Structural Feature-Based Image Hashing and Similarity Metric for Tampering Detection

Structural image features are exploited to construct perceptual image hashes in this work. The image is first preprocessed and divided into overlapped blocks. Correlation between each image block and a reference pattern is calculated. The intermediate hash is obtained from the correlation coefficients. These coefficients are finally mapped to the interval [0, 100], and scrambled to generate the hash sequence. A key component of the hashing method is a specially defined similarity metric to measure the “distance” between hashes. This similarity metric is sensitive to visually unacceptable alterations in small regions of the image, enabling the detection of small area tampering in the image. The hash is robust against content-preserving processing such as JPEG compression, moderate noise contamination, watermark embedding, re-scaling, brightness and contrast adjustment, and low-pass filtering. It has very low collision probability. Experiments are conducted to show performance of the proposed method. (This work was supported by the NSF of China (60773079, 60872116, and 60832010), the High-Tech Res. and Dev. Prog. of China (2007AA01Z477), the Innovative Res. Fdn. of Shanghai Univ. for Ph.D. Programs (shucx080148), and the Sci. Res. Fdn. of Guangxi Normal Univ. for Doctors.)

[1]  Ramarathnam Venkatesan,et al.  Robust image hashing , 2000, Proceedings 2000 International Conference on Image Processing (Cat. No.00CH37101).

[2]  Xinpeng Zhang,et al.  Fragile Watermarking With Error-Free Restoration Capability , 2008, IEEE Transactions on Multimedia.

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

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

[5]  Jiri Fridrich,et al.  Robust hash functions for digital watermarking , 2000, Proceedings International Conference on Information Technology: Coding and Computing (Cat. No.PR00540).

[6]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.

[7]  Jean-René Barra.  Testing Statistical Hypotheses , 1981 .

[8]  Qiming Li,et al.  On the security of non-forgeable robust hash functions , 2008, 2008 15th IEEE International Conference on Image Processing.

[9]  Vishal Monga,et al.  Robust and Secure Image Hashing via Non-Negative Matrix Factorizations , 2007, IEEE Transactions on Information Forensics and Security.

[10]  Andreas Uhl,et al.  Analysis of a wavelet-based robust hash algorithm , 2004, IS&T/SPIE Electronic Imaging.

[11]  Min Wu,et al.  Unicity Distance of Robust Image Hashing , 2007, IEEE Transactions on Information Forensics and Security.

[12]  E. Lehmann.  Testing Statistical Hypotheses , 1960 .

[13]  Fabien A. P. Petitcolas,et al.  Watermarking schemes evaluation , 2000, IEEE Signal Process. Mag..

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

[15]  C. De Vleeschouwer,et al.  Robust video hashing based on radial projections of key frames , 2005, IEEE Transactions on Signal Processing.

[16]  Xinpeng Zhang,et al.  Perceptual Similarity Metric Resilient to Rotation for Application in Robust Image Hashing , 2009, 2009 Third International Conference on Multimedia and Ubiquitous Engineering.

[17]  Jean-Didier Legat,et al.  RASH: RAdon soft hash algorithm , 2002, 2002 11th European Signal Processing Conference.

[18]  Benoit M. Macq,et al.  A robust soft hash algorithm for digital image signature , 2003, Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429).