New Technique Analyzes Shadows to Spot Photo Fakes

INSIDE SCIENCE NEWS SERVICE ^ | Aug 14 2013 | Ker Than

[neverdem]

Algorithm spots forgeries by spotting shadows that don't match light sources.

(ISNS) -- A new algorithm can spot fake photos by looking for inconsistent shadows that are not always obvious to the naked eye.

The technique, which will be published in the journal ACM Transactions on Graphics in September, is the latest tool in the increasingly sophisticated arms race between digital forensics experts and those who manipulate photos or create fake tableaus for deceptive purposes.

National security agencies, the media, scientific journals and others use digital forensic techniques to differentiate between authentic images and computerized forgeries.

James O'Brien, a computer scientist at the University of California, Berkeley, along with Hany Farid and Eric Kee of Dartmouth University, developed an algorithm that interprets a variety of shadows in an image to determine if they are physically consistent with a single light source.

In the real world, O'Brien explained, if you drew a line from a shadow to the object that cast the shadow and kept extending the line, it would eventually hit the light source. Sometimes, however, it isn't possible to pair each portion of a shadow to its exact match on an object.

"So instead we draw a wedge from the shadow where the wedge includes the whole object. We know that the line would have to be in that wedge somewhere. We then keep drawing wedges, extending them beyond the edges of the image," said O'Brien.

If the photo is authentic, then all of the wedges will have a common intersection region where the light source is. If they don't intersect, "the image is a phony," O'Brien said.

A growing toolbox

The new technique does have limits, though. For instance, it was designed for use with images in which there is a single dominant light source, not situations with lots of little lights or a wide, diffuse light.

One could also imagine a clever forger anticipating the use of the shadow detection software and making sure they created shadows that would pass the test. The researchers call this just one technique in a toolbox of methods that are being developed to catch forgers.

O'Brien says one of the motivations for developing their algorithm is to reduce the need to rely on subjective evaluation by human experts to spot forgeries, which can easily mistake forged photos for authentic photos and authentic photos for forged ones.

Take for example the iconic 1969 photo of NASA astronaut Buzz Aldrin posing on the surface of the moon.

"The shadows go in all kinds of different directions and the lighting's very strange...but if you do the analysis [with our software], it all checks out," O'Brien said.

Our trouble with shadows

It's unclear why humans are so bad at detecting inconsistent shadows, especially since our visual systems are so attuned to other cues, such as color, size and shape, said UC-Berkeley vision researcher Marty Banks.

One idea, Banks said, is that shadows are a relatively unimportant visual cue when it comes to helping organisms survive.

"It's important to get the color right because that might be a sign that the fruit or meat you're going to eat is spoiled, and it's important to get size and position right so you can interact with things," said Banks, who did not participate in the research. "And then there are things where it just doesn't really matter. One of them is shadows, we believe."

After all, before the advent of photography, one was unlikely to ever encounter a scene where the shadows are pointing in the wrong direction.

Analyzing shadows could also just be a more mentally taxing task, said Shree Nayar, a computer vision researcher at New York's Columbia University, who was also not involved in the research.

"This is a more complex second order effect," Nayar said, "and it's something we have a much harder time perceiving."

Man-machine collaboration

For now at least, the team's method still requires some human assistance, by matching shadows to the objects that cast them.

"This is something that in many images is unambiguous and people are pretty good at it," O'Brien explained.

Once that is done, the software takes over and figures out if the shadows could have been created by a common light source.

In this way, the scientists say, their method lets humans do what computers are poor at — interpreting the high-level content in images — and lets computers do what humans are poor at — testing for inconsistencies.

"I think for the foreseeable future, the best approaches are going to be this hybrid of humans and machines working together," O'Brien said.

Columbia's Nayar said he could envision a day when computers won't need human assistance to perform such tasks, because of increasingly sophisticated models and machine learning algorithms.

Because their software requires relatively simple human assistance, O'Brien and his team say it could one day be useful not only to experts, but the general public as well.

"So you could imagine a plug-in for Photoshop or an interactive app in your web browser where you can do that, and it would flag any inconsistencies," O'Brien said.

