Abstract
Sensor Pattern Noise (SPN) has proven to be an effective fingerprint for source camera identification. However, its estimation accuracy is still greatly affected by image contents. In this work, considering the confidence difference in varying image regions, an image edge guided weighted averaging scheme for robust SPN estimation is proposed. Firstly, the edge and non-edge regions are estimated by a Laplacian operator-based detector, based on which different weights are assigned to. Then, the improved SPN estimation is obtained by weighted averaging of image residuals. Finally, an edge guided weighted normalized cross-correlation measurement is proposed as similarity metric in source camera identification (SCI) applications. The effectiveness of the proposed method is verified by SCI experiments conducted on six models from the Dresden data set. Comparison results on different denoising algorithms and varying patch sizes reveal that performance improvement is more prominent for small image patches, which is demanding in real forensic applications.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Popescu, A.C., Farid, H.: Exposing digital forgeries by detecting traces of resampling. IEEE Trans. Sig. Process. 53(2), 758–767 (2005)
Popescu, A.C., Farid, H.: Exposing digital forgeries in color filter array interpolated images. IEEE Trans. Sig. Process. 53(10), 3948–3959 (2005)
Lin, Z., Wang, R., Tang, X., Shum, H.Y.: Detecting doctored images using camera response normality and consistency (2009)
Lukas, J., Fridrich, J., Goljan, M.: Digital camera identification from sensor pattern noise. IEEE Trans. Inf. Forensics Secur. 1(2), 205–214 (2006)
Chen, M., Fridrich, J., Goljan, M., Lukas, J.: Determining image origin and integrity using sensor noise. IEEE Trans. Inf. Forensics Secur. 3(1), 74–90 (2008)
Lukas, J., Fridrich, J., Goljan, M.: Detecting digital image forgeries using sensor pattern noise 6072 (2006)
Li, C.: Source camera identification using enhanced sensor pattern noise. IEEE Trans. Inf. Forensics Secur. 5(2), 280–287 (2010)
Wu, G., Kang, X., Liu, K.J.R.: A context adaptive predictor of sensor pattern noise for camera source identification. In: 2012 19th IEEE International Conference on Image Processing (ICIP) (2012)
Kang, X., Chen, J., Lin, K., Anjie, P.: A context-adaptive spn predictor for trustworthy source camera identification. Eurasip J. Image Video Process. 2014(1), 19 (2014)
Zeng, H., Kang, X.: Fast source camera identification using content adaptive guided image filter. J. Forensic Sci. 61(2), 520–526 (2016)
Zhang, L., Peng, F., Long, M.: Identifying source camera using guided image estimation and block weighted average. J. Vis. Commun. Image Represent. 48, 471–479 (2017)
Zhang, W., Liu, Y., Zou, Z., Zang, Y., Yang, Y., Law, B.N.: Effective source camera identification based on msepll denoising applied to small image patches (2019)
Cortiana, A., Conotter, V., Boato, G., De Natale, F.G.B.: Performance comparison of denoising filters for source camera identification. Proc. SPIE 7880, 788007 (2011)
Lin, X., Li, C.: Preprocessing reference sensor pattern noise via spectrum equalization. IEEE Trans. Inf. Forensics Secur. 11(1), 126–140 (2016)
Lawgaly, A., Khelifi, F., Bouridane, A.: Weighted averaging-based sensor pattern noise estimation for source camera identification, pp. 5357–5361 (2014)
Mihcak, M.K., Kozintsev, I.V., Ramchandran, K.: Spatially adaptive statistical modeling of wavelet image coefficients and its application to denoising 6, 3253–3256 (1999)
Dabov, K., Foi, A., Katkovnik, V., Egiazarian, K.: Image denoising by sparse 3-d transform-domain collaborative filtering. IEEE Trans. Image Process. 16(8), 2080–2095 (2007)
Wang, X.: Laplacian operator-based edge detectors. IEEE Trans. Pattern Anal. Mach. Intell. 29(5), 886–890 (2007)
Matsushita, K., Kitazawa, H.: An improved camera identification method based on the texture complexity and the image restoration. In: International Conference on Hybrid Information Technology, pp. 171–175 (2009)
Chan, L., Law, N., Siu, W.: A confidence map and pixel-based weighted correlation for prnu-based camera identification. Digital Invest. 10(3), 215–225 (2013)
Satta, R.: Sensor pattern noise matching based on reliability map for source camera identification, pp. 222–226 (2015)
Gloe, T., Bohme, R.: The ‘dresden image database’ for benchmarking digital image forensics, pp. 1584–1590 (2010)
Acknowledgments
This work was supported by National Key Research and Development Program (No. 2018YFC0831100), the National Nature Science Foundation of China (No. 61305015, No. 61203269), the National Natural Science Foundation of Shandong Province (No. ZR2017MF057), and Shandong Province Key Research and Development Program, China (No. 2016GGX101022).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Zhang, WN., Liu, YX., Zhou, J., Yang, Y., Law, NF. (2020). An Improved Sensor Pattern Noise Estimation Method Based on Edge Guided Weighted Averaging. In: Chen, X., Yan, H., Yan, Q., Zhang, X. (eds) Machine Learning for Cyber Security. ML4CS 2020. Lecture Notes in Computer Science(), vol 12487. Springer, Cham. https://doi.org/10.1007/978-3-030-62460-6_36
Download citation
DOI: https://doi.org/10.1007/978-3-030-62460-6_36
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-62459-0
Online ISBN: 978-3-030-62460-6
eBook Packages: Computer ScienceComputer Science (R0)