Big Data: Facial Recognition and the Biometrics Movement

Just a few years ago, using a fingerprint to sign on to your phone seemed futuristic. Today, it’s everywhere and just the beginning of how biometrics will be woven into our lives. Biometrics is a method of digital identity verification that scans a person’s physical characteristics such as a fingerprint, iris, face, or voice.

The field of biometrics presents both enormous promise as well as challenges. The promise includes new applications that can increase convenience, safety, and business opportunities. The challenges include finding the technology to manage this huge volume and variety of data as well as privacy and security concerns.

The world’s largest biometric database

One of the most ambitious biometrics initiatives is the Aadhaar project —building an identity verification database of India’s 1.2 billion residents. For the disadvantaged in India, the inability to prove one’s identity is one of the biggest barriers that prevent people from accessing benefits and subsidies. Since very few residents have any type of paper identification, it’s difficult for the government to ensure that welfare benefits go directly to the right person.

The world’s largest biometric database will provide every resident with a unique identification number that can be used to access a variety of services and benefits such as food coupons, cooking gas, checking accounts, loans, insurance, pensions, and property deeds. The project’s goal was to enroll a million people per day, taking four years to enroll the entire population.

The biometric database includes an iris scan, digital fingerprints, a digital photo, and text-based description for each resident. Residents use fingerprints or iris scans for authentication. The system processes over a hundred million identity verifications each day, and can verify a person’s identity within 200 milliseconds.

Using biometrics to fight crime

Biometric technologies are also being used to help fight crime. While fingerprints have been used in law enforcement for decades, there is increased investment in facial recognition technologies by the military, casinos, and law enforcement. And some retailers are starting to use facial recognition to identify known shoplifters in their stores or to prevent them from even entering a store.

Tracking human emotions in shopping experiences

Some retailers are also experimenting with facial recognition to gain insights about the customer’s shopping experience. A recent survey of British retailers revealed that more than 1 in 4 are using facial recognition technologies in their stores. A third of respondents object to stores collecting data on them and 24 per cent believe it’s useful for their shopping experience. Younger shoppers are more likely to find it to be beneficial to improve their shopping experience.

Facial recognition that focuses on reading emotions rather than a specific person’s identity is also being used in business. The Bank of New Zealand is using facial recognition software to gauge customer reactions to various financial scenarios, such as a person’s reaction to having to buy a last-minute plane ticket to attend a wedding. Consumers who agree to be filmed through a webcam hear financial scenarios while the software captures their muscle movements to decode their micro-expressions. The feedback allows consumers to be more aware about how their emotions may be guiding their financial decisions. The system can capture subtle responses much faster than a human can.

Focus groups are also using facial recognition software. Customer response is often emotional rather than rational, and companies often try to appeal to emotions instead of product features. Marketers can watch how people react viscerally to products, and use that feedback to make decisions on product features and branding. While the focus group is a controlled experience, it’s how people are responding in real time that makes the difference. Fortunately, there’s a way to analyse faces without a bunch of people having to sit in front of screens all day. Big data makes it possible to process the faces, reading the emotions of customers and generating insights for product or service development.

Giving your face to Facebook

Facial recognition technology is getting increasingly sophisticated. The large sample sizes that big data offers for companies like Facebook and Google is enabling them to build more accurate facial recognition algorithms. Facebook can recognise faces about 97 per cent of the time already, building on its vast network of users. Facebook is also working on a system that can identify people if they can’t see their faces through other identifiers like hair, posture, body or clothing. This system is 83 per cent accurate at identifying people without seeing their faces.

Google has built similarly powerful capabilities into its Google Photos search technology. It can already identify pictures of someone when their faces are not fully visible. This technology is currently available and free. However Google has chosen to not connect pictures with a person’s identity.

With more mobile phone owners capable of recording good quality video, the next big step will be video facial recognition. It’s not that much of a stretch, since a video is simply a string of lots of still images.

Let the people decide

As with any data collection, privacy is a big concern. Biometric technology developers and organisations that use these technologies need to ensure the public is educated and given the opportunity to opt out if they want to. While people in a focus group can consent to having their likenesses used, what about people in stores? Companies wanting to use facial recognition technologies should take care to inform their customers and anonymise personal data. While many young people relish being recognised wherever they go, many other people still prefer their anonymity.

Editor's note: this was originally published on IT ProPortal here. 

no

CTA_Inside

Streaming Data Architecture: New Designs Using Apache Kafka and MapR Streams

Streaming Data Architecture:

New Designs Using Apache Kafka and MapR Streams

 

 

 

Download for free