Back to articles
Volume: 30 | Article ID: art00011
Deep Learning for Detecting Processing History of Images
  DOI :  10.2352/ISSN.2470-1173.2018.07.MWSF-213  Published OnlineJanuary 2018

Establishing the pedigree of a digital image, such as the type of processing applied to it, is important for forensic analysts because processing generally affects the accuracy and applicability of other forensic tools used for, e.g., identifying the camera (brand) and/or inspecting the image integrity (detecting regions that were manipulated). Given the superiority of automatized tools called deep convolutional neural networks to learn complex yet compact image representations for numerous problems in steganalysis as well as in forensic, in this article we explore this approach for the task of detecting the processing history of images. Our goal is to build a scalable detector for practical situations when an image acquired by a camera is processed, downscaled with a wide variety of scaling factors, and again JPEG compressed since such processing pipeline is commonly applied for example when uploading images to social networks, such as Facebook. To allow the network to perform accurately on a wide range of image sizes, we investigate a novel CNN architecture with an IP layer accepting statistical moments of feature maps. The proposed methodology is benchmarked using confusion matrices for three JPEG quality factors.

Subject Areas :
Views 113
Downloads 30
 articleview.views 113
 articleview.downloads 30
  Cite this article 

Mehdi Boroumand, Jessica Fridrich, "Deep Learning for Detecting Processing History of Imagesin Proc. IS&T Int’l. Symp. on Electronic Imaging: Media Watermarking, Security, and Forensics,  2018,  pp 213-1 - 213-9,

 Copy citation
  Copyright statement 
Copyright © Society for Imaging Science and Technology 2018
Electronic Imaging
Society for Imaging Science and Technology