The role of facial recognition technology in protecting people, enterprises, and society in SEA

By Abhijit Shanbhag

Facial recognition (FR) capability can be divided into two types: FR-1 and FR-N.  FR-1 identifies in a binary way if a person is the hypothesized one (mainly for authentication) and FR-N is to detect if the person is from a database of a certain number of faces. With FR-N, the size of the database can typically range from a dozen, as with a small enterprise, to millions of people in a large city.

Facial recognition is becoming an invaluable tool for many applications involving people, cameras, and public places. AI technology has benefited from major advancements in recent years, reaching a 99.97 recognition accuracy level, according to the Centre for Strategic and International Studies (CSIS). Nonetheless, in most real-world situations, the precision has been lacking, with accuracy markedly lower among most CCTV in public places.

Amid the ongoing pandemic, however, FR has seen its employment increase on a wide scale. Its use in workplaces across Southeast Asia is significant, as the inherent contactless nature of FR makes it a highly desirable alternative to fingerprint scanners and even RFID cards for office access and/or attendance monitoring. Many buildings, construction sites and enterprises within Singapore, in particular, are now beginning to use FR-N for Access Control and when applicable, for their attendance management by leveraging CCTV installed at entrances. Full-featured AI-powered solutions may also monitor mask compliance and social distancing as well as attendance management and various other video analytics to improve security, safety and streamline office operations. Many malls across Southeast Asia are now pursuing such methods of leveraging this kind of technology.

For schools and higher education institutions, Attendance Management is one among many important elements of this technology, including various other video analytics which improve security and safety in the campuses and hostels. One of the top universities in Singapore is currently trialling the use of different attributes within Facial Recognition such as gender and age group, to obtain intrusion alerts within sensitive zones of the University.

Similarly, Singapore’s Changi Airport already leverages FR-1 at the immigration checkpoints, and also at automated immigration clearance gates which can enable them to be fully unmanned. Airports across Southeast Asia are increasingly trialling AI-powered video technology in order to identify consumer sentiments and overall experience within the airports. Ports in regions such as Philippines and Malaysia will also be deploying FR-N as part of their staff and visitor management.

Meanwhile, the ride-sharing industry has adopted facial recognition to bring an added layer of verification and security to rides. Grab, a ride-hailing company based in Southeast Asia, has also incorporated facial recognition technologies to accurately identify the right drivers and passengers for each ride.

The banking industry is also finding increased use for FR-1. OCBC now allows users to access their bank balances at ATMs simply by typing in their NRIC and facing the camera at the ATM. Adoption is at such a rate that we predict public announcements from some of the other banks within this year.

FR-N, on the other hand, is actively being piloted for various large events slated this year in Indonesia and Singapore. Participants simply upload their picture onto a portal and the FR-N at the registration kiosk will be able to identify the person, and the system thus registers attendees without requiring face-to-face interactions. A direct impact of pandemic-learning, this helps reduce the amount of physical contact between event staff and attendees and minimise touchpoints at registration kiosks. CCTV within the event site would then issue alerts in the case of breaches in safe-distancing rules or mask compliance.

In Thai retail and fast food chains, FR technology is already beginning to increase in prominence. As FR allows retailers to capture shoppers in-store, it provides an effective way to monitor customer satisfaction as well as the popularity of certain goods. This allows for actionable reports to be conducted by on-ground retail operators. Similarly, various customer experience metrics from entry to pick-up and exit can be obtained leveraging FR for fast food restaurants.

Social concerns regarding CCTV are largely related to the monitoring of private pursuits. Within an FR system however, the monitoring in existence is designed to be as regulated and safe as a physical security presence, such as that of security guards. The key is responsible and regulated use. FR technology can and should protect people, enterprises, and society.

A key protective use of facial recognition is on intrusion systems which can come with the feature of enabling individual blacklists and whitelists for different locations and entry points, thus preventing any unidentified individual from entering the premises and eliminating trespassing or intrusion. In public spaces, this can easily be expanded to prevent people who are not compliant with mask usage from entering the complex. Indeed, there are currently different trials underway across Southeast Asia for this reason.

Responsibly used, FR Technology has the potential to become a valuable and protective tool across Singapore and Southeast Asia. Facial analytics are set to prevail and evolve alongside that of cameras and other video sensors. While the technology will likely meet challenges, the value of FR at its core is evident.

Abhijit Shanbhag is the founder and CEO of Graymatics.