Another dot in the blogosphere?

Fake spotting

Posted on: May 21, 2019

Petapixel recently highlighted a microbiologist’s ability to spot photos that had been digitally manipulated.

Most of the manipulations were copies of existing artefacts in a photo. These extras were included to make the photos look even more dramatic. But doing this was offering lies as truth.

The microbiologist did not start critiquing photos for fun. It was part of her work:

My initial search for duplicated science images within the same paper led to a large project in which I screened over 20,000 scientific papers. About 4% contained duplicated or manipulated photos. Our publication was one of the first to investigate this problem, and it has led to much greater awareness and scrutiny among journal editors and peer reviewers.

She was fighting the offers of lies for truth.

Her interview revealed that she was using her own eyes and experience to detect fakes. She did not rely on technology algorithms to help spot patterns or the like.

We need this form of fake spotting in current and future student-submitted work. But most educators probably do not have this skillset. Current tools like Turnitin do not even begin to scratch the surface of doing this. For example, it cannot effectively evaluate images in a student’s work against another.

I wonder what is stopping companies from developing fake spotting tools aggressively. The central method is pattern recognition in submitted work and comparing it with existing work in a database. Perhaps it is that database that is the problem.

All that said, spotting faked images should not be left to automation just like spotting plagiarised work should not be left to a tool like Turnitin. We need to augment machine detection with evaluation by humans.

Tags: ,

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

This site uses Akismet to reduce spam. Learn how your comment data is processed.

Click to see all the nominees!

QR code

Get a mobile QR code app to figure out what this means!

My tweets


Usage policy

%d bloggers like this: