Record Details

Image Forensics: Detecting duplication of scientific images with manipulation-invariant image similarity

Harvard Dataverse (Africa Rice Center, Bioversity International, CCAFS, CIAT, IFPRI, IRRI and WorldFish)

View Archive Info
 
 
Field Value
 
Title Image Forensics: Detecting duplication of scientific images with manipulation-invariant image similarity
 
Identifier https://doi.org/10.7910/DVN/7I1YWJ
 
Creator Cicconet, M.
Elliott, H.
Richmond, D.L.,
Wainstock, D.
Walsh, M.
 
Publisher Harvard Dataverse
 
Description Manipulation and re-use of images in scientific publications is a concerning problem that currently lacks a scalable solution. Current tools for detecting image duplication are mostly manual or semi-automated, despite the availability of an overwhelming target dataset for a learning-based approach. This paper addresses the problem of determining if, given two images, one is a manipulated version of the other by means of copy, rotation, translation, scale, perspective transform, histogram adjustment, or partial erasing. We propose a data-driven solution based on a 3-branch Siamese Convolutional Neural Network. The ConvNet model is trained to map images into a 128-dimensional space, where the Euclidean distance between duplicate images is smaller than or equal to 1, and the distance between unique images is greater than 1. Our results suggest that such an approach has the potential to improve surveillance of the published and in-peer-review literature for image manipulation.
 
Subject Computer and Information Science
Social Sciences
Other
siamese network
similarity metric
image forensics
image manipulation
Computer Vision
Pattern Recognition
 
Contributor Barbosa, Sonia