How facial recognition technology works in backend?

By Srikanth
7 Min Read
Shaun Moore Co-Founder and CEO of biometrics firm Trueface

Facial recognition isn’t as simple as taking two pictures and seeing if they match.  Facial recognition algorithms create a mathematical representation of a human face (called a face template) and do so by identifying landmarks on the face such the nose and eyes and calculate the distance between those landmarks.


 It is at its basic form computing geometry.  These equations represent the face, which is then compared to other mathematical representations to find a match or a similarity score.  

Every human being has its equation or mathematical representation, which is unique to them but also uniquely ingested by the algorithm.  

It is not a one-sized fit all meaning you cannot take a face template from one company, and use it to identify that person running another company’s software positively. Face templates cannot be transferred across companies or algorithms, which is an essential aspect of this technology.   

We are witnessing an exponential increase in demand for a variety of different use cases of face recognition.  Before getting into the use cases, it’s essential to understand the three ways that face recognition is being utilized today.  

1. Personal Access Control (Opt-In). Your phone to gain access to emails, apps, and so on. (This is referred to as 1 to 1 Matching)  

2. Public Access Control (Opt-In). Services like Global Entry, Access to Sports Arenas.  (This is referred to as 1 to few) 

3. Public Monitoring. This is where law enforcement is looking to expedite their information gathering when forensically analyzing crime footage.  (This is referred to as 1 to N or 1 to many).  

We have seen adoption across police departments as a forensic tool, but we are unaware of any department using facial recognition in real-time.  Also, we are working with companies to provide face recognition as a credential for access control to corporate offices and construction sites.  Face recognition allows for the more efficient flow of people as well as more security for the individuals inside the building.  Also, face recognition is being used to authorize individuals to setting up bank accounts and making mobile transactions.

Face recognition is being used to expedite the boarding process on planes, the embarking process on cruise ships and to identify missing children.

Misinformed in terms of using facial recognition?

Face recognition is a single component of more significant advancement in technology. As our identities continue to digitize, we need methods and solutions to protect them and authenticate them. Passwords are too easy to hack, and biometrics have been the permanent solution for the last ten years. I am not suggesting that facial recognition as a single input is the end all be all solution but pairing it with social information or behavioural information certainly makes it more challenging to comprise an identity.

The debate that society is having is purely about a surveillance state and begs the question – should the government have the tools to ‘monitor’ everyone in real-time.  The fact is, this is not how the technology is being deployed, and the government isn’t watching every street block scanning faces.  

This technology is meant to aid the already challenging job of law enforcement, in identifying someone who has already committed a crime.  Instead of manually scanning through days of footage, face recognition can provide another source of information or point of reference.  It is not built to ‘be the decision’ it is to be used as a tool in a toolbox.  

How conversations, when innovation occurs, is understandable but will it hinder progress forward to ban such technologies?

I think Professor Juma does an incredible job defining the apprehension with the adoption of this type of technology. I recently visited China to understand more about how they perceive the 400 million face recognition cameras being installed and the new police glasses running face recognition in real-time in train stations. The overall sentiment was positive, to my surprise.

Airports are one of the most stressful environments for humans and implementing face recognition is gaining momentum. We see the value in eliminating lines and providing increased security. When we can start to wrap our heads around how face recognition can be used to find a missing child or a trafficked individual people immediately see the benefits.

All it takes is one instance where face recognition helped to catch a bad actor before the action, and I think our mindset will start to shift. The efficiency it would provide to a factory with 5000 workers trying to enter at the same time is unparalleled, and it’s important to remember that facial recognition isn’t the only solution, it is the best solution given our current infrastructure.

When we compare it to the alternative, it is significantly safer than a key card which can be lost or transferred and is far more efficient than having to go through the process of lining up to swipe a badge. As a product of face recognition, we also have access to a digital trail of individuals who have entered in the case that something terrible happens.

Moving in the direction of banning this technology will put our society at a significant disadvantage to the rest of the world.  Being fearful or a lack of understanding of advancement in technology is not a reason to outright ban it.  We must have an informed discussion about the limitations and create regulations that do not hinder progress.

Contributed by Shaun Moore, Co-Founder and CEO of biometrics firm, Trueface,

Share This Article
Passionate Tech Blogger on Emerging Technologies, which brings revolutionary changes to the People life.., Interested to explore latest Gadgets, Saas Programs
Leave a comment

Leave a Reply

Your email address will not be published. Required fields are marked *