Abstract
The photo-response non-uniformity (PRNU) noise of imaging sensor can be used as the fingerprint for identifying individual imaging device uniquely. As the first step of PRNU fingerprint extraction, estimating the natural noise from real-world images is rather important for source camera identification based on PRNU. The performance of most existing noise estimation schemes, which adapt to the additive white Gaussian noise (AWGN), degrade sharply for natural noise. In this paper, we present a new and effective PRNU extraction algorithm based on Densely-connected Hierarchical Denoising Network (DHDN) for source camera identification. Specifically, DHDN network is trained for dealing with different noise levels with one specific set of trained parameters. In addition, dense connectivity and residual learning are introduced to repeatedly utilize the antecedent feature maps as input and effectively solve the vanishing gradient problem for network training. Furthermore, the network can fully dig up the real-world image noise, and more PRNU related components remain in the extracted noise. By evaluating on the open digital camera and smartphone image databases, i.e., Dresden camera dataset and Daxing smartphone dataset, the proposed PRNU extraction algorithm outperforms other classical algorithms.
Similar content being viewed by others
References
Al-Ani M, Khelifi F (2016) On the spn estimation in image forensics: a systematic empirical evaluation. IEEE Trans Inform Forens Secur 12(5):1067–1081
Buades A, Coll B, Morel JM (2005) A non-local algorithm for image denoising. In: 2005 IEEE Computer society conference on computer vision and pattern recognition (CVPR’05), vol 2, pp 60–65. IEEE
Burger HC, Schuler CJ, Harmeling S (2012) Image denoising: can plain neural networks compete with bm3d? In: 2012 IEEE conference on computer vision and pattern recognition, pp 2392–2399. IEEE
Carletta J (1996) Assessing agreement on classification tasks: the kapp.a statistic. arXiv:cmp-lg/9602004
Chen M, Fridrich J, Goljan M, Lukás J (2008) Determining image origin and integrity using sensor noise. IEEE Trans Inform Forens Secur 3(1):74–90
Cooper AJ (2013) Improved photo response non-uniformity (prnu) based source camera identification. Forens Sci Int 226(1–3):132–141
Cortiana A, Conotter V, Boato G, De Natale FG (2011) Performance comparison of denoising filters for source camera identification. In: Media watermarking, security, and forensics III, international society for optics and photonics, vol 7880, p 788007
Corum CA, Connolly KM, Bawolek EJ (2000) Dark frame subtraction. US Patent 6,101:287
Dabov K, Foi A, Katkovnik V, Egiazarian K (2007) Image denoising by sparse 3-d transform-domain collaborative filtering. IEEE Trans Image Process 16(8):2080–2095
Elad M, Aharon M (2006) Image denoising via sparse and redundant representations over learned dictionaries. IEEE Trans Image process 15 (12):3736–3745
Excoffier L, Slatkin M (1995) Maximum-likelihood estimation of molecular haplotype frequencies in a diploid population. Molecul Biol Evol 12 (5):921–927
Filler T, Fridrich J, Goljan M (2008) Using sensor pattern noise for camera model identification. In: 2008 15th IEEE international conference on image processing, pp 126–1299. IEEE
Gloe T (2012) Feature-based forensic camera model identification. In: Transactions on data hiding and multimedia security VIII, pp 42–62. Springer
Gloe T, Böhme R (2010) The’dresden image database’for benchmarking digital image forensics. In: Proceedings of the 2010 ACM symposium on applied computing, pp 1584–1590
Goljan M, Fridrich J, Filler T (2009) Large scale test of sensor fingerprint camera identification. In: Media forensics and security, international society for optics and photonics, vol 7254, p 72540I
He K, Zhang X, Ren S, Sun J (2015) Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: Proceedings of the IEEE international conference on computer vision, pp 1026–1034
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778
Hochreiter S (1998) The vanishing gradient problem during learning recurrent neural nets and problem solutions. Int J Uncertain Fuzz Knowl-Based Syst 6 (02):107–116
Holst G (1998) CCD arrays cameras and displays, 2nd edn. SPIE Press
Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4700–4708
Janesick JR (2001) Scientific charge-coupled devices, vol 83. SPIE Press
