques especially as regards copyright protection [1], [2] and authentication related applications [3]. In case of copyright protection based application, watermarking systems still face the challenge of being robust against real world attack scenarios, which consist of a series of legitimate/illegitimate distortions [4]. These distortions are somewhat conceivable based on application environment and the level of access the attacker has. A watermark is usually concealed in the cover work by keeping in view the response of human perception mechanism. For this reason, it is amplified in the regions where it is imperceptible to the naked eye and attenuated in areas where it could be perceptible. This is referred as perceptual shaping and incorporated by the help of perceptual models based on Human Visual System (HVS). Watson's Perceptual Model (WPM) [5], [6] is a pertinent example along many others proposed in literature [7], [8], [9], [10]. However, these perceptual models are based on visual characteristics alone and altogether lack the shaping ability in view of attacks. This is primarily due to the reason that attack information is not taken into account while designing these models. Therefore, it is judicious to propose new Perceptual Shaping Functions (PSFs) that are able to shape a watermark with respect to its robustness against a series of real world attacks, as well as maintaining its invisibility property. Our approach for developing such PSFs is by employing multi objective Genetic Programming (GP) [11] to generate expressions (PSFs) that make a delicate balance between robustness and imperceptibility at the watermark embedding stage. Through GP simulation, PSFs are evolved by stochastically searching for appropriate coefficient positions and suitable strength of alterations for watermark embedding in Discrete Cosine Transform (DCT) domain. Objective measures for watermark robustness and imperceptibility comprise the fitness function in order to drive the simulation towards an optimum/pareto-optimal region. Similarly, an intelligent watermark extraction strategy is needed at the decoding stage which may adapt itself in accordance to the widespread and dynamic applications of watermarking, where different types of attacks are expected at different instances. In this context, most of the existing watermark extraction strategies [12], [13], [14] do not consider the existence of attacks during the training phase and thus are not adaptive. In the same way, other approaches, such as threshold based decoding techniques [15], [16] are also not versatile towards attacks. These approaches neither considers the alterations that may incur to the features nor exploit the individual frequency bands; rather treat all the frequency bands collectively. Consequently, these approaches use a single feature for extraction of a message bit. Recently, Khan et al. [17] have proposed machine learning (ML) based decoding. However, their system does not employ intelligent embedding. In this letter we propose a novel scheme which utilizes ML techniques at the watermark embedding as well as decoding stages. For this purpose, firstly, we perform GP based intelligent embedding which selects appropriate frequency bands and the magnitude of allowable alterations for watermark embedding. Considering the available frequency bands in an 8 × 8 block DCT, this in turn also acts as a feature reduction strategy. Secondly, we exploit the learning capabilities of Support Vector Machine (SVM) and Artificial Neural Networks (ANN) to gain knowledge of the distortion that might have incurred varyingly on the different selected frequency bands due to the sequence of attacks. Lastly, to perform this efficiently and in an adaptive manner, we devise a new feature extraction strategy for watermark extraction in presence of attacks. Both of the above attributes of the proposed scheme make it extremely difficult for an adversary to gain the secret knowledge of the system by analyzing the embedding and/or decoding space. The paper is organized as follows. Section 2 describes the proposed watermarking system including details of the encoding and decoding phases. Our experimental results are discussed in Section 3 followed by conclusions in Section 4.
Section snippets
Proposed watermark encoding and decoding structures
This work enhances both the encoding and decoding phases of a watermarking system. Fig. 1 illustrates the block diagram of the proposed watermarking system. The following subsections elaborate these ideas.
