AI Computer Vision
3D body (skeletal) tracking middleware
Facial and body recognition library for server, mobile and embedded solutions
Scalable API for facial
and body recognition
Advanced face liveness detection for digital onboarding and KYC
AI video analytics platform
for human activity recognition
Edge AI hardware
for face and body tracking
3DiVi Inc., founded in 2011, is one of the leading developers of AI and machine learning (ML) technologies for computer vision.
3DiVi Blog

Facial Recognition. Three common pitfalls, and how to fix them. Pitfall #1

Key indicators such as recognition accuracy, along with a decrease in operating costs, are becoming the main parameters by which, the effectiveness of face recognition systems is measured.

Mikhaylo Pavlyuk, CCO, 3DiVi Inc. explains what challenges operating experience brings in facial recognition systems. Including those that are not obvious at the start of the project. Let's take a closer look at three of them. Perhaps fixing them can make your processes more efficient, and your business more successful.

Face Recognition Pitfall #1

Mixed photo quality in the database makes a promised recognition rate unreachable.


We do not understand what quality photos we have in the comparison database, and we cannot adequately build decision thresholds “yes / no”. Thresholds are set either "by eye", or based on some general recommendations.

The result is not optimal operation of the recognition system, a multiple increase in errors of the first and second kind. Additional cost for processing erroneous comparisons.

Estimated losses

The cost per mismatch incident is highly dependent on the business case.

If we talk about ACS, then this is the time spent by the security service on re-identification in case the correct person is not missed, or the time and effort spent on localizing the consequences of the penetration of a “stranger”.

If we take a more complex case - identification during a banking transaction, then this is the price of a possible loss of a client if we do not recognize him, or the admission of a stranger to the user's bank accounts.


Let's consider a business case of bank application login through biometrics.

According to statistics, the average number of logins per user is 19 to 25 times a month. Take, for example, a bank with a base of 1 million customers. We receive at least 19 million identifications per month. The best NIST algorithms for the highest quality Visa Photos dataset show FNMR = 0.0006 at FMR = 0.00001

In practice, having a dataset that is not quality checked, we will get at best FNMR = 0.003 with FMR = 0.00001.

This is more than 45,000 "extra" incidents per month. If each incident costs us an average of $1 (which is a grossly underestimate), then we get from 450,000$ per year of "extra" costs**. This amount is quite commensurate with the annual cost of owning a biometric system.


Using the photo quality control algorithm, we build a procedure for regularly checking the dataset. We remove and replace low-quality photos.


Cost savings commensurate with the cost of ownership of a biometric service, or 0.002$ per 1 transaction.

Go to Face Recognition Pitfall #2 >