Asaad, A. and Jassim, Sabah A. (2017) Topological Data Analysis for Image Tampering Detection. In: Digital Forensics and Watermarking: 16th International Workshop , IWDW 2017. Lecture Notes in Computer Science (10431). Springer Cham, pp. 136146. ISBN 9783319641843

Text
TDA.pdf  Accepted Version Download (612kB)  Preview 
Abstract
This paper introduces a topological approach to detection of image tampering for forensics purposes. This is based on the emerging Topological Data Analysis (TDA) concept of persistent homological invariants associated with certain image features. Image features of interest are pixels that have a uniform Local Binary pattern (LBP) code representing texture feature descriptors. We construct the sequence of simplicial complexes for increasing sequence of distance thresholds whose vertices are the selected set of pixels, and calculate the corresponding nonincreasing sequence of homology invariants (number of connected components). The persistent homology of this construction describes the speed with which the sequence terminates, and our tamper detection scheme exploit its sensitivity to image tampering/degradation. We test the performance of this approach on a sufficiently large image dataset from a benchmark dataset of passport photos, and show that the persistent homology sequence defines a discriminating criterion for the morphing attacks (i.e. distinguishing morphed images from genuine ones).
Item Type:  Book Section 

Uncontrolled Keywords:  Topological Data Analysis, Persistent homology, Image tampering, Image morphing 
Subjects:  Q Science > QA Mathematics > QA75 Electronic computers. Computer science 
Divisions:  School of Computing 
Depositing User:  Rachel Pollard 
Date Deposited:  01 Aug 2019 10:17 
Last Modified:  12 Mar 2020 15:10 
URI:  http://bear.buckingham.ac.uk/id/eprint/397 
Actions (login required)
View Item 