Robust image hashing via visual attention model and ring partition

Zhenjun Tang; Yongzheng Yu; Hanyun Zhang; Mengzhu Yu; Chunqiang Yu; Xianquan Zhang; Zhenjun Tang; Yongzheng Yu; Hanyun Zhang; Mengzhu Yu; Chunqiang Yu; Xianquan Zhang

doi:10.3934/mbe.2019305

Mathematical Biosciences and Engineering

2019, Volume 16, Issue 5: 6103-6120. doi: 10.3934/mbe.2019305

Previous Article Next Article

Research article Special Issues

Robust image hashing via visual attention model and ring partition

Guangxi Key Lab of Multi-source Information Mining & Security, and Department of Computer Science, Guangxi Normal University, Guilin 541004, China

Received: 06 March 2019 Accepted: 24 June 2019 Published: 03 July 2019

Robustness is an important property of image hashing. Most of the existing hashing algorithms do not reach good robustness against large-angle rotation. Aiming at this problem, we jointly exploit visual attention model and ring partition to design a novel image hashing, which can make good rotation robustness. In the proposed image hashing, a visual attention model called PFT (Phase spectrum of Fourier Transform) model is used to detect saliency map of preprocessed image. The LL sub-band of saliency map is then divided into concentric circles invariant to rotation by ring partition, and the means and variances of DWT coefficients on concentric circles are taken as image features. Next, these features are encrypted by a chaotic map and the Euclidean distances between normalized encrypted features are finally exploited to generate hash. Similarity between hashes is measured by L₁ norm. Many experimental tests show that our image hashing is robust to digital operations including rotation and reaches good discrimination. Comparisons demonstrate that classification performance of our image hashing outperforms those of some well-known hashing algorithms in terms of receiver operating characteristics curves. Simulation of image copy detection is carried out on an open image database called UCID and the result validates effectiveness of our hashing.
- image hashing,
- visual attention model,
- ring partition,
- saliency map,
- image copy detection
Citation: Zhenjun Tang, Yongzheng Yu, Hanyun Zhang, Mengzhu Yu, Chunqiang Yu, Xianquan Zhang. Robust image hashing via visual attention model and ring partition[J]. Mathematical Biosciences and Engineering, 2019, 16(5): 6103-6120. doi: 10.3934/mbe.2019305

Related Papers:

Abstract

Robustness is an important property of image hashing. Most of the existing hashing algorithms do not reach good robustness against large-angle rotation. Aiming at this problem, we jointly exploit visual attention model and ring partition to design a novel image hashing, which can make good rotation robustness. In the proposed image hashing, a visual attention model called PFT (Phase spectrum of Fourier Transform) model is used to detect saliency map of preprocessed image. The LL sub-band of saliency map is then divided into concentric circles invariant to rotation by ring partition, and the means and variances of DWT coefficients on concentric circles are taken as image features. Next, these features are encrypted by a chaotic map and the Euclidean distances between normalized encrypted features are finally exploited to generate hash. Similarity between hashes is measured by L₁ norm. Many experimental tests show that our image hashing is robust to digital operations including rotation and reaches good discrimination. Comparisons demonstrate that classification performance of our image hashing outperforms those of some well-known hashing algorithms in terms of receiver operating characteristics curves. Simulation of image copy detection is carried out on an open image database called UCID and the result validates effectiveness of our hashing.

