Robust Image Hashing Scheme using Laplacian Pyramids

Abstract Due to tremendous growth in multimedia applications and services, people can easily create, distribute, broadcast and store information. The fact that multimedia content can be easily copied and tampered has motivated a large number of researchers to devise image verification techniques using perceptual image hashing. In this paper, a perceptual image hashing technique is proposed by using difference of Laplacian pyramids. A Laplacian pyramid is a multi-scale representation of an image and can be used to extract stable features. In the proposed scheme, two different pyramids are generated by using filters of different diameters. The difference of Laplacian is calculated to get a unique and robust hash. A number of experiments have been carried out to gauge the effectiveness of the proposed scheme. The results reveal that the proposed technique is robust against non-malicious manipulations and can detect minute level tampering.

[1]  Xiamu Niu,et al.  A Self-Synchronized Image Hash Algorithm , 2010, 2010 International Conference on Communications and Mobile Computing.

[2]  Mohammed Yakoob Siyal,et al.  A secure and robust hash-based scheme for image authentication , 2010, Signal Process..

[3]  Shih-Fu Chang,et al.  A robust image authentication method distinguishing JPEG compression from malicious manipulation , 2001, IEEE Trans. Circuits Syst. Video Technol..

[4]  Sushil K. Bhattacharjee,et al.  Compression tolerant image authentication , 1998, Proceedings 1998 International Conference on Image Processing. ICIP98 (Cat. No.98CB36269).

[5]  Weimin Wei,et al.  Perceptual image hash for tampering detection using Zernike moments , 2010, 2010 IEEE International Conference on Progress in Informatics and Computing.

[6]  Huazhong Shu,et al.  Robust hashing for image authentication using quaternion discrete Fourier transform and log-polar transform , 2015, Digit. Signal Process..

[7]  Lei Xu,et al.  Robust image authentication via locality sensitive hashing with core alignment , 2018, Multimedia Tools and Applications.

[8]  Xinpeng Zhang,et al.  Robust Hashing for Image Authentication Using Zernike Moments and Local Features , 2013, IEEE Transactions on Information Forensics and Security.

[9]  Zhenjun Tang,et al.  Robust image hashing using ring-based entropies , 2013, Signal Process..

[10]  Zheng Qin,et al.  Data embedding in digital images using critical functions , 2017, Signal Process. Image Commun..

[11]  Shichao Zhang,et al.  Robust Image Hashing With Ring Partition and Invariant Vector Distance , 2016, IEEE Transactions on Information Forensics and Security.

[12]  Ramarathnam Venkatesan,et al.  New Iterative Geometric Methods for Robust Perceptual Image Hashing , 2001, Digital Rights Management Workshop.

[13]  Min Wu,et al.  Robust and secure image hashing , 2006, IEEE Transactions on Information Forensics and Security.

[14]  Namitha Sidharthan,et al.  Robust image hashing for content authentication with tampering localization and image recovery , 2017, 2017 International Conference on Energy, Communication, Data Analytics and Soft Computing (ICECDS).

[15]  Vishal Monga,et al.  Perceptual Image Hashing Via Feature Points: Performance Evaluation and Tradeoffs , 2006, IEEE Transactions on Image Processing.

[16]  N. Memon,et al.  Confusion/Diffusion Capabilities of Some Robust Hash Functions , 2006, 2006 40th Annual Conference on Information Sciences and Systems.

[17]  Ramarathnam Venkatesan,et al.  Robust perceptual image hashing via matrix invariants , 2004, 2004 International Conference on Image Processing, 2004. ICIP '04..

[18]  Shichao Zhang,et al.  Robust Image Hashing with Tensor Decomposition , 2019, IEEE Transactions on Knowledge and Data Engineering.

[19]  Lusia Rakhmawati,et al.  A recent survey of self-embedding fragile watermarking scheme for image authentication with recovery capability , 2019, EURASIP J. Image Video Process..

[20]  Shih-Fu Chang,et al.  A Robust and Secure Media Signature Scheme for JPEG Images , 2005, J. VLSI Signal Process..