Product AI
Published in

Product AI

For identity, it’s not just facial recognition anymore

“The serial number of a human specimen is the face, that accidental and unrepeatable combination of features. It reflects neither character nor soul, nor what we call the self. The face is only the serial number of a specimen,” said author Milan Kundera. It’s a rather unromantic way of looking at what many would consider the most important part of a human being, and Kundera was disregarding so many other ways human beings can be identified, such as through their gait, their voice, even their heartbeat. The uses for identification technology are growing by the day as airlines, retailers, casinos, hotels, automobile manufacturers, financial services companies, social media platforms, and even government departments are using voice, facial, and even heartbeat recognition technology to identity VIPs, to keep areas safe and secure, to cut down on merchandise losses, to be part of a payment platform, and even to act as biometric passwords.

Follow the heartbeat

As David Hambling explains in his MIT Technology Review article The Pentagon has a laser that can identify people from a distance — by their heartbeat, everyone’s heart is unique and, like an iris or a fingerprint, a person’s unique cardiac signature can be used for identification. Most crucially, it can be done from a distance, says Hambling. Unlike gaits and faces, which are not necessarily unique, an individual’s cardiac signature is original and remains constant throughout life, and cannot be altered or disguised.

Bionym, a wearable tech company, has created a product called the Nymi, which uses electrocardiogram (ECG) to authenticate user identity. In her Wired article Your Heartbeat May Soon Be Your Only Password, Carrie Yury states, “In effect, the Nymi turns a person’s own heartbeat into a unique key that can be used to unlock any conceivable device.” Andrew D’Souza, President of Bionym, believes the Nymi could mean the end of things like passwords, pin numbers, car keys, house keys, credit cards, and even airplane boarding passes. “We think that a wearable device that’s paired with your biometric can be a much easier, more secure form of user identification,” contends D’Souza.

“Everybody’s got a unique heartbeat,” states D’Souza, adding, it’s based on the size, shape of one’s heart as well as the orientation of the heart’s valves. For D’Souza, there’s a spectrum of biometrics: retinae are the most unique, fingerprints are next, then ECGs, followed by things like voice recognition. ECG metrics are not quite as developed as fingerprints, but they should surpass one of the original biometric identity systems in the next few years. The unique part of what Bionym is doing is the idea of persistent identity, claims D’Souza. Whereas an iPhone user must put her fingerprint onto a biometric scanner every time she wants to access her phone, with the Nymi, she only has to put it on once and, until the device is removed, she would be continuously or persistently authenticated, explains D’Souza. Only one match is needed. “We can tune the system to be very secure during that one matching process, and then you don’t need to think about it,” says D’Souza.

Walk to your own beat of your own unique drum

In his article Chinese ‘gait recognition’ tech IDs people by how they walk, Dake Kang reports that authorities in China are deploying ‘gait recognition’ software to identify a person’s walk. The ‘Gait recognition’ system can identify people from up to 50 meters (165 feet) away, says Kang, even when a person’s back is turned, or the face covered. This system fills a gap in facial recognition, which requires high-resolution images of a person’s face to work, states Kang. “You don’t need people’s cooperation for us to be able to recognize their identity,” says Huang Yongzhen, the CEO of Watrix, one of the leaders in gait recognition technology. Gait recognition is not fooled by limping, walking oddly, or being hunched over because the entire body is being analyzed, says Yongzhen

The technology is far from new as scientists in Japan, England, and the U.S. Defense Information Systems Agency have been researching gait recognition for over a decade, states Kang, but the Chinese might be perfecting it. “It’s more complex than other biometrics, computationally,” said Mark Nixon, a leading expert on gait recognition at the University of Southampton in Britain. “It takes bigger computers to do gait because you need a sequence of images rather than a single image.”

A person’s silhouette is analyzed, and a model is created out of the way a person walks, explains Kang. Users must upload video into the program and the software takes about 10 minutes to search through an hour of video. Special cameras aren’t required but real-time is not an option yet, which limits its commercial use, at least for now.

Although not as good as facial recognition technology, Huang argues the 94% accuracy rate should be good enough for commercial use and he envisions gait recognition augmenting face-scanning software. Beyond surveillance, gait recognition could help spot people in distress or help those in danger.

