Now, a computer science professor at Dartmouth College who has developed an authoritative reputation in the field of visual forensics has invented a free, do-it-yourself online image verification service that could quickly confirm, or debunk, the authenticity of what you are seeing on the screen.
We’re building Fourandsix upon more than a decade of research in detecting image manipulation. Here’s a sampling of press coverage of co-founder Hany Farid’s innovations, as well as coverage for our first product, FourMatch:
Thanks to editing tools like Photoshop, it can be hard to tell what’s real on the web. There have been a number of forensic tools available to those wishing to investigate suspect images, but likely none so easy to use as Izitru, the service introduced on Monday by Dartmouth professor Hany Farid
These automated tests help with one important element of photo verification: provenance. You want to know who took the image and whether that image came directly from a digital camera. By shooting with the Izitru app, it ensures the photo is an original from the phone’s camera. The Izitru website can also be used by journalists to upload and test a photo.
While the photo app may be great for one-off validation of breaking news photos or other images that are called into question, there is potential in the developer API, which isn’t free, for online dating sites, auction sites or citizen journalists. A dating site could automatically reject images if it detects that photo has been photoshopped. An auction site could offer a high degree of trust that the image photographed is the real deal. Websites like CNN’s iReport could check before they’re even published that the image from the the news event is an original, untouched photograph.
[translated from German]
“There are two experienced digital picture experts behind Izitru, Kevin Connor and Hany Farid. The latter is a renowned expert in proofing picture manipulations. His statistical methods are also being applied for Izitru where image manipulations can be proven mathematically.”
Dr Hany Farid, professor of computer science at Dartmouth College, and Kevin Connor, the CEO of the image authentication company Fourandsix Technologies, examined Hansen’s RAW file of Gaza Burial – the original unaltered copy of the image captured by the camera. They concluded that Hansen had applied a “fair amount of post-production, in the sense that some areas have been made lighter and others darker”. But Farid and Connor “ruled out” any suggestion the image was a composite. As a result, Gaza Burial has been reconfirmed as the 2013 World Press Photo of the Year.
In the age of Photoshop, it’s almost impossible to say with absolute certainty whether any given image is real, but one former Photoshop employee hopes to change that. Fourandsix Technologies, a startup founded by a former Adobe Photoshop executive and a digital forensics expert, unveiled its first piece of software this week, which promises to help law enforcement determine whether a photo is authentic or not.
These days, how do you know if a photo is real? What are the ways we can detect if a photo is authentic, and why is that ability becoming more important especially for law enforcement? Nora Young speaks with Hany Farid, he’s a professor of Computer Science at Dartmouth College who has been researching ways to authenticate photos. Just this week, he launched his company Fourandsix Technologies, which offers software to help with this task.
As an expert in digital forensics, Farid’s work has primarily been geared towards individual projects. That is, until now. With the announcement of startup company Fourandsix Technologies, Farid and and co-founder Kevin Connor, a 15-year Adobe veteran, are making their services available to the public.
Hany Farid, a professor at Dartmouth College, has built a career and a reputation as a leading researcher in digital image forensics. He has made software tools for a number of impressive projects in recent years. One was a pixel-sleuthing program to detect how much fashion photographs have been burnished with Adobe’s Photoshop editing program to remove wrinkles and flab, while plumping up lips and breasts. Another was software for the automated detection of child pornography on the Web to help law enforcement agencies.
Company executives have good street cred in the area: the software came from Chief Technology Officer Hany Farid, a longtime expert in photo forensics (Get it? Forensics sounds like Fourandsix), and its president is Kevin Connor, former vice president of product management for Photoshop at Adobe Systems. Farid and Adobe worked together in the area in 2007, but never released any software.
The startup, which is currently self-funded, sees a market for its fake flagging software in law enforcement — combating crimes such as child exploitation — and for legal professionals.
Over the course of 16 years spent working in product management for Adobe, Kevin Connor often heard customers ask if there was any way to determine whether an image had been altered using Photoshop. …Connor is now working with noted digital image forensics expert Dr. Hany Farid on a startup to provide tools to help sniff out altered images. Their company, Fourandsix, will roll out its first detection product later this year.
Also featured in:
“There is a better way. Computer image specialists Hany Farid and Eric Kee at Dartmouth College in New Hampshire, US, have come up with a technique that measures how much a digital picture has been manipulated. It ignores trivial tweaks that improve the picture quality and focuses on changes that most alter a person’s appearance.”
“Their system scores a ‘1’ when there is little retouching and ‘5’ when there are significant changes. The computer programme they have developed looks at the image in terms of geometric changes, which include slimming the legs, hips and arms, the elongating of the neck or the enlarging of the eyes. It also assesses the photometric alterations, which affect skin tone and texture and are used to eradicate wrinkles, cellulite, blemishes, freckles, and dark circles under the eyes.”
“Farid, along with a Ph.D. student Eric Kee, invented the novel five-point metric measurement, and their research will be published this week in the American academic journal Proceedings of the National Academy of Sciences. He said they’re now considering developing a tool for Photoshop through his software company, Fourandsix (a play on forensics).”
“The resulting system is able to rate the extent of manipulation in new pairs of images with an accuracy of about 80%, says Farid. Although the technique is currently specifically tuned to images of people, Farid sayst that the unerlying algorithms could easily be adapted to analyse scientific images, using journal editors and scientists during the training process.”
“Dr. Farid’s position is in computer science, but his interest is social change. He proposes that magazines voluntarily adopt a code in which his algorithm’s result would be shown alongside modified photographs, possibly with explanatory text that details the sorts of changes found. Dr. Farid says an objective (though subjectively tuned) reference point removes the heat from the topic, and might give magazines a goal to reduce retouching if the extent of their efforts is numerically revealed.”