With the proliferation of embedded and physical cameras and a continuing exponential increase in computing power, facial recognition (FR) is becoming an important tool for many applications involving people and cameras.

There have been significant advances in leveraging some of the latest in Artificial Intelligence technology for facial recognition, which has also been enabled by advances in technology. This has come about as facial recognition systems have nearly absolute precision in ideal conditions, reaching a 99.97 per cent recognition accuracy level, according to research published by the Centre for Strategic and International Studies (CSIS).
However, it has to be noted that in most real-life scenarios, the conditions are far from ideal. Accuracy can commonly be lower even with more advanced algorithmic techniques – especially with regard to CCTV in public places.

Facial recognition capability can be divided into two types: FR-1 and FR-N. FR-1 identifies in a binary way if a person is the hypothesised 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.

Given the current pandemic, 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, but also within Southeast Asia (SEA) are now beginning to use FR-N for Access Control and when applicable, for their attendance management by leveraging CCTV installed at entrances.

They can also have a full-featured AI-powered solution on these same CCTVs, which may include from mask compliance and social distancing to attendance management and various other video analytics to improve security, safety and streamline office operations. There are a number of malls within SEA which are now closely looking into leveraging this technology.

Schools and higher institutions of learning, including universities have shown strong interest to leverage similar solutions for attendance management, apart from bringing in various other video analytics to improve security and safety in the campuses and hostels.

One of the top universities in Singapore is currently trialing the use of different attributes within facial recognition such as gender and age group, to obtain intrusion alerts within sensitive zones of the university.
Within the transportation segment, Singapore’s Changi Airport already leverages FR-1 at the immigration checkpoints, and also at automated immigration clearance gates which are expected to be fully unmanned. Increasingly, we are seeing more airports within SEA beginning to trial AI-powered video technology to identify consumer sentiments and experiences within the airports.