Abstract
This study presents a method for resampling detection. By combining texture analysis with resampling detection, the task of resampling detection is considered as a texture classification problem. In other words, the influence of resampling operations on a raw single-sampled image is viewed as an alteration of the image texture in a fine scale. First, local linear transform is used to obtain textural detail sub-bands. A 36-D feature vector is then extracted from the normalized characteristic function moments of textural detail sub-bands to train a support vector machine classifier. Finally, experimental results are reported on three databases, with each having almost 10,000 images. Comparison with the previous study reveals that the proposed method is effective for resampling detection. In addition, extensive experiments on cover and stego bitmap images illustrate that the proposed method is essential for constructing accurate targeted and blind steganalysis methods for heterogeneous images, raw single-sampled images, and images resampled at different scales.
Similar content being viewed by others
Abbreviations
- BMP:
-
Bitmap
- LLT:
-
Local linear transform
- CF:
-
Characteristic function
- 1-D:
-
One dimensional
- EM:
-
Expectation/maximization
- SOD:
-
Second-order derivative
- SVM:
-
Support vector machine
- DFT:
-
Discrete Fourier transform
- DCT:
-
Discrete cosine transform
- PDF:
-
Probability density function
- LSB:
-
Least significant bit
- MB1:
-
Model-based
- AC:
-
Alternating current
- bpnc:
-
Bit per non-zero AC DCT coefficient
References
Chang CC, Lin CJ. LIBSVM: a library for support vector machines [EB/OL]. http://www.csie.ntu.edu.tw/~cjlin/libsvm. Accessed 11 May 2011
Doёrr G Image database for steganalysis studies [Online]. http://www.cs.ucl.ac.uk/staff/I.Cox/Content/Downloads.html. Accessed 11 May 2011
Farid H (2009) Image forgery detection. IEEE Signal Process Mag 26(2):16–25. doi:10.1109/MSP.2008.931079
Feng XY, Cox IJ, Doërr G (2012) Normalized energy density-based forensic detection of resampled images. IEEE Trans Multimed 14(3):536–545. doi:10.1109/TMM.2012.2191946
Fridrich J (2004) Feature-based steganalysis for JPEG images and its implications for future design of steganographic schemes. In: Proc. 6th Information Hiding Workshop, Springer LNCS, 3200:67–81. doi:10.1007/978-3-540-30114-1_6
Gallagher AC (2005) Detection of linear and cubic interpolation in JPEG compressed images. In: Proc. 2th Canadian Conf. on Computer and Robot Vision, Washington, DC, pp 65–72. doi:10.1109/CRV.2005.33
Harmsen JJ, Pearlman WA (2003) Steganalysis of additive noise modelable information hiding. In: Proc. SPIE, Security and watermarking of Multimedia Contents V, Santa Clara, CA, 5020:131–142
Kirchner M (2008) Fast and reliable resampling detection by spectral analysis of fixed linear predictor residue. In: Proc. 10th ACM Workshop on Multimedia and Security, New York, NY, USA, pp 11–20. doi:10.1145/1411328.1411333
Li B, Huang JW, Shi YQ (2008) Textural features based universal steganalysis. In: Proc. SPIE Security, Forensics, Steganography and Watermarking of Multimedia Contents X, 6819:1201–1212. doi:10.1117/12.765817
Li X, Zhang T, Zhang Y, Li WX, Li KD (2012) A novel blind detector for additive noise steganography in JPEG decompressed images. Multimed Tools Appl, published online. doi:10.1007/s11042-012-1112-2
Lyu S, Farid H (2006) Steganalysis using higher-order image statistics. IEEE Trans Inf Forensics Secur 1(1):111–119. doi:10.1109/TIFS.2005.863485
Mahdian B, Saic S (2008) Blind authentication using periodic properties of interpolation. IEEE Trans Inf Forensics Secur 3(3):529–538. doi:10.1109/TIFS.2004.924603
Ng I, Tan T, Kittler J (1992) On local linear transform and Gabor filter representation of texture. In: Proc. 11th Int. Conf. on Pattern Recognition, Hague, III:627–631
Popescu AC, Farid H (2004) Statistical tools for digital forensics. In: Proc. 6th Information Hiding Workshop, Springer LNCS, 3200:128–147. doi:10.1007/978-3-540-30114-1_10
Popescu AC, Farid H (2005) Exposing digital forgeries by detecting traces of re-sampling. IEEE Trans Signal Process 53(2):758–767. doi:10.1109/TSP.2004.839932(410) 53
Prasad S, Ramakrishnan KR (2006) On resampling detection and its application to image tampering. In Proc. of the IEEE Int. Conference on Multimedia and Expo, Toronto, Canada, pp 1325–1328. doi:10.1109/ICME.2006.262783
Sallee P (2004) Model-based steganography. In: Proc. IWDW, Springer LNCS, 2939:154–167. doi:10.1007/978-3-540-24624-4_12
Sharp T (2001) An implementation of key-based digital signal steganography. In: Proc. 4th Int. Workshop on Information Hiding, Springer LNCS, 2137:13–26. doi:10.1007/3-540-45496-9_2
Shi YQ, Xuan GR, Yang CY et al (2005) Effective steganalysis based on statistics moments of wavelet characteristic function. In: Proc. IEEE Int. Conference on Information Technology: Coding and Computing, 1:768–773. doi:10.1109/ITCC.2005.138
Siwei L, Farid H (2003) Detecting hidden message using higer-order statistics and support vector machines. In: Proc. 5th Information Hiding workshop, Springer LNCS, 2578:340–354. doi:10.1007/3-540-36415-3_22
Uccheddu F, De Rosa A, Piva A, Barni M (2010) Detection of resampled images: performance analysis and practical challenges. In: Proc. 18th European Signal Processing Conference, Aalborg, Denmark, pp 1675–1679
Unser M (1986) Local linear transforms for texture measurements. Signal Process 11(1):61–79. doi:10.1016/0165-1684(86)90095-2
Wang Y, Moulin P (2007) Optimized feature extraction for learning-based image steganalysis. IEEE Trans Inf Forensics Secur 2(1):31–45. doi:10.1109/TIFS.2006.890517
Xiong G, Ping XJ, Zhang T, Hou XD (2012) Image textural features for steganalysis of spatial domain steganography. J Electron Imaging 21(3):033015-1–033015-15. doi:10.1117/1.JEI.21.3.033015
Xuan GR, Shi YQ, Gao JJ et al (2005) Steganalysis based on multiple features formed by statistics moments of wavelet characteristic functions. In: Proc. 7th Information Hiding Workshop, Springer LNCS, 3727:262–277. doi:10.1007/11558859_20
Zheng EG, Ping XJ, Zhang T (2011) Local linear transform and new features of histogram characteristic functions for steganalysis of least significant bit matching steganography. KSII Trans Int Inform Syst 5(4):840–855. doi:10.3837/tiis.2011.04.012
Acknowledgments
This work was supported by the National Natural Science Foundation of China (No. 61272490 and 60903221). The authors would like to thank the reviewers for their insightful comments and helpful suggestions.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Hou, X., Zhang, T., Xiong, G. et al. Image resampling detection based on texture classification. Multimed Tools Appl 72, 1681–1708 (2014). https://doi.org/10.1007/s11042-013-1466-0
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-013-1466-0