Follow Us:
Friday, September 17, 2021

Andrei Telenkov: ‘India key market for facial recognition tech; hope to grow smart city use cases’

NtechLab sees India as one of the priority markets for video surveillance and facial recognition technology.

Written by Pranav Mukul | New Delhi |
September 8, 2021 3:00:57 am
NtechLab’s CEO Andrei Telenkov

Russian facial recognition technology provider NtechLab, which recently announced a contract with Indian Railways to implement its technology at 30 stations across Gujarat and Maharashtra, sees India as one of the priority markets for video surveillance and facial recognition technology. NtechLab’s CEO Andrei Telenkov, in an interview with Pranav Mukul, talks about the expanding use cases and how India is leveraging the technology. Edited excerpts:

How do you see India as a market?

We definitely see India as one of the key markets, as part of our international expansion. We are already present in India, and have several use cases of our product, but the one we made public was the one with Indian Railways. In terms of size, population and how well we can cooperate with partners here, India is known internationally for very good expertise in engineering and IT. We are hopeful that our portfolio of use cases will grow — through expansion with current clients — and hopefully we can enter different segments like smart city, retail, and banking. India is definitely a top priority for us, and this year we have hired dedicated people who will work exclusively with India.

What are the various use cases possible in India?

We see a huge number of scenarios and use cases that can be set up. In Russia, we have a Moscow Safe city, which we believe is the largest project worldwide if you don’t count China. Moscow has 1,70,000 cameras and we do not do only facial recognition but different kind of video analytics. Of course it’s about faces, that is how we started, but now we have expanded into different technologies. We can detect people by silhouettes, we can detect and recognise cars even with no number plates. We can implement smart solutions on video cameras. We also can recognise weapons in police cases, if someone is using a weapon in front of the camera. The number of cases is growing, growing and growing and we hope that we will implement these in other markets as well — India being a priority market. Of course, law enforcement is a key scenario but there are many other cases for example, cities use video analytics to analyse the flow of people — how many people are on the street, how many are waiting for a bus, etc.

Are there any India-specific challenges that you faced?

In terms of technical challenges, there was a very interesting challenge for our R&D team. India was a very hard case in terms of number of faces. The client was Indian Railways, which is arguably the world’s busiest railways. In some geographies, when you do a project of this kind, the average video will have 10 faces, but in India, in one frame, the average number of faces was 50. That was a huge technical challenge to detect and recognise all those faces.

Is it possible for clients to use your technology beyond the stated purpose?

Absolutely, it is very possible. We often come across this case. Many of our clients in Russia, they start with a blacklist — that are the people they don’t want to see in their establishment. These people are suspected to be criminals by law enforcement, our clients use our technology to get alerts about these people if they enter the premises. After the first step, they will continue to use our system for different scenarios, other use cases. As a company, we are very open to what the client puts in front of us and we check whether their problem can be solved with video analytics.

Can a client, for example Indian Railways, expand its reference database that it uses for facial recognition?

This depends on the structure of the contract. Sometimes we are flexible, where we can give unlimited licence, which will be unlimited in terms of number of faces it can recognise. But it varies from contract to contract. Technically, it is very possible. We can add to and go through databases very fast. For example, one of our clients, which is an internet company, has a database of 1.5 billion faces and we can search a face through this huge database in less than 0.3 seconds.

Does a company like NtechLab build safeguards so the clients don’t use it to violate privacy of citizens?

It is really up to the client how they use it. From our experience, the majority of the clients are established institutions, which have their compliance systems in place. From what we know, the clients are very careful because this is very sensitive information. We don’t get the access to the database, we just provide the technology and the know-how but we cannot comment on each client because we are technology providers. For example, Indian Railways is a reputable client and this has extremely low chance of happening. We don’t know how the system is used precisely, we provide the technology and it’s up to the client to compile a database and check on this database.

📣 The Indian Express is now on Telegram. Click here to join our channel (@indianexpress) and stay updated with the latest headlines

For all the latest Business News, download Indian Express App.

  • The Indian Express website has been rated GREEN for its credibility and trustworthiness by Newsguard, a global service that rates news sources for their journalistic standards.