In the modern era of online social networks (OSNs), the number of online users of such services has increased exponentially. User‐generated and posted data has brought up to the surface several challenges
In the modern era of online social networks (OSNs), the number of online users of such services has increased exponentially. User‐generated and posted data has brought up to the surface several challenges. An OSN by nature promotes visual contents sharing. The volume of these Big-visual-Data is reported to be in billions (as of 2011 Stats); Flicker® hosts about 6 billion images, Facebook® 70 billion images, 100h/min of video streams are uploaded on YouTube®. The consequences on security and individual privacy are enormous. A challenge in the OSNs arena is the intentional editing of images to mislead the public opinion (or a specific community) regarding certain issue (e.g., duplicating certain regions in a given image to hide/alter its local or global semantic information)[1-4].
Motivated by the above challenge, this project will be termed as Intra/Inter Image Tamper Detection. Within this framework, the proposed project topic could be formulated as follows (open to discussion with the potential student(s)). Existing methods will be investigated in order to develop a system that can serve to achieve the goal of this project in an efficient way (computational complexity and accuracy are to be considered). The data set and a MATLAB code are available from  to begin with.
Implementation of an algorithm to detect copy-move image tempering, in which one region of an image is copied to another area of the same image. For more enthusiastic students, that can be extended to detecting regions coming from photo composites by using different image(s) (a.k.a. Inter-image tamper detection).
Prerequisite knowledge (if any)
Machine Learning/ Data Mining
Knowledge of image processing is a plus but not a prerequisite
Abbas Cheddad (Universitetslektor): Office: J3112, Email: email@example.com
ReferencesVincent Christlein et al.(2012). An Evaluation of Popular Copy-Move Forgery Detection Approaches. IEEE Transactions on Information Forensics and Security, 7(6), pp:1841-1854.
 Ewerton Silvaetal.(2015).Going deeper into copy-move forgery detection: Exploring image telltales via multi-scale analysis and voting processes. Journal of Visual Communication and Image Representation,29,pp:16–32.
 JianLietal.(2014).Segmentation-Based Image Copy-Move Forgery Detection Scheme. IEEE Transactions on Information Forensics and Security, 10 (3) pp:507-518.A. Popescu and H.Farid(2004).Exposing digital forgeries by detecting duplicated image regions. Department of Computer Science, Dartmouth College, Tech. Rep.TR2004-515.