The maturing of contactless fingerprints enables the unification of biometric capture using smartphones

0

Contactless fingerprinting was one of the hottest areas of biometric development even before the discovery of the novel coronavirus in 2019, along with other contactless biometric technologies in general. The reason for this is that it allows for great scalability by taking advantage of existing infrastructure such as the internet-enabled smartphones that we all carry. The adoption and therefore further development of these technologies has only accelerated during the pandemic. The heat was generated by a series of advances in fingerprint image acquisition using conducive mobile phone camera systems, image processing techniques resulting in high precision matching performance with fingerprints and legacy systems, widespread adoption and recognition from standards bodies.

When we talk about contactless fingerprinting, we mean the acquisition and/or verification of fingerprints without placing the fingers on the type of device that we are all used to, for example at border control. Until recently, for a number of reasons, placing your finger(s) on such a reader was the only way to properly acquire or verify a fingerprint.

The potential for contactless fingerprint capture technology, particularly via mobile phones, includes a complete reconfiguration of the dominant national identity registration and verification model, Tech5 Co-founder and CTO Rahul Parthe recounts Biometric update in an interview.

This reconfiguration would involve the gradual replacement of a whole generation of acquisition devices dedicated to contact fingerprint biometrics. Their replacement would only require software and mobile phones, and the same smartphones will also serve as face capture devices.

“We all carry these awesome computers in our hands,” says Parthe. “It’s a perfectly packaged hardware device that’s ideal for any capture technology. Smartphones are powerful computing devices at the edge, with a nice built-in camera with autofocus and flash. And now the phones are also equipped with multiple cameras which can help in better estimation of focus and depth. This allows users to take pictures of their fingers and the software takes care of the rest. I would just like to point out here that we are talking about using the phone’s camera to capture biometrics and using a smartphone to replace a dedicated reader. We’re not talking about the in-display fingerprint acquisition that we’re all familiar with on many devices, which is the way to access the device itself. »

The recent state of the art

The technology is maturing: contactless fingerprinting has achieved high accuracy, such as with contact-based biometric systems when using multiple fingers. A preliminary test conducted by the US National Institute of Standards and Technology (NIST) in early 2020 proved the same.

Its interoperability with fingerprints captured using contact fingerprint scanners has also been confirmed by NIST, informing guidance issued by the agency last June.

Getting to this point required innovation in capture technology, says Parthe. Unlike a dedicated touch device, fingerprint images are captured at varying distances, requiring precise scale correction to be built into software.

“There’s a lot of machine learning going on with the capture itself,” says Parthe. “To detect the fingerprint, then once you’ve detected it and segmented it, you need to convert it into a format acceptable to, say, the national ID solution provider’s legacy system.”

Images should be adjusted to match reference patterns captured with contact-based systems, with 500 dpi, grayscale and specific contrast characteristics. Only then can biometric data be processed in the same way.

According to Parthe, contact-based fingerprint scanners have advanced significantly over the past decade, with smaller and somewhat portable devices hitting the market with high accuracy. However, they still involve a significant investment and require a secondary computing device, such as a laptop or tablet, which further increases the overall cost. Additionally, they limit scalability and require maintenance.

NIST’s guidance should also lead to additional documentation and possibly new standards for contactless fingerprints.

A new generation

Before the pandemic, contactless fingerprint solutions were already rapidly gaining popularity with banks and for know-your-customer (KYC) and remote onboarding applications.

“The main use cases are where people want to verify themselves against a reference biometric identity known to themselves and perform 1:1 verification,” says Parthe.

Adoption of contactless fingerprint biometrics is now shifting from banks to governments.

Governments are very cost-conscious and reluctant to invest in expensive new scanners, but they also have a mandate, increasingly shared by banks, to reach all citizens. Contact-based biometric scanners typically operate in fixed deployments, making it difficult to fulfill this mandate. These systems are also often prevented from connecting the last mile to remote citizens or customers with limitations in internet connectivity and other infrastructure.

The technology best suited to achieve these goals, says Parthe, is provided by the mobile device-based approach. The software now offers similar biometric accuracy to dedicated scanners, he says, with convenience and scalability that opens up new applications.

The software solution is easy to integrate and use, he says, and the reduced maintenance compared to hardware-based approaches further adds to the cost advantage, further improving scalability.

“Especially when you’re talking about contactless fingerprinting, the fundamental requirement is that someone has a baseline database,” Parthe explains, “that’s why governments that have already collected fingerprints as part of their national ID databases are those who are quick to jump on the use of contactless technologies.

Shortly after this conversation, Ethiopia announced a trial of Tech5’s technology for its national ID system.

The pandemic has provided contactless fingerprinting technologies with “a boost for adoption” according to Parthe, due to concerns over the potential for “superspreading” of surfaces intended to be touched by many different people. , like traditional biometric scanners.

The T5-AirSnap Finger solution, launched by Tech5 in September, offers an alternative via an SDK that is easily integrated into applications.

The possibilities

The use of software and cell phones removes barriers that have prevented the deployment of biometric technology in various situations, Parthe points out.

“It basically delivers all the necessary and useful features you want in an acquisition technology.”

Parthe would not be surprised to see governments using technology to enroll citizens in national ID databases in the near future, he says.

As this happens, he predicts that contactless technology will soon begin to replace contact scanners. There is also a significant development in the field of fingerprint matching using neural network (NN) based algorithms which have higher tolerance to scale and quality variations. The combination of the two will dramatically increase the efficiency of these large programs, making contactless capture technology an easy choice.

Tech5’s contactless fingerprint offering is called T5-AirSnap Finger. Another contactless capture technology available from Tech5 is called T5-AirSnap Face, and the company’s technology roadmap also includes the development of T5-AirSnap Iris – again for use on a standard mobile phone. Additionally, since voice biometrics capturing is the most widely available capture modality for mobile phones, they can effectively provide a complete multimodal biometric capture solution, Parthe claims.

For national programs that have traditionally involved SLR cameras, iris scanners, fingerprint scanners, laptops and more, in some cases deployed in remote island chains, cell phones could be a powerful alternative.

Parthe notes that NIST’s active involvement in defining potential certification standards shows that it believes in the longer-term potential of contactless fingerprint biometrics.

Meanwhile, Tech5’s T5-AirSnap Finger is already serving a growing number of customers for an ever-widening range of applications.

Article topics

biometric enrollment | biometrics | state-of-the-art biometrics | contactless | fingerprint readers | machine learning | research and development | Software Development Kit | smartphones | T5-AirSnap Finger | TECH5

Share.

Comments are closed.