26 Sep Facial recognition leaders

The use of facial recognition in Russia has already seen more than 50,000 crimes solved, and an 85 per cent drop in burglaries and car thefts. So what can the Middle East learn from this pioneer of the technology? Andemir Bizhoev, Head of Sales, NtechLab, explains.

Various facial recognition projects are currently being implemented in 30 regions across Russia. Moscow has been a pioneer in the development of this technology and has been using facial recognition since 2017. In just five years, the technology has reached 99.99 per cent accuracy.

More than 200,000 video surveillance cameras have been installed on the streets, in yards and at entrances of residential buildings in Moscow. Approximately 125,000 of these cameras are programmed to recognise faces. So how is Russia ensuring it sets the pace for the technology?

The next step

Now that the face recognition accuracy (up to 99,99 per cent) and speed (less than 0.5 seconds) are so high, it would be appropriate to ask how to develop the technology further. The battle for fractions of seconds and tiny increments in accuracy percentage will surely rage on, but the existing results already allow the majority of complex tasks to be solved with billion-entry datasets, covering all areas of application, both for public safety, and business security. So what’s next?

NtechLab engineers started their search for the answer a few years ago, which resulted in the creation of silhouette (attributes) recognition algorithms. Tracking by silhouette — which is also a unique set of human features — allows to detect and instantly count almost any number of people in the tracking zone, even with their backs turned to the camera. It is also capable of tracking their routes within the city.

Integrating algorithms

In the early stages of video analytics development each algorithm was created and used on a stand-alone basis. This means each application is separate. For instance, face recognition is in one system, car recognition in a different product, and the ability to respond to specific situations requires another system. Presently, companies are striving to create integrated products by combining several algorithms into a single solution. As a result of this the algorithm integration of different analytic processes are connected with each other, leading to new opportunities for businesses.

Software developers, for instance, are combining face recognition with recognition of silhouettes, cars, and other objects. This is complemented with action recognition in multi-object video analytics products, in which cameras are configured to recognise different object types, and a single camera can process several different types of objects at once.

Tackling bias

With the emerging anti-discrimination trends and the proliferation of video analytics around the world, companies are increasingly focusing on ensuring that algorithms work equally well for different ethnic groups the world over.

This is achieved by carrying out a set of tests for each individual ethnic group and ensuring that the accuracy is the same in all cases before releasing any video analytics algorithm into the market. At NtechLab each new algorithm undergoes these tests automatically. If there are problems detected, they are dealt with promptly.

New applications

In Russia, facial recognition has proved its worth and efficacy across multiple scenarios. In addition, the world’s largest pay-by-face project was implemented in the Moscow metro. Seven million people a day use the transport system and passengers can pay for travel using facial biometrics. New scenarios for the use of facial recognition are emerging at the intersection of security and developing safe urban environments because these technologies simultaneously solve several problems at once.

Russia’s facial recognition revolution in numbers:

• After installing 500 cameras across Moscow ahead of the 2018 FIFA World Cup, almost 200 wanted persons were recognised in real-time and detained.
• In 2020, the use of facial recognition system helps solve 5,085 crimes in Moscow – including apprehending the thief who stole a million-dollar painting from the Tretyakov Gallery within 24-hours.
• In 2021, the technology helped solve 7,131 crimes with a further 3,491 thefts uncovered.
• Between 2017 and 2022, facial recognition in Moscow helped the number of burglaries and car thefts drop by more than 85 per cent, and robberies by 75 per cent.
• Moscow Metro got its own face recognition system in September 2020. As well as helping to detect and detain more than 5,000 wanted persons it has also helped find missing people.