I confess, I worked together with the founder of imagetwin some years ago, even encouraging him to found a company. I would have even been interested in a further collaboration but unfortunately the company has cut all ties.
Should we really pay now 25€ for testing a single PDF?
My proposal was to build an academic community with ImageTwin’s keypoint matching and other AI text analysis as core functions; do further method development; provide a platform and comprehensive reviews instead of just drawing boxes around duplicated image areas.
Duplicated images in research articles erode integrity and credibility of biomedical science. Forensic software is necessary to detect figures with inappropriately duplicated images. This analysis reveals a significant issue of inappropriate image duplication invour field.
Unfortunately the authors are missing a basic understanding of the integrity nomenclature, they flags images that are expected to look similar. On the other contrary side it misses duplications as ImageTwin is notoriously bad with Western blots. Although I do not know which version of ImageTwin is even been used now, I think this paper erodes now the credibility of image analysis.
Is ImageTwin running out of control now just like Proofig?
Or will these startup companies soon be sold to Elsevier as the next step of the publisher giant to control science from cradle to grave?