An Adaptive Curvelet Based Semi-Fragile Watermarking Scheme for Effective and Intelligent Tampering Classification and Recovery of Digital Images

An Adaptive Curvelet Based Semi-Fragile Watermarking Scheme for Effective and Intelligent Tampering Classification and Recovery of Digital Images

K R. Chetan (Jawaharlal Nehru National College of Engineering, Shimoga, India) and S Nirmala (Jawaharlal Nehru National College of Engineering, Shimoga, India)
Copyright: © 2018 |Pages: 26
DOI: 10.4018/IJRSDA.2018040104
OnDemand PDF Download:
List Price: $37.50
10% Discount:-$3.75


A novel adaptive semi-fragile watermarking scheme for tamper detection and recovery of digital images is proposed in this paper. This scheme involves embedding of content and chroma watermarks generated from the first level Discrete Curvelet Transform (DCLT) coarse coefficients. Embedding is performed by quantizing the first level coarse DCLT coefficients of the input image and amount of quantization is intelligently decided based on the energy contribution of the coefficients. During watermark extraction, a tampered matrix is generated by comparing the feature similarity index value between each block of extracted and generated watermarks. The tampered objects are subsequently identified and an intelligent report is formed based on their severity classes. The recovery of the tampered objects is performed using the generated DCLT coefficients from luminance and chrominance components of the watermarked image. Results reveal that the proposed method outperforms existing method in terms of tamper detection and recovery of digital images.
Article Preview


Digital watermarking is mainly used for protection of the integrity and authenticity of the digital images across a wide range of applications. There a myriad of application areas of digital watermarking like Content identification and management, Content protection for audio and video content, Forensics and piracy deterrence, Communication of ownership and copyrights, Document and image security, Authentication of content and objects (includes government IDs), Broadcast monitoring and others (Ingemar, Matt & Jeffrey,2000). Digital watermarking provisions effective content identification by embedding a unique digital identity to all forms of media content. It is imperceptible to humans, but easily detected and understood by computers, networks and a wide range of common digital devices (Vipula,2011). The usage of watermarks for content management has been discussed in depth by the authors (Shing-Chi, Dickson & Cedric, 2008; Dominic, 2012). Digital watermarking provides an additional layer of security to the content protection chain to combat the unauthorized use of multimedia content. This is achieved by embedding watermarks that identify the permitted uses of the content into the music or motion picture soundtrack prior to theatrical, packaged media and online digital distribution. Devices read the watermark during playback or copying of content. If the watermark indicates that the use is unauthorized, the playback or copying is stopped or the audio is muted, and an explanatory message may be displayed. Few notable works in area of multimedia protection using watermarking is discussed in (Chang-Tsun, 2008; Chun-Shien, 2005). Forensic watermark applications enhance content owner's ability to detect and respond to misuse of its assets. Forensic watermarking is used not only to gather evidence for criminal proceedings, but also to enforce contractual usage agreements between a content owner and the people or companies with which it shares its content (Banerjee et al. 2015). It provides positive, irrefutable evidence of misuse for leaked content assets. Forensic watermarking applications are discussed in detail by the authors (Dey, Das, Das & Chaudhuri, 2012; Chakraborty, Maji, Pal, Biswas & Dey, 2014; Dey, Biswas, Das, Das & Chaudhuri, 2012). Document images are widely and rapidly used in multiple manifestations, through email and across the Internet.

Complete Article List

Search this Journal:
Volume 9: 1 Issue (2023): Forthcoming, Available for Pre-Order
Volume 8: 1 Issue (2022): Forthcoming, Available for Pre-Order
Volume 7: 4 Issues (2021): 1 Released, 3 Forthcoming
Volume 6: 3 Issues (2019)
Volume 5: 4 Issues (2018)
Volume 4: 4 Issues (2017)
Volume 3: 4 Issues (2016)
Volume 2: 2 Issues (2015)
Volume 1: 2 Issues (2014)
View Complete Journal Contents Listing