Finding one voice

In his Atlantic article The Panopticon Is Already Here, Ross Andersen states that “China’s iFlytek is perfecting a technology that can recognize individuals by their ‘voiceprint.’” iFlytek is not alone. According to classified documents leaked by Edward Snowden, the National Security Agency monitors terrorists using voice recognition technology. The US Bureau of Prisons also uses prisoners’ voiceprints to monitor their phone calls, reports Mara Hvistendahl in her article How a Chinese AI Giant Made Chatting — and Surveillance — Easy.

Voice navigation has become increasingly popular in China and iFlytek Input’s data privacy agreement lets it collect and use personal information for “national security and national defense security,” without users’ consent, says Hvistendahl.

“Voice identification technology captures and measures the physical qualities of a person’s voice when speaking as well as the unique biological parameters that combine to produce that voice,” says Ori Akstei in his article With Voice Identification, You Know Who’s Calling. Today, voice Identification is being used by call centers to authenticate each caller before services are provided. Voice identification uses the innate biological characteristics of a person’s voice, including duration, intensity, pitch, timbre, and dynamics, to create a unique voiceprint, contends Akstei. Voice identification is extremely difficult to spoof, and it simplifies the log-in process for users as passwords and/or answers to security questions aren’t required.

What the future holds

Facial recognition technology has become second nature to most consumers. In the West, few people seem to have a philosophical problem with the technology while in China companies can gather all kinds of data as consumers have no choice but to consent to its collection, whether they like it or not. Facial recognition and gait recognition can identify known shoplifters or spot problem gamblers who are on exclusion lists. They can also identify VIPs at retail establishments, in hotels or casinos, or at sporting arenas. As Parmy Olson explains in her WSJ article Facial Recognition’s Next Big Play: the Sports Stadium, facial and gait recognition software can also be used at sporting events to provide fans with a more personalized experience. For example, the Los Angeles Football Club has plans to, as they put it, “move everything to face.” They are currently testing facial recognition technology in stadiums with the goal of admitting “fans by authenticating faces and making the process as touchless — and as safe — as possible during the COID-19 pandemic,” says Olson.

Chinese AI companies are even now producing facial-recognition helmets for police that contain built-in infrared fever detectors, which can automatically send data to the government, says Andersen. In Malaysia, Yitu, a Chinese AI start-up, is bringing facial recognition technology to Kuala Lumpur’s police department, while 110,000 lampposts are being retrofitted with facial recognition cameras in Singapore, adds Andersen.

From security, safety, VIP identity, loss prevention, and payment processing, facial, gait, heartbeat, and voice recognition are radically altering the way businesses and customers interact. Airlines, automobile manufacturers, hospitality and gaming companies, banks and fintech companies, as well as sports teams, are utilizing identification technology in new and revolutionary ways to provides safety, security, and a better customer experience. What all of these technologies prove is that each customer is unique. “The face might be the serial number of a specimen,” as Kundera said, but so too is the voice, the walk, and the heartbeat. Everyone needs to be treated like the individual they are, even if, as Margaret Mead once ironically quipped, “Always remember, you are absolutely unique, just like everyone else.”

--

--

--

Product AI is a magazine that covers AI product/project management, AI business cases and reference architectures. We invite product experts and solution architects to share their knowledge here.

Recommended from Medium

Pascal’s Wager and the art of designing autonomous cars

8 Must Do’s In Enterprise AI Chatbot Development

Collective Intelligence - the bigger picture.

Machine Learning for Grandpas and Grandmas

Creative Artificial Intelligence in Music: Genius Innovation for Sync and Other Fascinating Use…

Trump’s AI Initiatives and the Future of AI and Governments

How Chatbots Have Become Our Guide in Times of COVID-19?

At last, a chat bot that is different!

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Andrew W. Pearson

Andrew W. Pearson

Andrew Pearson is the MD of Intelligencia, a software consulting company. Speaker, author, columnist, Pearson writes about IT issues like AI, CI, and analytics.

More from Medium

ML for Noobs: The Landscape

Can AI Breathe? Or, Where Humanity Ends and the Automaton Begins

From Songs to Stems — Music Source Separation with Artificial Intelligence

Segna Newsletter — 16 December 2021