You and your family are at the pier, giddy to board the massive cruise ship docked nearby. Ahead lies a week of sunny beaches, indulgent buffet feasts and lounging around doing absolutely nothing.
And then you see the long lines for security, baggage and ID checks. It often takes 75 minutes for passengers to check in, but the Pool Deck looks a lifetime away.
Royal Caribbean Cruises thinks it has the answer to getting passengers aboard faster: AI-powered .
In December, passengers started taking part in a pilot program at a company embarkation point in Ft. Lauderdale, Florida. Passengers take selfies with the company’s app, then at the port, an AI-powered database matches their faces. After a quick double-check, Royal Caribbean’s staff members direct guests to their cabins.
The result: all-time high customer satisfaction.
“We wanted to turn what was a cold transaction into a really welcoming moment,” said Jay Schneider, who runs the Miami company’s digital operations. The goal is to get passengers “from car to bar in 10 minutes.”
Propelling the spread of facial recognition systems are huge leaps in artificial intelligence, the technology that seeks to give computers some of the ability, versatility and even creativity of human thinking. The biggest improvements have come through a specific area of AI called neural networks, inspired by the actual workings of human brain cells. Hardware and software improvements enabled an approach called deep learning — multiple layers of digital neurons that provide increasingly refined image analysis.
Overall, it’s a profound change. Recognizing and interpreting human faces is so important to us that whole sections of our brains are devoted to it. As we teach computers those skills, our interactions with them become more convenient — less like submitting database commands and more like dealing with the natural world in which we evolved. On the flip side, facial recognition can undercut privacy as our anonymity evaporates.
How neural networks work
In a training phase, neural networks scrutinize vast numbers of images of faces, learning on their own what’s important in the recognition process. It’s more accurate than the old way, with programmers describing what eyes, noses and mouths look like.
“Some layers capture color and texture and gradients,” said Amit Roy-Chowdhury, chair of electrical and computer engineering at the University of California, Riverside. “As you go deeper, they capture the shape of different parts of the object and ultimately the shape of the object itself.”
After training, neural networks create a stripped-down mathematical representation for each face. That representation can be compared rapidly with those of other faces, letting a facial recognition system decide if a person entering an office is on an authorized employee list or raise an alert when a potential shoplifter also appears on police arrest records.
To work well, facial recognition systems need images with well-illuminated, clear faces that give a neural network detailed, accurate data. That’s why passport photos require even lighting, plain backgrounds, neutral expressions and subjects facing straight toward the camera. “You try to make your input as consistent as possible so your analysis can be easier,” said Raj Minhas, leader of Xerox’s PARC Interaction and Analytics Lab.
Errors in the system
Facial recognition systems are getting better, but can still return errors. False positives match a face when no match should exist, such as when a person’s image isn’t in the database. A false negative occurs when the system misses a match it should have made.
Top-notch facial recognition systems today are 99.7 percent accurate with good lighting conditions, a 2018 study from the National Institute of Standards and Technology found.
One way to reduce errors is to tune the system by pushing some of the data apart to make it clearer for the neural net, reducing the likelihood of a false positive, said Marios Savvides, director of the CyLab Biometrics Center at Carnegie Mellon University.
Savvides’ team is also blending modern AI with an older approach called correlation filters that allows neural networks to improve facial recognition accuracy when faces are obscured, poorly lit or facing away from the camera. Overall, Savvides’ team is able to reconstruct faces even when they’re looking away or obscured by breathing masks, he said. “We live in a time where AI can surpass the human brain’s capability,” he said.
Another way to improve facial recognition is to pair it with other attributes, such as fingerprints, voice prints and other biometric data, or factors such as passwords. That might not work well when a system is just scanning people walking into a store, but it’s pretty common for controlled situations where people are logging into a network.
“We call it irrefutable identity,” said Vishal Gupta, chief technology officer at Unisys, which sells biometric authentication technology to the US Customs and Border Protection agency, among other customers. Unisys’ facial recognition system alone is 99 percent accurate, but with an approach it calls fusion that blends in other biometric factors, the company reaches 99.9 percent or 99.99 percent accuracy.
Facial recognition promises convenience, but it isn’t without concerns. Privacy advocates worry it will usher in an era of Big Brother monitoring or companies secretly tracking you. It also raises questions about AI bias; if you train a system using images of mostly white people, a common practice, the system might have difficulty recognizing people of color. Bias can creep into data sets in other ways, too, based on the data sets that are used to train the AI. If the photos used to train an AI show women cooking, the system might automatically conclude that women are likely to be in the kitchen.
“There’s no good way to know your data set is biased until you notice it failing,” said Broad Daylight security consultant Nick Merrill. “And by the time a biased algorithm wreaks real-world havoc, it’s too late.”
Still, many companies are thinking about how to use facial recognition to enhance the experience of their customers, visitors, patients and guests. They want facial recognition to make interactions easier, not creepy.
Northwell Health, which serves 3.5 million patients and is the largest health care provider in New York, is using a facial recognition program to streamline patient visits, reduce clerical errors and ultimately improve health.
Its system, whose hardware and software are made by RightPatient, uses sophisticated cameras that photograph faces and irises of patients. When a patient arrives for a checkup, the receptionist’s computer confirms the patient’s identity and pulls up his or her chart for the doctor. If there’s no record, the patient is enrolled with an ID check.
The system offers a number of advantages besides a smoother arrival in an office with less fumbling for ID. It’s less susceptible to problems of duplicate records for the same patient. If you’re already in the system, it’ll recognize you even if you got married and changed your name. Identity theft — think people trying to snatch prescriptions — is reduced because you can’t fake a face.
In emergencies like car accidents, the system would be able to identify an unconscious patient so that nurses and doctors could find medical histories and family contacts.
“We’re literally putting a face with a name,” said Laura Semlies, vice president of digital patient experience. “It just makes for a better clinical relationship.”
Biometric data is protected with encryption and is subject to the same strict privacy limits as other health data, she said.
Only about 12,000 of Northwell’s 3.5 million patients are enrolled so far, but now the network is spreading it more broadly around its facilities.
Facial recognition ahoy
Royal Caribbean Cruises has twice as many passengers as Northwell has patients, and more of them, too, will see facial recognition as the program expands, project leader Schneider said.
After finishing selfie and passport-scanning homework, passengers using the optional system can head to the port. As they arrive, passengers see a live view of themselves captured by cameras arrayed across the entrance. They’re arranged to avoid airport-style bottlenecks.
Behind the scenes, a computer matches their faces to the ones on record. Once there’s a match, passengers see a green box around their faces on the screens. A human agent verifies the matches, greets the passengers by name and checks their passports.
Royal Caribbean is required to have passenger photos, so the facial recognition system doesn’t significantly add to the data the company has. The company deletes passenger photos when the cruise ends, said Schneider, the cruise company’s digital chief.
The result is a system that whisks passengers aboard and gets the holiday started more quickly than before.
“Guests didn’t feel like they were on vacation until day 2,” Schneider said. “We wanted to give you that day back.”
Originally published at 5:00 a.m. PT.