---

Ker Than is a freelance writer based in Southern California.

[Yaelle]

That hand is so fake looking. I don’t see a reason to fake this pic but that hand is seriously weird.

[Fresh Wind]

[Fred Nerks]

Interesting photograph, but I’ve always had a sense that it shows the boy and Stanley Armour meeting Stanley Ann Dunham and Maya when they finally showed up from Indonesia in 1971-1972 after zero had been attending grade five at Punahua, and what you see under zero’s arm is a pocket-book of some kind - because no one would hold a child around the chest with a fist.

[yefragetuwrabrumuy]

For at least 10 years now, Photoshop has had a plugin that allows you to change a light source not shown. It also changes the resultant shadows.

It is pretty neat looking, like you are looking through a camera lens at your picture, and somebody behind you is moving the light source illuminating the scene.

[kvanbrunt2]

only a bunch of geeks would call their group the Association for Computing Machinery. I loved reading their journals learned alot and was the local chapter program chairman and VP for a season. great stuff.

[smoothsailing]

It is intriguing.

According to the linked story, there are additional anomalies in the picture that strongly suggest photo manipulation.

http://www.wnd.com/2012/07/another-doctored-image-deepens-obama-mystery/

[Daffynition]

..........or.........

you could just look with your eyes.

[Cold Case Posse Supporter]

What the hell?

[Eagles6]

Watch out barry! There’s a large, disembodied hand, dispraportinal to anything else in the picture, hovering over your left shoulder!

[JoeProBono]

[Fred Nerks]

Barring accidents or birth defects, everyone who has a hand has fingers, and finger have knuckles, and black hands have black fingers with black knuckles...

The assumption that the hand belonged to FMD is rather meaningless when one considers it’s a known fact that zero arrived in Hawaii approx one year before Stanley Ann Dunham did. Her father and zero met her at the airport on arrival, it must have been in 1972, when Maya was almost two years old, and in 1973, Stanley Ann Dunham and Lolo Soetoro lodged a joint tax return in Hawaii, so if there’s a body missing that might have belonged to the hand, it would more likely belong to Lolo Soetoro, whose presence in Hawaii wasn’t known until the tax return came to light recently.

Joel Gilbert is a fraud.

[Fred Nerks]

[Jane Long]

What is THAT?

[madison10]

Someone was taken out in that space between Obama’s and Michelle’s legs. The gray/tan there looks painted in and Michelle must be an alien because she appears to have two right hands.

[Fred Nerks]

It's a SPOOF, like this one:

[smoothsailing]

Lolo's hand?

I suppose it could be. It sure looks like somebody's hand.

[smoothsailing]

[JoeProBono]

[Fred Nerks]

I think it looks ‘like somebody’s hand’ simply because Stanley Ann Dunham is standing there. Take her away, and it would look like he was holding something between his arm and chest.

There certainly are fakes, the Central Park sequence is an example, but with each fake, there has to be a need. What need would there be to tamper with an arrival image - for an event known to have taken place?

We saw this ‘black hand’ years before Joel Gilbert got hold of it and used it in his DVD and book. Did he mention that Lolo Soetoro was working and living in Hawaii with Stanley Ann and Maya as shown on their joint tax return?

No he didn’t. He was too busy trying to implicate Stanley Ann Dunham and Frank Marshall Davis in a liason that never happened, to ask any questions of that nature. It suited his style to promote the theory that ‘black fist’ which was probably a bag of some sort, as being the hand of FMD.

Joel Gilbert is a fraud. Every item of his mockumentary has been exposed for what it was, and this is just one more example.

[sun7]

So many things wrong with the team photo:

1. The black teen’s whole profile (his head, body and arm) is larger than that of anyone in the photo. It would look more natural if such a profile was on the front row. If the photo was real, such a teen should have grown to a much bigger man than obama;

2. Something is definitely amiss with the left arm of the youngster sitting to the right of the black teen;

3. Everyone was looking straight ahead except the black teen;

4. The black teen’s left leg/knee doesn’t look real at all. His right knee is too small compared to his body. Both legs are likely fake.

5. Letters are showing on everyone’s tops except the black teen’s, what a coincidence.