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.

[Ditter]

LOL! I see what you did there.

[publius911]

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

Will this new miracle technique work on Long Form Birth Certificates or University records?

[bigheadfred]

The King of Saudia Arabia.

[sun7]

Continuing with my post #40 above, between the black teen’s legs there should be something more instead of total darkness. Just compare with those sitting next to him.

[Right Wing Assault]

Black people absorb all the light around them.

Actually, someone told me, “Black people draw heat.” That’s why rooms will a lot of black people in them get warm.

[Fightin Whitey]

"All right there King ol' bud let's keep your hand where we can see it for now and save the puppet trick for later."

[smoothsailing]

I'll leave it to you to evaluate all this, it's not a subject I've spent much time with. As for Gilbert, if you say he's a fraud, so be it.

Now this one is very suspicious!

[LonePalm]

One more item.

The trim stripes on the black teen's uniform show white on the outside edge.

None of the trim stripes on the other player's uniforms show white outside the trim.

Garde la Foi, mes amis! Nous nous sommes les sauveurs de la République! Maintenant et Toujours!
(Keep the Faith, my friends! We are the saviors of the Republic! Now and Forever!)
LonePalm, le Républicain du verre cassé (The Broken Glass Republican)

[Fred Nerks]

LOL! That’s a REAL fake!

[smoothsailing]

Are you sure? B^)

[Ditter]

Are there any other pictures of obama at this age?

No one has mentioned it but the black teen with the Punahou team doesn't even look like obama to me. I know people change from their teens to adulthood but come on........ Is this really him?

[JoeFromSidney]

There is a HUGE assumption that there is only one light source

There's a phenomenon I've observed repeatedly. On a bright but overcast day, while driving on a freeway, I frequently see a car ahead of me casting a shadow on both sides. Nothing mysterious about it, since diffuse light is coming from the entire sky. However, I wonder how their algorithm would handle that.

[Principle Over Politics]

A new style of HAND-bag, perhaps?

[Fred Nerks]

Supposedly taken from a page of his yearbook.

[WildHighlander57]

Re #27.

O’s left arm is too long....

[Bikkuri]

[Fresh Wind]

6. The shadow across the shoulders of the black teen isn’t matched on any of the other people in the picture (which is why I posted the picture).

[Darksheare]

Gramps hand was lifted from grams left arm.
Note scalloping on palm matches sleeve ruffle on left arm.

[Ditter]

I can't find anything wrong with that picture other than moosechelle’s slime green pant suit doesn't fit her and it is the one of the ugliest garments I have ever seen. In that respect it is perfect for her.

[Ditter]

His expression is exactly the same as the other photo and he is bigger than everyone else. The hand on his left shoulder looks weird but it is probably the guy standing behind him.