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

TL;DR

This paper introduces a deep learning-based method using a Siamese CNN to detect manipulated scientific images by measuring similarity invariant to common transformations, aiming to improve image duplication detection.

Contribution

It presents a novel data-driven approach with a 3-branch Siamese CNN that effectively identifies manipulated images regardless of various transformations.

Findings

The model successfully maps duplicate images to a small Euclidean distance in 128D space.

It outperforms traditional manual and semi-automated detection methods.

Potential to enhance surveillance of scientific literature for image manipulation.

Abstract

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.