Data-Driven Feature Characterization Techniques for Laser Printer Attribution

• Published in: IEEE transactions on information forensics and security Vol. 12; no. 8; pp. 1860 - 1873
• Main Authors: Ferreira, Anselmo, Bondi, Luca, Baroffio, Luca, Bestagini, Paolo, Jiwu Huang, dos Santos, Jefersson A., Tubaro, Stefano, Rocha, Anderson
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.08.2017; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial neural networks; convolutional neural networks; Crime; deep learning-based document provenance analysis; Feature extraction; Image color analysis; Laser applications; Laser printer attribution; Laser printers; Machine learning; multiple data; multiple representation; Neural networks; Printers; Printing; Representations; Training

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 assumption...