Jiang X, Wei S, Zhao R, Zhao Y, Du X, DU G (2019) Survey of imaging device source identification. J Bjing Jiaotong Univ 43(2):48–57
Kang X, Chen J, Lin K, Anjie P (2014) A context-adaptive spn predictor for trustworthy source camera identification. EURASIP J Image Vid Process 2014(1):1–11
Kang X, Li Y, Qu Z, Huang J (2011) Enhancing source camera identification performance with a camera reference phase sensor pattern noise. IEEE Trans Inform Forens Secur 7(2):393–402
Kay SM (1993) Fundamentals of statistical signal processing. Prentice Hall PTR
Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv:14126980
Kligvasser I, Shaham TR, Michaeli T (2018) xunit: learning a spatial activation function for efficient image restoration. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2433–2442
Lefkimmiatis S (2018) Universal denoising networks: a novel cnn architecture for image denoising. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3204–3213
Levin A, Nadler B (2011) Natural image denoising: optimality and inherent bounds. In: CVPR 2011, pp 2833–2840. IEEE
Li XW, Sun K, Li LD (2014) Accelerated tracing scheme for gaussian fingerprinting. J Inf Hiding Multim Signal Process 5(3):379–390
Liu P, Zhang H, Zhang K, Lin L, Zuo W (2018) Multi-level wavelet-cnn for image restoration. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp 773–782
Long M, Peng F, Zhu Y (2019) Identifying natural images and computer generated graphics based on binary similarity measures of prnu. Multimed Tools Applic 78(1):489–506
Lukas J, Fridrich J, Goljan M (2006) Digital camera identification from sensor pattern noise. IEEE Trans Inform Forens Secur 1(2):205–214
Mastriani M, Giraldez AE (2007) Microarrays denoising via smoothing of coefficients in wavelet domain. Int J Electron Commun Eng 1(2):386–393
Mihcak MK, Kozintsev I, Ramchandran K, Moulin P (1999) Low-complexity image denoising based on statistical modeling of wavelet coefficients. IEEE Signal Process Lett 6(12):300–303
Park B, Yu S, Jeong J (2019) Densely connected hierarchical network for image denoising. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition workshops, pp 1–10
Ronneberger O, Fischer P, Brox T (2015) U-net: convolutional networks for biomedical image segmentation. In: International conference on medical image computing and computer-assisted intervention, pp 234–241. Springer
Shi W, Caballero J, Huszár F, Totz J, Aitken AP, Bishop R, Rueckert D, Wang Z (2016) Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1874–1883
Tian H, Xiao Y, Cao G, Zhang Y, Xu Z, Zhao Y (2019) Daxing smartphone identification dataset. IEEE Access 7:101046–101053
Yang P, Baracchi D, Ni R, Zhao Y, Argenti F, Piva A (2020) A survey of deep learning-based source image forensics. J Imaging 6(3):9
Yang WC, Jiang J, Chen CH (2020) A fast source camera identification and verification method based on prnu analysis for use in video forensic investigations. Multimedia Tools and Applications, 1–22
Zeng H, Kang X (2016) Fast source camera identification using content adaptive guided image filter. J Forens Sci 61(2):520–526
Zhang K, Zuo W, Chen Y, Meng D, Zhang L (2017) Beyond a gaussian denoiser: residual learning of deep cnn for image denoising. IEEE Trans Image Process 26(7):3142–3155
Zhang K, Zuo W, Zhang L (2018) Ffdnet: toward a fast and flexible solution for cnn-based image denoising. IEEE Trans Image Process 27(9):4608–4622
Zhao H, Gallo O, Frosio I, Kautz J (2016) Loss functions for image restoration with neural networks. IEEE Trans Comput Imag 3(1):47–57
Zhao Y, Zheng N, Qiao T, Xu M (2019) Source camera identification via low dimensional prnu features. Multimed Tools Applic 78(7):8247–8269
Acknowledgements
This work was supported in part by the National Natural Science Foundation of China (Grant No. 61972405, 61772539, 62071434), the Fundamental Research Funds for the Central Universities (Grant No. CUC21GZ010). Thanks Yunfei Hao, Xinze Hao, Yuxin Mao et al. for their hard work during the process of data collection and collation.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of Interests
The authors declare that they have no conflict of interest.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Xiao, Y., Tian, H., Cao, G. et al. Effective PRNU extraction via densely connected hierarchical network. Multimed Tools Appl 81, 20443–20463 (2022). https://doi.org/10.1007/s11042-022-12507-w
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-022-12507-w