Data-Driven Feature Characterization Techniques for Laser Printer Attribution

Laser printer attribution is an increasing problem with several applications, such as pointing out the ownership of crime proofs and authentication of printed documents. However, as commonly proposed methods for this task are based on custom-tailored features, they are limited by modeling assumptions about printing artifacts. In this paper, we explore solutions able to learn discriminant-printing patterns directly from the available data during an investigation, without any further feature engineering, proposing the first approach based on deep learning to laser printer attribution. This allows us to avoid any prior assumption about printing artifacts that characterize each printer, thus highlighting almost invisible and difficult printer footprints generated during the printing process. The proposed approach merges, in a synergistic fashion, convolutional neural networks (CNNs) applied on multiple representations of multiple data. Multiple representations, generated through different pre-processing operations, enable the use of the small and lightweight CNNs whilst the use of multiple data enable the use of aggregation procedures to better determine the provenance of a document. Experimental results show that the proposed method is robust to noisy data and outperforms existing counterparts in the literature for this problem.

[1]  Alexei A. Efros,et al.  Fast bilateral filtering for the display of high-dynamic-range images , 2002 .

[2]  Rafael C. González,et al.  Local Determination of a Moving Contrast Edge , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Jan P. Allebach,et al.  Printer and Scanner Forensics: Models and Methods , 2010, Intelligent Multimedia Analysis for Security Applications.

[4]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[5]  Jian Sun,et al.  Guided Image Filtering , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Shize Shang,et al.  A printer forensics method using halftone dot arrangement model , 2015, 2015 IEEE China Summit and International Conference on Signal and Information Processing (ChinaSIP).

[7]  Matti Pietikäinen,et al.  A comparative study of texture measures with classification based on featured distributions , 1996, Pattern Recognit..

[8]  Heung-Kyu Lee,et al.  Electrophotographic printer identification by halftone texture analysis , 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

[9]  Min-Jen Tsai,et al.  Digital forensics of printed source identification for Chinese characters , 2013, Multimedia Tools and Applications.

[10]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  Min-Jen Tsai,et al.  Source color laser printer identification using discrete wavelet transform and feature selection algorithms , 2011, 2011 IEEE International Symposium of Circuits and Systems (ISCAS).

[12]  André Braz,et al.  Raman spectroscopy for forensic analysis of inks in questioned documents. , 2013, Forensic science international.

[13]  Jan P. Allebach,et al.  Printer Forensics Using SVM Techniques , 2005, NIP & Digital Fabrication Conference.

[14]  William Puech,et al.  Two-Level QR Code for Private Message Sharing and Document Authentication , 2016, IEEE Transactions on Information Forensics and Security.

[15]  Z. Jane Wang,et al.  Median Filtering Forensics Based on Convolutional Neural Networks , 2015, IEEE Signal Processing Letters.

[16]  Hae-Yeoun Lee,et al.  Identifying Color Laser Printer Using Noisy Feature and Support Vector Machine , 2010, 2010 Proceedings of the 5th International Conference on Ubiquitous Information Technologies and Applications.

[17]  Norbert Wiener,et al.  Extrapolation, Interpolation, and Smoothing of Stationary Time Series , 1964 .

[18]  Steven J. Simske,et al.  Printer-scanner identification via analysis of structured security deterrents , 2009, 2009 First IEEE International Workshop on Information Forensics and Security (WIFS).

[19]  Jan P. Allebach,et al.  Survey of Scanner and Printer Forensics at Purdue University , 2008, IWCF.

[20]  Anderson Rocha,et al.  Laser printer attribution: exploring new features and beyond. , 2015, Forensic science international.

[21]  Thomas G. Dietterich Approximate Statistical Tests for Comparing Supervised Classification Learning Algorithms , 1998, Neural Computation.

[22]  Heung-Kyu Lee,et al.  Colour laser printer identification using halftone texture fingerprint , 2015 .

[23]  Jan P. Allebach,et al.  Intrinsic and Extrinsic Signatures for Information Hiding and Secure Printing with Electrophotographic Devices , 2003, NIP & Digital Fabrication Conference.

[24]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[25]  N. Otsu A threshold selection method from gray level histograms , 1979 .

[26]  Po-Chun Chu,et al.  Forensic analysis of laser printed ink by X-ray fluorescence and laser-excited plume fluorescence. , 2013, Analytical chemistry.

[27]  Hany Farid,et al.  Printer profiling for forensics and ballistics , 2008, MM&Sec '08.

[28]  Yubao Wu,et al.  Printer forensics based on page document's geometric distortion , 2009, 2009 16th IEEE International Conference on Image Processing (ICIP).

[29]  Heung-Kyu Lee,et al.  Color laser printer identification using photographed halftone images , 2014, 2014 22nd European Signal Processing Conference (EUSIPCO).

[30]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[31]  Jan P. Allebach,et al.  Application of Principal Components Analysis and Gaussian Mixture Models to Printer Identification , 2004, NIP & Digital Fabrication Conference.

[32]  Anderson Rocha,et al.  Multiclass From Binary: Expanding One-Versus-All, One-Versus-One and ECOC-Based Approaches , 2014, IEEE Transactions on Neural Networks and Learning Systems.

[33]  Edward J. Delp,et al.  Forensic printer detection using intrinsic signatures , 2011, Electronic Imaging.

[34]  Min-Jen Tsai,et al.  Japanese character based printed source identification , 2015, 2015 IEEE International Symposium on Circuits and Systems (ISCAS).

[35]  Heung-Kyu Lee,et al.  Color laser printer identification by analyzing statistical features on discrete wavelet transform , 2009, 2009 16th IEEE International Conference on Image Processing (ICIP).

[36]  Jan P. Allebach,et al.  Printer identification based on texture features , 2004 .

[37]  Faisal Shafait,et al.  Printer Identification Using Supervised Learning for Document Forgery Detection , 2014, 2014 11th IAPR International Workshop on Document Analysis Systems.

[38]  Jan P. Allebach,et al.  Scanner identification with extension to forgery detection , 2008, Electronic Imaging.

[39]  Hae-Yeoun Lee,et al.  Color laser printer forensics with noise texture analysis , 2010, MM&Sec '10.

[40]  Marco Schreyer,et al.  Intelligent Printing Technique Recognition and Photocopy Detection for Forensic Document Examination , 2009, Informatiktage.

[41]  Jan P. Allebach,et al.  Printer identification based on graylevel co-occurrence features for security and forensic applications , 2005, IS&T/SPIE Electronic Imaging.

[42]  Yun Q. Shi,et al.  A Novel Multi-size Block Benford's Law Scheme for Printer Identification , 2010, PCM.

[43]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[44]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[45]  Min-Jen Tsai,et al.  Digital forensics for printed source identification , 2013, 2013 IEEE International Symposium on Circuits and Systems (ISCAS2013).

[46]  Orhan Bulan,et al.  Geometric distortion signatures for printer identification , 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.