Figure Reuse Detection

By  Markus | Aug 24, 2024
Figure Reuse Detection

Imagetwin now detects figure reuse across articles for all figure types, including diagrams, flowcharts, box plots, photographs, and more. While our initial focus was on life science images such as FACS plots, microscopy images, or Western blots, this update expands Imagetwin’s capabilities to cover all scientific disciplines. Whether in the humanities, computer science, mathematics, or physics, Imagetwin can now effectively identify problematic manuscripts containing plagiarized figures or other inappropriate scientific behaviour.

Figure extraction and reuse detection

The system automatically extracts figures from manuscripts and compares them against our image database to detect reuse across articles. If a figure or substantial portions of it have been reused in another publication, Imagetwin flags the duplicate. These flagged duplicates are displayed in our web application, with detailed information about the source paper, such as DOI, authors, and publication year. This enables users to quickly determine whether the duplication represents acceptable reuse or potential scientific misconduct.

For figure reuse detection, we have indexed 25 million figures from previously published articles in our image database. We will continuously add new figures in future updates.

Detection accuracy

We evaluated the figure reuse detection algorithm by measuring its accuracy and false positive rate. We used 216 figures extracted from 50 randomly selected papers. We applied various alterations to the figures, including cropping, image quality/resolution changes, JPEG compression, and adjustments to brightness and contrast. We use the altered images to measure how effective the algorithm is in detecting the figures’ original sources. The algorithm successfully identified 197 of the 216 figures, achieving a 91% accuracy rate.

Cases, where duplication was not detected (false negatives), involved small figures without distinctive features, making unique identification across millions of images difficult. We identified 3 false positives among the 216 evaluated figures, resulting in a false positive rate of about 1%. The false positives involved maps and highly similar (but not identical) bar plots. The evaluation results demonstrate the robustness of our algorithm in accurately detecting figure reuse while maintaining a minimal false positive rate.

Evaluation results for figure reuse detection applied on 216 figures from 50 papers
Metric Result
Accuracy 197 of 216 figure duplicates detected (91% accuracy)
False positive rate 3 false positives in 216 checked figures (1% false positive rate)

See Related Blogs

Imagetwin Integrates with Wiley’s Research Exchange to Strengthen Image Integrity at Scale
By Kim
•
May 26, 2026

Imagetwin Integrates with Wiley’s Research Exchange to Strengthen Image Integrity at Scale

We are proud to announce that Imagetwin has been integrated into Research Exchange, Wiley's research publishing platform. Wiley is a global leader in authoritative content and research intelligence for the advancement of scientific discovery, innovation and learning. The integration brings AI-powered image integrity screening to the 25+ research integrity checks already embedded in Research Exchange, enabling editors and integrity specialists to identify potentially manipulated or fraudulent images before publication.

A Researcher’s Sleuthing Journey and How It Led to a $15M Case
By Sofiia
•
Apr 22, 2026

A Researcher’s Sleuthing Journey and How It Led to a $15M Case

Research integrity sleuth Sholto David joins Imagetwin CEO Patrick Starke to discuss image manipulation detection, the Dana-Farber $15M False Claims Act case, and practical screening advice for journal editors and integrity officers.

Imagetwin Partners with CACTUS to Scale Image Integrity Across Research Workflows
By Sofiia
•
Apr 22, 2026

Imagetwin Partners with CACTUS to Scale Image Integrity Across Research Workflows

Imagetwin is now integrated into CACTUS solutions, enabling automated detection of image duplication, manipulation, plagiarism, and AI-generated figures within research and publishing workflows.

Protect Research Integrity with Confidence

Start using Imagetwin to detect image integrity issues and support trustworthy research publishing.

Get Started
Contact Us

Frequently asked questions

Imagetwin is software designed to detect integrity issues in figures of scientific articles. It helps identify inappropriate manipulations and duplications in various figure types, including western blots, microscopy images, and light photography.

Imagetwin is beneficial for researchers, peer reviewers, journal editors, and institutions aiming to uphold the quality and trustworthiness of scientific publications by ensuring the integrity of visual data.

Users can upload a PDF or multiple image files to Imagetwin. The software then scans the content using algorithms and vast databases of published scientific figures to detect potential integrity issues. Within seconds, results are presented through a web interface, highlighting any detected problems for review.

Yes, we prioritize data privacy and security, ensuring that all image indexing and exchanges are protected with industry-standard encryption and security best practices.

Create an account and start using Imagetwin immediately. We prepared a few example documents that you can scan free of charge.

Yes, Imagetwin is a powerful addition to the peer-review process. It automatically detects various integrity issues, which can then be quickly verified by a reviewer, enhancing the efficiency and accuracy of the review process. Imagetwin also partners with industry leaders in publishing and scholarly workflows, such as Morressier, TNQ Technologies and more, transforming how research is submitted, reviewed and published.

For more detailed guidance on using Imagetwin, contact our support team through our Contact Us page.