Abstract
Source printer identification for printed documents has been studied extensively in recent years. Applying machine learning to features extracted from the artifacts of the printed papers is a potential approach in this field. Due to the fact that extracting features is a manual task that requires domain knowledge from the expert, which is one of the most resource-intensive tasks, In this work, we aim to reduce the number of training features on many different machine learning models but guarantee the high performance of the identifying results. Following the work of the authors from [1], our proposed features selection methods show that we can achieve about the same accuracy while significantly reduced the number of features.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Nguyen, Q.T., Mai, A., Chagas, L., Reverdy-Bruas, N.: Microscopic printing analysis and application for classification of source printer. Comput. Secur. 108, 102320 (2021). https://doi.org/10.1016/j.cose.2021.102320
International Data Corporation. (2021, August 3) IDC Forecasts Worldwide Page Volumes to Rebound In 2021, But Will Not Reach Pre-COVID-19 Levels. https://www.idc.com/getdoc.jsp?containerId=prUS48126321
Chiang, P.J., et al.: Printer and scanner forensics. IEEE Signal Process. Mag. 26(2), 72–83 (2009)
Ferreira, A., Navarro, L.C., Pinheiro, G., dos Santos, J.A., Rocha, A.: Laser printer attribution: exploring new features and beyond. Forensic Sci. Int. 247, 105–125 (2015)
Khanna, N., Delp, E.J.: Intrinsic signatures for scanned documents forensics: effect of font shape and size. In: Proceedings of 2010 IEEE International Symposium on Circuits and Systems, pp. 3060–3063. IEEE (May 2010)
Chiang, P.J., Allebach, J.P., Chiu, G.T.C.: Extrinsic signature embedding and detection in electrophotographic halftoned images through exposure modulation. IEEE Trans. Inf. Forensics Secur. 6(3), 946–959 (2011)
Chiang, P.J., et al.: Printer and scanner forensics: models and methods. In: Sencar, H.T., Velastin, S., Nikolaidis, N., Lian, S. (eds.) Intelligent Multimedia Analysis for Security Applications. Studies in Computational Intelligence, vol. 282, pp. 145–187. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-11756-5_7
Shang, S., Kong, X.: Printer and Scanner Forensics. In: Anthony, T.S., Ho, S.L. (eds.) Handbook of Digital Forensics of Multimedia Data and Devices, pp. 375–410. Wiley, Chichester (2015)
Hao, J., Kong, X., Shang, S.: Printer identification using page geometric distortion on text lines. In: 2015 IEEE China Summit and International Conference on Signal and Information Processing (ChinaSIP), pp. 856–860. IEEE (July 2015)
Bulan, O., Mao, J., Sharma, G.: Geometric distortion signatures for printer identification. In: 2009 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 1401–1404. IEEE (April 2009)
Escher, S., Strafe, T.: Robustness analysis of a passive printer identification scheme for halftone images. In: 2017 IEEE International Conference on Image Processing (ICIP), pp. 4357–4361. IEEE (September 2017)
Mikkilineni, A.K., Chiang, P.J., Ali, G.N., Chiu, G.T., Allebach, J.P., Delp III, E.J.: Printer identification based on graylevel co-occurrence features for security and forensic applications. In: Security, Steganography, and Watermarking of Multimedia Contents VII, vol. 5681, pp. 430–440. International Society for Optics and Photonics (March 2005)
Mikkilineni, A.K., Khanna, N., Delp, E.J.: Forensic printer detection using intrinsic signatures. In: Media Watermarking, Security, and Forensics III, vol. 7880, p. 78800R. International Society for Optics and Photonics (February 2011)
Tsai, M. J., Yuadi, I.: Printed source identification by microscopic images. In: 2016 IEEE International Conference on Image Processing (ICIP), pp. 3927–3931. IEEE (September 2016)
Olson, E.: Particle shape factors and their use in image analysis part 1: theory. J. GXP Compliance 15(3), 85 (2011)
Acknowledgements
We would like to thank Dr. Quoc Thong Nguyen at Université Bretagne Sud for his contribution on the data. This paper is supported by a project with the International University, Ho Chi Minh City, Vietnam (contract No. T2020–04-IT/HĐ-ĐHQT-QLKH, dated 01/02/2021).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Nguyen, Q.P., Dang, N.T., Mai, A., Nguyen, V.S. (2021). Features Selection in Microscopic Printing Analysis for Source Printer Identification with Machine Learning. In: Dang, T.K., Küng, J., Chung, T.M., Takizawa, M. (eds) Future Data and Security Engineering. Big Data, Security and Privacy, Smart City and Industry 4.0 Applications. FDSE 2021. Communications in Computer and Information Science, vol 1500. Springer, Singapore. https://doi.org/10.1007/978-981-16-8062-5_14
Download citation
DOI: https://doi.org/10.1007/978-981-16-8062-5_14
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-8061-8
Online ISBN: 978-981-16-8062-5
eBook Packages: Computer ScienceComputer Science (R0)