Scanner Model Identification of Official Documents Using Noise Parameters Estimation in the Wavelet Domain
In this article, we propose a novel approach for discerning which scanner has been used to scan a particular document. Its originality relates to a signature extracted in the wavelet domain of the digitized documents where the acquisition noise specific to a scanner is located in the first subbands of details. This signature is an estimate of the statistical noise model which is modeled by a General Gaussian distribution (GGD) and whose parameters are estimated in the HH subband by maximizing the likelihood function. These parameters constitute a unique identifier for a scanner. For a given image, we propose to identify its origin by minimizing the Kullback-Leibler divergence between its signature and those of known scanners. Experiments conducted on a real scanned-image database, developed for the validation of the work presented in this paper, show that the proposed approach achieves high detection performance. Total of 1000 images were used in experiments.
KeywordsDigitized documents Scanner identification Image forensics Authenticity Wavelet transform
This work was financially supported by the “PHC Utique” program of the French Ministry of Foreign Affairs and Ministry of higher education and research and the Tunisian Ministry of higher education and scientific research in the CMCU project number 17G1405.
- 1.de Laubier, C.: La difficile quête du zéro papier. http://www.lemonde.fr/economie/article/2017/09/03/la-difficile-quete-du-zero-papier_5180409_3234.html
- 2.Ferguson, N., Schneier, B., Kohno, T.: Cryptography Engineering: Design Principles and Practical Applications. Wiley, Hoboken (2011)Google Scholar
- 5.Gloe, T., Franz, E., Winkler, A.: Forensics for flatbed scanners, in security, steganography, and watermarking of multimedia contents IX. Int. Soc. Opt. Photonics 6505, 65051I (2007)Google Scholar
- 6.Gou, H., Swaminathan, A., Min, W.: Robust scanner identification based on noise features. In: Security, Steganography, and Watermarking of Multimedia Contents IX. International Society for Optics and Photonics, vol. 6505, p. 65050S (2007)Google Scholar
- 9.Khanna, N., Mikkilineni, A.K., Chiu, G.T.C., Allebach, J.P., Delp, E.J.: Scanner identification using sensor pattern noise. In: Security, Steganography, and Watermarking of Multimedia Contents IX. International Society for Optics and Photonics, vol. 6505, p. 65051K (2007)Google Scholar
- 10.Khanna, N., Delp, E.J.: Source scanner identification for scanned documents. In: First IEEE International Workshop on Information Forensics and Security, WIFS 2009, pp. 166–170. IEEE (2009)Google Scholar
- 11.Joshi, S., Gupta, G., Khanna, N.: Source classification using document images from smartphones and flatbed scanners. In: Rameshan, R., Arora, C., Dutta Roy, S. (eds.) NCVPRIPG 2017. CCIS, vol. 841, pp. 281–292. Springer, Singapore (2018). https://doi.org/10.1007/978-981-13-0020-2_25CrossRefGoogle Scholar
- 12.Dirik, A.E., Sencar, H.T., Memon, N.: Flatbed scanner identification based on dust and scratches over scanner platen. In: IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2009, pp. 1385–1388. IEEE (2009)Google Scholar
- 13.Elsharkawy, Z.F., Abdelwahab, S.A., Dessouky, M.I., Elaraby, S.M., Abd El-Samie, F.E.: Identifying unique flatbed scanner characteristics for matching a scanned image to its source. Digit. Image Process. 5(9), 397–403 (2013)Google Scholar
- 15.Choi, C.-H., Lee, M.-J., Lee, H.-K.: Scanner identification using spectral noise in the frequency domain. In: 2010 17th IEEE International Conference on Image Processing (ICIP), pp. 2121–2124. IEEE (2010)Google Scholar
- 18.Daubechies, I.: Ten Lectures on Wavelets, vol. 61. SIAM (1992)Google Scholar
- 22.Cochran, M.: A proposed standard procedure to define minimum scanning attribute levels for hard copy documents. In: 2014 47th Hawaii International Conference on System Sciences (HICSS), pp. 2036–2043. IEEE (2014)Google Scholar