Soft Computing

, Volume 22, Issue 6, pp 1981–1992 | Cite as

Spatial rich model steganalysis feature normalization on random feature-subsets

  • Pengfei Wang
  • Zhihui Wei
  • Liang Xiao
Methodologies and Application


Spatial rich model (SRM) steganalysis feature is formed by high-order statistics collected from image noise residuals. These statistics are simply rescaled before machine learning. It is noted that SRM features of different cover images are very different. In this paper, we propose a feature normalization method based on random feature-subsets (NRS) for SRM. We randomly draw feature-subsets from SRM feature. Then these feature-subsets are normalized by using per-sample rescaling method to make the feature-subsets of different images have the same 1-norm (the sum of all elements). The proposed NRS method can adjust the feature distribution and increase the feature diversity. The normalized feature-subsets can achieve better detection performance and also can be used as a useful complement for the existing steganalysis features. Experimental results show that: (1) a small amount of normalized feature-subset supplement can obviously improve the detection performance of SRM feature; (2) under the same dimensionality, the proposed NRS version feature can achieve a better detection accuracy than that of original feature; (3) the proposed NRS method is applicable to projections of spatial rich model feature; (4) compared with steganalysis feature extraction, the computational time of NRS can be negligible.


Steganalysis Co-occurrence Feature normalization Random feature-subsets 



The authors would like to thank the Network Center of Anhui University of Technology (AHUT) for providing cloud services to support this work. This study was funded by National Natural Science Foundation of China (Grant Nos. 61302178, 61105020), Foundation for Major Program of Education Bureau of Anhui Province (Grant No. KJ2015ZD09) and Excellent Youth Foundation of Anhui University of Technology (Grant No. z10097).

Compliance with ethical standards

Conflict of interest

All the authors and the Network Center of Anhui University of Technology declare that they have no conflict of interest.

Ethical approval

This article does not contain any studies with human participants or animals performed by any of the authors.


