Podcasts & RSS Feeds
Most Active Stories
- Listen: Can You Pick Out The Northwest Accent? (And Yes, We Have One!)
- Former Boeing Executive Alan Mulally’s Advice On Labor: 'Working Together Works’
- Tips On Staying Healthy While You Travel
- Mass: Expect Intensifying Rains With Global Warming
- Just Back From Spain, Nancy Leson Offers A Few Pointers On Paella
News & Music Contributors
Sun March 16, 2014
Photo Identification: The 'Best And Worst Way' To ID People
Originally published on Sun March 16, 2014 3:35 pm
As an international armada of planes, ships and helicopters continues to comb the Indian Ocean for any sign of Malaysian Airlines flight 370, now missing for more than a week, Interpol confirms that two passengers aboard that flight were traveling on stolen passports.
Aviation experts say the incident highlights a major security gap at many airports: It is simply too easy to board a flight using someone else's photo ID.
A new study looked in to the reliability of facial recognition with photos. Researchers found that the fewer fake IDs people see, the harder it is to spot them when the do come along — and multiple traps can cloud screeners' judgment.
The study, conducted by Megan Papesh of Louisiana State University and Stephen Goldinger of Arizona State University, was published in the journal Attention, Perception, & Psychophysics in February.
Find The Fake
The study authors showed subjects a set of photos of people they had never met. The set was made up of pairs: One photo was a photo ID taken months or even years earlier, the other was a candid contemporary shot. In some cases, the photos were of two different people — one standing in as a "fake ID." Researchers asked subjects to pick out the pairs that were not of the same people.
When the rate of fakes was high — that is, when half of the photo IDs didn't match their user — those surveyed were wrong 20 percent of the time. But with fewer fakes — more closely resembling a real-world situation like an airport security line — the number of errors skyrocketed. Even when people were given multiple opportunities to detect their errors, they failed to pick out the fake nearly half the time.
Researcher Megan Papesh says one reason we're so bad at picking out fake IDs is that people change the way they look all the time — their hair, weight, whether they wear glasses. "Myriad changes occur, and that makes people willing to accept a lot of changes," she says.
Learning From Bouncers
One lesson from this study may be that security agents, who rarely see fake IDs, can learn something from bouncers at bars, who see many more fakes.
"A lot of my research assistants have told me that bouncers at clubs are really good at spotting fake IDs, despite the motivation to let people in and sell alcohol to them, because they encounter so many of them," says Papesh. "We're interested in providing training to individuals who are tasked with doing this in more security contexts with those bursts of fake IDs, kind of like they would get if they were bouncers at a club."
Another possible way to make the system more reliable, Papesh says, would be to take better pictures in the first place. For example, in passport photos people are asked to put long hair behind their ears and take off glasses. Most states do not require this for driver's license photos. Another possibility would be requiring multiple photos of the same person for a single ID. Papesh says previous research has suggested that having multiple photos, perhaps from multiple angles, can help screeners identify fakes.
Ultimately, though, are photo IDs just a bad way to identify people?
"Unfortunately, it's simultaneously the best and the worst way that we have," says Papesh. Reliable computer face-recognition is still a long way away, and other technologies are more invasive.
"Barring anything much more invasive like retinal scans or thumbprint ID," she says, "face matching is really the best way to go without being too terribly invasive."
ARUN RATH, HOST:
Someone intentionally took the plane off course. That is the consensus of investigators still struggling to understand what happened to Malaysia Airlines flight 370.
Today, the Malaysian defense minister announced the authorities were refocusing their investigation on all crew and passengers. Last week, Interpol confirmed that two passengers aboard the flight were traveling on stolen passports. While there's no evidence that those passengers are behind the plane's disappearance, aviation experts say it highlights a major security gap at many airports. It is still possible to board an airplane with a fake photo ID.
How could that be the case? A new study of facial recognition finds that people are shockingly bad at picking out fake photo IDs.
Megan Papesh is one of the authors of that study.
MEGAN PAPESH: When you are tasked with matching somebody to a photo ID that had been taken days, months, even years prior, all of the many changes that occur in people - gain weight, lose weight, shave, put on glasses - you know, myriad changes occur, and that makes people really willing to accept a lot of changes.
RATH: So how did you do the study? How did you take a look at this?
PAPESH: We took pictures of students at Arizona State University and got their permission to download their student ID photos. And then at Louisiana State University, we presented those photos to students and asked them to make - basically match mismatched decisions to those where we manipulated how frequently we showed them IDs that mismatched. So those are the critical ones. Those are the bad guys.
RATH: Mm-hmm. And how often did they get it wrong?
PAPESH: Well, when they see the mismatches frequently - so that's 50 percent of the time - they would get it wrong about 20 percent of the time. So they would be about 80 percent accurate. But when they only saw the mismatches 10 percent of the time, their error rates actually skyrocketed. They went up to 45 percent.
RATH: Just for some real-world examples, say, if you're a bouncer at a bar, you're checking IDs, are you more or less likely to get those right compared to other situations?
PAPESH: That situation's actually really interesting. So a lot of my research assistants have told me that bouncers at clubs are really good at spotting fake IDs despite the motivation to let people in and sell alcohol to them because they encounter so many of them, which is part of why we're interested in providing training to individuals who are tasked with doing this in more security contexts with those bursts of fake IDs, kind of like they would get if they were bouncers at a club.
RATH: So TSA agents could learn something from the bouncer community.
PAPESH: I hesitate to put them on that spot, but it's possible.
RATH: Potentially. And in terms of the ID itself, is there anything that could be done with that or photographic techniques that could make them less fallible?
PAPESH: Well, I hear for passport photos, you have to put your hair behind your ears if you have long hair because most people don't change their ears. But driver's licenses don't have those sort of constraints. But there are some researchers in the U.K. that have found that having multiple photos of the same person helps people identify faces to photographs.
RATH: You know, I know that we know from computer modeling that facial recognition is extremely complicated. And your work would seem to indicate that humans actually aren't as good at it as we might have thought we were. Is this simply a bad way to identify people?
PAPESH: Unfortunately, it's simultaneously the best and the worst way that we have. Computer face recognition software is making tremendous strides. But unfortunately, that software doesn't perform at the level of humans yet, so it can't be deployed in applied contexts. And barring anything much more invasive, like retinal scans or thumbprint ID, face matching is really the best way to go without being too terribly invasive.
RATH: Megan Papesh's most recent study is about the reliability of photo ID recognition. Megan, thank you.
PAPESH: Thank you very much for having me.
(SOUNDBITE OF MUSIC)
RATH: This is NPR News. Transcript provided by NPR, Copyright NPR.