COVID-19 pandemic VS biometrics: challenges and perspectives

CEO of BIOSMART, Alexander Dremin, talks about how biometric technologies can be useful, what happened to the industry during the COVID-19 pandemic, and how safe it is to store your biometric information in a database.

The first ever biometric system 

The effectiveness of identification by biometrics was convincingly proved in the middle of the XIX century. The man who is now considered the founding father of biometrics, British officer William Herschel, who served in the colonial administration of Bengal, first used fingerprints to recognize a person back in 1958.

On duty, he supervised the payment of salaries to Indian soldiers. The Indians realized that the Europeans could not distinguish their faces well, and they shamelessly took advantage of this: after receiving a salary once, they returned and claimed that they had not received money, or sent friends or relatives. To prevent fraud, Herschel created the world's first database of biometric information: all soldiers first left their fingerprints on a list with names, and when they received money, they sealed the receipt with their fingerprint.

Advantages of biometric systems: versatility, security, and scalability

Biometric identification is still one of the most reliable ways to confirm a person's identity. 
You can't forget your fingerprint or palm vein pattern at home, lose it, or pass it on to a colleague. Modern biometric devices make it impossible to cheat with the help of technical means of silicone dummies. A high-quality biometric system from a responsible developer is more reliable than any other ACS. Our readers and terminals being used by Ministry of defense, for example, speak for themselves.

Sometimes biometric systems are impressive in their scale. Since 2016, we have been implementing a project to implement the ACS and worktime tracking system in X5 Retail Group. Thousands stores in a single database — 900 thousand employees! 3.6 million authentication events on a monthly basis. There are no analogues of such a project.

At the same time, compromising biometric data is extremely unlikely, because a person's biometric information is stored in a database in the form of a mathematical model. The biometric scanner does not work with the image of a biometric identifier, but with its digital template — a set of individual features. It is technically impossible to decrypt a template and restore a full-fledged image of a face, fingerprint, or vein pattern from it. This is the world standard for the biometric industry.

Biometrics in the age of the pandemic: perspectives and pitfalls

The COVID-19 pandemic has given the biometric industry a difficult challenge.

On the one hand, in the context of the pandemic, many previous systems have lost their former effectiveness. Let’s take solutions for face identification as an example. Recently the national Institute of standards and technology (NIST) of the United States conducted a series of studies on how well facial recognition algorithms work in mask mode. NIST specialists tested 89 algorithms created before the start of the pandemic on 6 million photos in verification mode. As a result, it turned out that algorithms that normally recognized faces with an accuracy of 99.7% are wrong on average with a probability of 20% to 50%. This is little better than coffee fortune-telling. 
On the other hand, biometric technologies are booming among consumers during the pandemic. Companies that previously did not dare to use biometrics in ACS and worktime tracking finally realized its advantages, such as hygiene, no contact, speed and convenience of recognition. As a result, the simplest devices for biometric identification (in fact, tablets with a camera), thermal imagers and "coronavisors" flooded into the market.

The natural result of widespread attempts to introduce cheap hardware and software was disappointment in the technology itself. Consumers were convinced that such devices are unreliable, packed in a flimsy case, and difficult to integrate into ACS. In addition, the software trained on the faces of people of one ethnic group does not cope with the identification of the other, and the security of storing biometric data raises a lot of questions.

The saddest thing here is that by introducing cheap, dubious equipment developed by one-day companies, consumers make a conclusion about the technology as a whole, whereas in reality, real high-quality biometrics is a very complex branch of knowledge and it has nothing to do with this kind of crafts.

The pandemic clearly showed that in order to make a reliable biometric device that is effective in a pandemic, you need first of all experience and deep knowledge in the field of neural network programming. We have been working on the market since 2006. Today, the BIOSMART R&D group has 25 highly qualified programmers who are graduates of leading universities. Even with such impressive resources, we understand how difficult it is to create an algorithm that will reliably and stably recognize a person, guarantee the security of the system and eliminate the very possibility of theft of biometric and personal information.

BioSmart Quasar terminal — a comprehensive anti-COVID solution for face identification

One of the company's anti-COVID know-how is the BioSmart Quasar biometric terminal — a multifunctional biometric device that recognizes a person by face and an RFID card.
The terminal's brain is a 6-core ARM processor which solves complex tasks using a convolutional neural network, an algorithm modeled on the visual cortex. The convolutional network is capable of deep learning — passing through a large array of examples, it learns to detect the distinctive features of objects, finds relations between them, and applies the experience to detect new objects.

Since the beginning of the pandemic, we have been working to train our BioSmart Quasar terminal to work in mask mode. We generated a database of masked faces by applying three types of masks to photos of people. We ran hundreds of tests. We debugged and improved the algorithm dozens of times, until we were convinced that it can be released to the big world.
The devices successfully identify people in medical masks by the upper part of their face. Built - in anti-spoofing algorithms do not allow you to deceive the device using photo and video images. An access control system based on BioSmart Quasar terminals increases the security level of the government complex and provides contactless access to the building, which reduces the risk of COVID-19 infection.

The PALM JET reader — a comprehensive anti-COVID solution for identification by the veins of the palm

At BIOSMART we develop biometric devices ourselves and write algorithms for identifying a person based on biometric indicators. One of our flagship inventions is palm vein scanning technology in the multispectral IR range. The technology is officially patented in Europe and the USA.

We have created a number of devices based on this technology. Our latest development — the PALMJET — is the device that everyone has been dreaming about since the beginning of the pandemic. This is the fully contactless palm vein reader with the function of remote wrist temperature measurement. 

A hygienic, compact and versatile solution suitable for both business and home use. The PALMJET based corporate ACS is an effective comprehensive anti-COVID system that eliminates the need for employees to touch the same locks, turnstiles, or buttons to open doors. PALMJET is perfectly protected against forgery — it is impossible to deceive it with a silicone dummy or a photo. 
We hope that the effectiveness of the device will soon be appreciated by consumers all around the globe.