  1. Anthony TH, Li S (2015) Handbook of digital forensics of multimedia data and devices. IEEE Press, New YorkGoogle Scholar
  2. Arpit D, Zhou Y, Kota BU, Govindaraju V (2016) Normalization propagation: A parametric technique for removing internal covariate shift in deep networks. In: Proceedings of the 33 rd international conference on machine learning, vol 48. New York, NY, USAGoogle Scholar
  3. Bas P, Filler T, Pevný T (2011) Break our steganographic system—the ins and outs of organizing boss’. In: Filler T, Pevný T, Ker A, Craver S (eds) 13th international conference of information hiding, lecture notes in computer science, Prague, Czech Republic, vol 6958, pp 59–70Google Scholar
  4. Böhme R (2010) Advanced statistical steganalysis. Springer, BerlinCrossRefzbMATHGoogle Scholar
  5. Breiman L (1996) Bagging predictors. Mach Learn 24:123–140MathSciNetzbMATHGoogle Scholar
  6. Chen Y, Lai D, Qi H (2016a) A new method to estimate ages of facial image for large database. Multimed Tools Appl 75(5):2877–2895CrossRefGoogle Scholar
  7. Chen Y, Tang S, Zhou L, Wang C, Du J, Wang T, Pei S (2016) Decentralized clustering by finding loose and distributed density cores. Inf Sci. doi: 10.1016/j.ins.2016.08.009 Google Scholar
  8. Cogranne R, Sedighi V, Fridrich J, Pevn T (2015) Is ensemble classifier needed for steganalysis in high-dimensional feature spaces? In: IEEE international workshop on information forensics and security. Italy, Rome, pp 1–5Google Scholar
  9. Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20(3):273–297zbMATHGoogle Scholar
  10. Ester M, Kriegel H, Sander J, Xu X (1996) A density-based algorithm for discovering clusters in large spatial databases with noise. In: Simoudis E, Han J, Fayyad U (eds) Kdd, vol 96. AAAI Press, Menlo Park, CA, pp 226–231Google Scholar
  11. Filler T, Fridrich J (2010) Gibbs construction in steganography. IEEE Trans Inf Forensics Secur 5(4):705–720CrossRefGoogle Scholar
  12. Fridrich J, Kodovský J (2012) Rich models for steganalysis of digital images. IEEE Trans Inf Forensics Secur 7(3):868–882CrossRefGoogle Scholar
  13. Geng X, Yin C, Zhou Z (2013) Facial age estimation by learning from label distributions. IEEE Trans Pattern Anal Mach Intell 35(10):2401–2412CrossRefGoogle Scholar
  14. Goljan M, Fridrich J, Cogranne R (2014) Rich model for steganalysis of color images. In: IEEE workshop on information forensic and security. Atlanta, GAGoogle Scholar
  15. Gu B, Sun X, Sheng V (2016) Structural minimax probability machine. IEEE Trans Neural Netw Learn Syst. doi: 10.1109/TNNLS.2016.2544779 Google Scholar
  16. Holub V, Fridrich J (2012) Designing steganographic distortion using directional filters. In: Fourth IEEE international workshop on information forensics and security. Tenerife, Spain, pp 234–239Google Scholar
  17. Holub V, Fridrich J (2013a) Digital image steganography using universal distortion. In: Puech W, Chaumont M, Dittmann J, Campisi P (eds) Proceedings of the first ACM workshop on Information hiding and multimedia security. France, Montpellier, pp 59–68Google Scholar
  18. Holub V, Fridrich J (2013b) Random projections of residuals for digital image steganalysis. IEEE Trans Inf Forensics Secur 8(12):1996–2006CrossRefGoogle Scholar
  19. Holub V, Fridrich J (2015) Low complexity features for JPEG steganalysis using undecimated DCT. IEEE Trans Inf Forensics Secur 10(2):219–228CrossRefGoogle Scholar
  20. Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. In: 32nd international conference on machine learning (ICML 2015), vol 1, pp 448–456Google Scholar
  21. Kodovský J, Fridrich J, Holub V (2012) Ensemble classifiers for steganalysis of digital media. IEEE Trans Inf Forensics Secur 7(2):432–444CrossRefGoogle Scholar
  22. Kwon YH, Lobo NV (1999) Age classification from facial images. Comput Vis Image Underst 74(1):1–21CrossRefGoogle Scholar
  23. Lai D, Chen Y, Luo X, Du J, Wang T (2016) Age estimation with dynamic age range. Multimed Tools Appl. doi: 10.1007/s11042-015-3230-0 Google Scholar
  24. Li F, Zhang X, Chen B, Feng G (2013) JPEG steganalysis with high-dimensional features and Bayesian ensemble classifier. IEEE Signal Process Lett 20(3):233–236CrossRefGoogle Scholar
  25. Luo X, Song X, Li X, Zhang W, Lu J, Yang C, Liu F (2016) Steganalysis of hugo steganography based on parameter recognition of syndrome-trellis-codes. Multimed Tools Appl 75(13):13,557–13,583CrossRefGoogle Scholar
  26. Lyu S, Farid H (2002) Detecting hidden messages using higher order statistics and support vector machines. In: 5th international workshop on information hiding, Lecture notes in computer science, vol 2578, pp 340–354Google Scholar
  27. 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 CrossRefGoogle Scholar
  28. Maaløe L, Sønderby CK, Sønderby SK, Winther O (2016) Auxiliary deep generative models. In: Proceedings of the 33rd international conference on machine learning, vol 48. New York, NY, USAGoogle Scholar
  29. Mohammadi FG, Abadeh MS (2014) A new metaheuristic feature subset selection approach for image steganalysis. J Intell Fuzzy Syst 27(3):1445–1455Google Scholar
  30. Ng A, Ngiam J, Foo CY, Mai Y, Suen C (2013) Data preprocessing. Accessed 8 Dec 2015
  31. Pevný T, Bas P, Fridrich J (2010) Steganalysis by subtractive pixel adjacency matrix. IEEE Trans Inf Forensics Secur 5(2):215–224CrossRefGoogle Scholar
  32. Raschka S (2015) Feature scaling and normalization. Accessed 22 Feb 2016
  33. Rodriguez A, Laio A (2014) Clustering by fast search and find of density peaks. Science 344(6191):1492–1496CrossRefGoogle Scholar
  34. Sønderby CK, Raiko T, Maaløe L, Sønderby SK, Winther O (2016) Ladder variational autoencoders. In: NIPS 2016: annual conference on neural information processing systems. Barcelona, SpainGoogle Scholar
  35. Song X, Liu F, Yang C, Luo X, Zhang Y (2015) Steganalysis of adaptive JPEG steganography using 2D Gabor filters. In: ACM workshop on information hiding and multimedia security, pp 15–23Google Scholar
  36. Wang P, Wei Z, Xiao L (2016a) Fast projections of spatial rich model feature for digital image steganalysis. Soft Comput. doi: 10.1007/s00500-015-2011-z Google Scholar
  37. Wang P, Wei Z, Xiao L (2016b) Pure spatial rich model features for digital image steganalysis. Multimed Tools Appl 75(5):2897–2912CrossRefGoogle Scholar
  38. Wu A, Feng G, Zhang X, Ren Y (2016) Unbalanced JPEG image steganalysis via multiview data match. J Vis Commun Image Represent 34:103–107CrossRefGoogle Scholar
  39. Yu J, Zhang X, Li F (2016) Spatial steganalysis using redistributed residuals and diverse ensemble classifier. Multimed Tools Appl 75(21):13,613–13,625CrossRefGoogle Scholar
  40. Zhang Y, Luo X, Yang C, Liu F (2016) Joint jpeg compression and detection resistant performance enhancement for adaptive steganography using feature regions selection. Multimed Tools Appl. doi: 10.1007/s11042-016-3914-0 Google Scholar
  41. Zou D, Shi YQ, Su W, Xuan G (2006) Steganalysis based on markov model of thresholded prediction-error image. In: Proceedings of the IEEE international conference on multimedia and expo, Toronto, Canada, pp 1365–1368Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2016

Authors and Affiliations

  1. 1.School of Computer Science and EngineeringNanjing University of Science and TechnologyNanjingChina
  2. 2.School of Computer Science and TechnologyAnhui University of TechnologyMaanshanChina

Personalised recommendations