References

[1]	Z. Tang, Z. Huang, X. Q. Zhang, et al., Robust image hashing with multidimensional scaling, Signal Process., 137(2017), 240–250.
[2]	C. Qin, X. Chen, D. Ye, et al., A novel image hashing scheme with perceptual robustness using block truncation coding, Inform. Sci., 361(2016), 84–99.
[3]	Z. Tang, L. Chen, X. Q. Zhang, et al., Robust image hashing with tensor decomposition, IEEE Trans. Knowl. Data En., 31(2019), 549–560.
[4]	Z. Tang, S. Wang, X. P. Zhang, et al., Lexicographical framework for image hashing with implementation based on DCT and NMF, Multimed. Tools Appl., 52(2011), 325–345.
[5]	F. Lefebvre, B. Macq and J. D. Legat, RASH: Radon soft hash algorithm, In: Proc. of European Signal Processing Conference, Toulouse, France, Sep. 3−6, 2002, pp.299–302.
[6]	A. Swaminathan, Y. Mao and M. Wu, Robust and secure image hashing, IEEE Trans. Inf. Foren. Secur., 1(2006), 215–230.
[7]	V. Monga and B. L. Evans, Perceptual image hashing via feature points: performance evaluation and trade-offs, IEEE Trans. Image Process., 15(2006), 3453–3466.
[8]	Y. Ou and K. H. Rhee, A key-dependent secure image hashing scheme by using Radon transform, In: Proc. of the IEEE International Symposium on Intelligent Signal Processing and Communication Systems, pp.595–598, 2009.
[9]	Z. Tang, S. Wang, X. P. Zhang, et al., Structural feature-based image hashing and similarity metric for tampering detection, Fundam. Inf., 106(2011), 75–91.
[10]	C. Qin, C. C. Chang and P. L. Tsou, Robust image hashing using non-uniform sampling in discrete Fourier domain, Digit. Signal Process., 23(2013), 578–585.
[11]	Z. Tang, X. Q. Zhang, L. Huang, et al., Robust image hashing using ring-based entropies, Signal Process., 93(2013), 2061–2069.
[12]	Z. Tang, Y. Dai, X. Q. Zhang, et al., Robust image hashing via colour vector angles and discrete wavelet transform, IET Image Process., 8(2014), 142–149.
[13]	L. Ghouti, Robust perceptual color image hashing using quaternion singular value decomposition, In: Proc. of IEEE International Conference on Acoustic, Speech and Signal Processing (ICASSP 2014), pp.3794–3798, 2014.
[14]	C. Yan, C. Pun and X. Yuan, Quaternion-based image hashing for adaptive tampering localization, IEEE Trans. Inf. Foren. Secur., 11(2016), 2664–2677.
[15]	C. Qin, X. Chen, J. Dong, et al., Perceptual image hashing with selective sampling for salient structure features, Displays, 45(2016), 26–37.
[16]	Z. Tang, X. Q. Zhang, X. Li, et al., Robust image hashing with ring partition and invariant vector distance, IEEE Trans. Inf. Foren. Secur., 11(2016), 200–214.
[17]	R. K. Karsh, R. H. Laskar and B. B. Richhariya, Robust image hashing using ring partition-PGNMF and local features, SpringerPlus, 5(2016), 1–20.
[18]	R. K. Karsh, R. H. Laskar and Aditi, Robust image hashing through DWT-SVD and spectral residual method, EURASIP J. Image Vide., 2017(2017), 1–17.
[19]	R. Davarzani, S. Mozaffariand and K. Yaghmaie, Perceptual image hashing using center-symmetric local binary patterns, Multimed. Tools Appl., 75(2016), 4639–4667.
[20]	X. Huang, X. Liu, G. Wang, et al., A robust image hashing with enhanced randomness by using random walk on zigzag blocking, In: Proc. IEEE Trustcom/BigDataSE/ISPA, pp.23–26, 2016.
[21]	R. K. Karsh, A. Saikia and R. H. Laskar, Image authentication based on robust image hashing with geometric correction, Multimed. Tools Appl., 77(2018), 25409–25429.
[22]	C. Qin, M. Sun and C.-C. Chang, Perceptual hashing for color images based on hybrid extraction of structural features, Signal Process., 142(2018), 194–205.
[23]	Z. Tang, Z. Huang, H. Yao, et al., Perceptual image hashing with weighted DWT features for reduced-reference image quality assessment, Comput. J., 61 (2018), 1695–1709.
[24]	L. Itti, C. Koch and E. Niebur, A model of saliency based visual attention for rapid scene analysis, IEEE Trans. Patt. Anal. Mac. Intell., 20(1998), 1254–1259.
[25]	D. Walther and C. Koch, Modeling attention to salient proto-objects, Neural Networks, 19(2006), 1395–1407.
[26]	X. Hou and L. Zhang, Saliency detection: A spectral residual approach, In: Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.1–8, 2007.
[27]	C. Guo, Q. Ma and L. Zhang, Spatio-temporal saliency detection using phase spectrum of quaternion Fourier transform, In: Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.1–8, 2008.
[28]	Z. Tang, X. Q. Zhang and S. Zhang, Robust perceptual image hashing based on ring partition and NMF, IEEE Trans. Knowl. Data En., 26(2014), 711–724.
[29]	Z. Tang, L. Huang, X. Q. Zhang, et al., Robust image hashing based on color vector angle and canny operator, AEÜ-Int. J. Electron. Commun., 70(2016), 833–841.
[30]	Kodak Lossless True Color Image Suite. Available online: http://r0k.us/graphics/kodak/.
[31]	F. A. P. Petitcolas, Watermarking schemes evaluation, IEEE Signal Process. Mag., 17(2000), 58–64.
[32]	Z. Wang, A. C. Bovik, H. R. Sheikh, et al., Image quality assessment: from error visibility to structural similarity, IEEE Trans. Image Process., 13(2004), 600–612.
[33]	Ground Truth Database. Available online: http://www.cs.washington.edu/research/imagedatabase/groundtruth/.
[34]	T. Fawcett, An introduction to ROC analysis, Patt. Recog. Lett., 27(2006), 861–874.
[35]	IEEE Std754–2008, IEEE Standard for Floating-Point Arithmetic, pp.1–70, 2008.
[36]	G. Schaefer and M. Stich, UCID-an uncompressed color image database, Proc. SPIE, Storage and Retrieval Methods and Applications for Multimedia, pp.472–480, 2004.

Reader Comments

Your name:*

Email:*
© 2019 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)