Skip to main content

Want to find out which viral photos were Photoshopped? So does Adobe

Adobe Research: Spotting Image Manipulation with AI

The Photoshop name is synonymous with image editing, but the same company behind the popular image editor is training an artificial intelligence program how to recognize manipulated photos. Adobe researchers, including senior researcher Vlad Morariu, recently published work on training a machine learning system to recognize doctored photos.

Rather than looking at all adjustments in general, including innocent adjustments like simple color corrections, the team focused on three types of image edits that can be used to create misleading images. Those “tampering techniques” include splicing or merging parts of one image with another, cloning sections within the same image, and removing an object.

To train a system to recognize a faked photo within a matter of seconds, the team fed the software thousands of manipulated images in order to help train the computer to spot photo trickery. The software looks at a handful of different clues that suggest an image might be manipulated. One method is to look for the slight differences in the red, green and blue color channels from altered pictures.

The second method the program uses for finding fakes is to generate a noise map of the image. The noise or grain that a camera captures, which is more obvious at high ISOs but appears in all images, has a unique pattern to each camera sensor. Because of that unique pattern, objects that have been added from another image will pop in that noise map. Using both techniques together helped improve the program’s accuracy.

As concern for the viral spread of fake news grows, more companies are looking to implement programs to help spot not just inaccurate text but altered images. Facebook, for example, recently expanded its fake news algorithms to include images and video. 

“Adobe is certainly a leader in creating tools that can produce manipulated images, so I think that makes Adobe uniquely positioned to also create tools that can help people determine if they are in possession of an authentic or manipulated image,” Morariu said.

The software won’t label a manipulated image with 100 percent certainty but could help reduce the number of fakes floating around feeds — if the program makes it out of research stages and sees wider implementation. Recognizing things like copied objects may help flag doctored images, but not other categories of fakes, such as pairing an unaltered image with an unrelated story or an event that happened at a different time.

Until then, there are a handful of ways to spot a fake photo without becoming a forensic photo expert.

Editors' Recommendations

Hillary K. Grigonis
Hillary never planned on becoming a photographer—and then she was handed a camera at her first writing job and she's been…
Is the iPad Pro ready for real photo editing? I ditched my MacBook to find out
can ipad pro replace macbook for photo editing photography 7120

With an eight-core A12X processor, the iPad Pro (2018) promised enough power to handle tasks normally reserved for laptop computers -- and photographers took note. At launch, the iPad's processor, Liquid Retina screen, and ultra-thin profile held big promise for creative pros on the go.

Unfortunately, the reality was less dazzling than the dream, dampened by the inability to use external storage and the annoyance of uploading photos twice if you wanted to use something other than Apple's default Photos app, such as Adobe Lightroom.

Read more
Photoshop just turned 30. So what’s coming in the next three decades?
photoshop is 30 rockers 1 copy

Adobe Photoshop turns 30 today, but instead of a party, the industry-standard photo editor is doing some self-reflection and making a handful of tweaks. In an update that launched on February 18, Photoshop for desktop gains several improvements to the workspace and performance, while the young iPad version sees a larger update as several major features migrate to the tablet version. As part of the anniversary, Adobe also offered a glimpse at what’s next for the now 30-year-old software.

The list of updates on the desktop starts with a why-wasn’t-this-always-like-this tweak. The Content-Aware Fill tool will now fill multiple areas without leaving the tool and going back into the workspace. Photo editors can click “apply” to fill one area and remain in the content-aware fill workspace, or click “OK” when finished with the tool entirely.

Read more
Photoshop for iPad gets a boost as Adobe adds these missing features
photoshop for ipad guide 9443

Photoshop for iPad is not yet even a month old, but Adobe is already sharing plans to narrow the gap between the iOS app and the desktop program. In a blog post published on November 21, Adobe shared a road map for the features that are coming next to Photoshop for iPad, starting with more-advanced selection tools.

While Adobe says the goal is to create an iPad app with the same features, the company said from the start that the iPad app wouldn’t have identical features to the desktop program. Despite the warning that full Photoshop for iPad is still coming, the app was met with mixed reviews at launch. Based on the same code base as the desktop app, Photoshop for iPad at launch still has more features than apps like Photoshop Fix using an interface that, while adapted to a touchscreen, feels familiar to previous desktop users. Those features include Adobe Fonts, which users also need to download the Creative Cloud app to bring to the iPad.

Read more