Capability in terms of watermark shaping
The watermark strength distribution for Trees image and attack scenario B across both frequency and number of blocks is shown in Fig. 2. This strength distribution is generated using the GP based embedding phase of the proposed technique. It can be observed that amplitude of the watermark strength increases with frequency inside each block. This attribute is consistent with HVS modeling, where high watermark strength should be used for high frequencies to reduce the resultant distortion. If we
Conclusions
We have proposed a novel watermarking system with intelligent techniques employed at both the encoding and decoding stages. In view of HVS, GP is used to embed a high energy watermark in frequency bands that are least affected when presented to a sequence of attacks. Similarly, learning capabilities of SVM and ANN are utilized to learn about the induced distortions at the decoding side and estimate the hidden message accordingly. Experimental results on a dataset of test images demonstrate
Acknowledgment
This work was supported by the Higher Education Commission of Pakistan under the indigenous PhD scholarship program (17-5-1(Cu-204)/HEC/Sch/2004)
Imran Usman was born in Quetta, Pakistan in 1980. He studied computer software engineering at the Foundation University, Islamabad and got his BS in software Engineering. He received his MS degree in Computer Systems Engineering in 2006 from Ghulam Ishaq Khan Institute of Engineering Sciences and Technology (GIK Institute), Topi, Pakistan. In Aug 2010, he completed his PhD degree from Pakistan Institute of Engineering and Applied Sciences (PIEAS). His research interests include Digital Image
References (20)
- et al.
Localized image watermarking in spatial domain resistant to geometric attacks
International Journal of Electronics and Communications
(2009) - et al.
Genetic perceptual shaping: utilizing cover image and conceivable attack information using genetic programming
Information Fusion
(2007) - et al.
Blind self-authentication of images for robust watermarking using integer wavelet transforms
International Journal of Electronics and Communications
(2009) Wavelet-based watermarking for color images through visual masking
International Journal of Electronics and Communications
(2010)- et al.
Machine learning based adaptive watermark decoding in view of an anticipated attack
Pattern Recognition
(2008) - et al.
Intelligent watermarking techniques
(2004) Visual optimization of DCT quantization matrices for individual images
- et al.
Visibility of DCT basis functions: effects of contrast masking
- et al.
A vision-based masking model for spread-spectrum image watermarking
IEEE Transactions on Image Processing
(2002) - et al.
Perceptual quality metric for digitally coded color images
Cited by (2)
An overview of information fusion in the domain of watermarking and document security
2013, Information FusionIntelligent reorganized discrete cosine transform for reduced reference image quality assessment
2017, Turkish Journal of Electrical Engineering and Computer Sciences
Imran Usman was born in Quetta, Pakistan in 1980. He studied computer software engineering at the Foundation University, Islamabad and got his BS in software Engineering. He received his MS degree in Computer Systems Engineering in 2006 from Ghulam Ishaq Khan Institute of Engineering Sciences and Technology (GIK Institute), Topi, Pakistan. In Aug 2010, he completed his PhD degree from Pakistan Institute of Engineering and Applied Sciences (PIEAS). His research interests include Digital Image Processing, Evolutionary Algorithms, Digital Watermarking and Machine Learning. From 2002 to 2003 he worked at LMKR as a software developer. From 2003 to 2004 he served in Iqra University, Pakistan, as a lecturer. Currently, he is working as an assistant professor at the Department of Electrical Engineering, COMSATS Institute of Information Technology, Islamabad, Pakistan.
Asifullah Khan received his MSc degree in Physics from University of Peshawar, Pakistan in 1996 and his MS degree in Nuclear Engineering from Pakistan Institute of Engineering and Applied Sciences (PIEAS), Islamabad, Pakistan, in 1998. He received his MS and PhD degrees in Computer Systems Engineering from Ghulam Ishaq Khan Institute of Engineering Sciences and Technology (GIK Institute), Topi, Pakistan, in 2003 and 2006 respectively. From October 1998 to June 2006, he had been working as a Senior Scientist at Pakistan Institute of Nuclear Sciences and Technology (PINSTECH). Currently, he is working as an associate professor in Department of Computer and Information Sciences at PIEAS. His research areas include Digital Watermarking, Pattern Recognition, Genetic Programming, Data Hiding, Machine Learning, and Computational Materials Science.
Rafiullah Chamlawi was born in Pakistan in 1977. He received his MSc in computer science from the University of Peshawar Pakistan in 2001. He completed his MS in computer systems engineering from GIK Institute in 2006. In 2010 he completed his PhD degree in computer science from PIEAS, Pakistan. He joined the Computer Science department at Air University Islamabad Pakistan in August 2010 as an assistant professor. His research interests include Image Processing, Multimedia Security, Digital Watermarking, Machine Learning, and Bioinformatics.