By Use Cases
By Industry
3DiVi Inc., founded in 2011, is one of the leading developers of AI and machine learning (ML) technologies for computer vision.
Let's talk business
Just fill in the form and we will contact you shortly
On-premise license request
Just fill in the form and we will contact you shortly
Your request has been successfully sent. We'll get in touch shortly.
THANK YOU!
Let's talk business
Just fill in the form and we will contact you shortly
When AI Makes Mistakes: Key Facial Recognition Errors and Strategies to Minimize Them
Even the most advanced face recognition systems make mistakes. The question isn’t if — it’s why, and how often.
Whether you're integrating FRT into mobile apps, KYC flows, or access control systems, understanding how errors happen (and what impacts them) is crucial for building reliable, high-accuracy solutions.
Whether you're integrating FRT into mobile apps, KYC flows, or access control systems, understanding how errors happen (and what impacts them) is crucial for building reliable, high-accuracy solutions.
Two Most Common Facial Recognition Errors
False Rejection Rate (FRR):
A real user is wrongly denied → Leads to frustration, drop-offs, failed onboarding.
False Acceptance Rate (FAR):
An imposter is wrongly accepted → Leads to security breaches and compliance risks.
These are measured via a similarity score threshold. Tighten the threshold = fewer imposters get through, but more real users get blocked. Loosen it = smoother UX, but higher risk.
A real user is wrongly denied → Leads to frustration, drop-offs, failed onboarding.
False Acceptance Rate (FAR):
An imposter is wrongly accepted → Leads to security breaches and compliance risks.
These are measured via a similarity score threshold. Tighten the threshold = fewer imposters get through, but more real users get blocked. Loosen it = smoother UX, but higher risk.
The default recommended similarity score threshold is 0.85. At this threshold, the algorithm achieves:
This balance ensures extremely low chances of unauthorized access while maintaining high acceptance for legitimate users.
- False Acceptance Rate (FAR): 0.0000009919
- False Rejection Rate (FRR): 0.0075107813
This balance ensures extremely low chances of unauthorized access while maintaining high acceptance for legitimate users.
Real-World Test: How Good Are Face Recognition Algorithms at Spotting Look-Alikes?
Since 1999, Canadian photographer François Brunelle has been working on his project "I'm Not a Look-Alike", capturing portraits of unrelated people who look strikingly alike — so much so that they could easily be mistaken for twins.
It's a compelling case for evaluating how well face recognition algorithms can distinguish between look-alikes where even humans might be fooled.
Example 1.
It's a compelling case for evaluating how well face recognition algorithms can distinguish between look-alikes where even humans might be fooled.
Example 1.
Score is 17. FAR=0,019458; FRR=0,003017. Verdict: Different people.
Example 2
Example 2
Score is 23. FAR=0,007506; FRR=0,003363. Verdict: Different people.
Example 3
Example 3
Score is 14. FAR=0,053261; FRR=0,002691. Verdict: Different people.
And for a clearer visualization — here's a comparison of individuals taken from different lookalike pairs.
And for a clearer visualization — here's a comparison of individuals taken from different lookalike pairs.
Score is 15. FAR=0,034590; FRR=0,002873. Verdict: Different people.
These results show that even when two faces appear strikingly similar, face recognition algorithms can still distinguish between them with high accuracy — far outperforming human judgment in such cases.
But here’s the catch: accuracy isn’t guaranteed. It still hinges on a few critical factors — like quality and diversity of training data, the underlying model architecture, and the real-world conditions.
These results show that even when two faces appear strikingly similar, face recognition algorithms can still distinguish between them with high accuracy — far outperforming human judgment in such cases.
But here’s the catch: accuracy isn’t guaranteed. It still hinges on a few critical factors — like quality and diversity of training data, the underlying model architecture, and the real-world conditions.
Strategies to Minimize Facial Recognition Errors
Despite impressive results, face recognition performance still depends on several key factors that must be addressed to reduce error rates:
Training Data Quality: The more diverse and extensive the data used to train an algorithm, the better it performs in recognizing different types of faces (varying in age, race, and gender). High-quality and well-balanced datasets significantly boost accuracy.
Model Architecture: Modern face recognition algorithms—especially those based on convolutional neural networks (CNNs)—achieve high accuracy thanks to deep learning and the ability to detect subtle facial features. Nearly all leading market players use complex neural architectures for precise facial identification.
Image Quality: Just like with human recognition, image clarity is critical. Sharp images with good lighting significantly improve recognition accuracy, while blurred, dark, or partially obscured faces can challenge the system (Tip: Tools like 3DiVi QAA can pre-filter low-quality images before they hit your system).
Appearance Changes: Contemporary algorithms are capable of recognizing faces despite minor appearance changes (e.g., hairstyle, makeup, or glasses). However, drastic alterations can make recognition more difficult.
Cross-Race Effects: Just like humans, algorithms may be biased depending on the data they were trained on. If the training set lacks ethnic diversity, algorithms may struggle to recognize underrepresented groups. Still, even accounting for this effect, modern systems make significantly fewer mistakes than humans in similar conditions.
Training Data Quality: The more diverse and extensive the data used to train an algorithm, the better it performs in recognizing different types of faces (varying in age, race, and gender). High-quality and well-balanced datasets significantly boost accuracy.
Model Architecture: Modern face recognition algorithms—especially those based on convolutional neural networks (CNNs)—achieve high accuracy thanks to deep learning and the ability to detect subtle facial features. Nearly all leading market players use complex neural architectures for precise facial identification.
Image Quality: Just like with human recognition, image clarity is critical. Sharp images with good lighting significantly improve recognition accuracy, while blurred, dark, or partially obscured faces can challenge the system (Tip: Tools like 3DiVi QAA can pre-filter low-quality images before they hit your system).
Appearance Changes: Contemporary algorithms are capable of recognizing faces despite minor appearance changes (e.g., hairstyle, makeup, or glasses). However, drastic alterations can make recognition more difficult.
Cross-Race Effects: Just like humans, algorithms may be biased depending on the data they were trained on. If the training set lacks ethnic diversity, algorithms may struggle to recognize underrepresented groups. Still, even accounting for this effect, modern systems make significantly fewer mistakes than humans in similar conditions.
Accuracy Benchmarks You Should Know
- NIST FRVT (Face Recognition Vendor Test): Top-tier algorithms in NIST rating now exceed 99.9% accuracy in 1:1 face comparisons under ideal conditions — surpassing human performance. In 1:N identification tasks (e.g., searching a face in a database), accuracy also remains high but depends on database size and image quality.
- Real-time face recognition: In challenging environments (e.g., outdoor surveillance), accuracy can drop. However, advanced algorithms still achieve over 95% accuracy, particularly when improved image processing and adaptive techniques are applied.
3DiVi algorithms, benchmarked by NIST, show world-class performance with a False Match Rate (FMR) of 0.000001 and False Non-Match Rate (FNMR) of 0.003 at the default threshold.
Bottom Line
Modern face recognition algorithms are pushing the boundaries—reaching near-100% accuracy and outperforming humans in controlled settings. But it’s not without limits — bias in training data, false match rates, and poor image quality can still get in the way.
Want to test it yourself? Try a live face recognition demo (based on 3DiVi’s algorithms) directly on 3divi.ai.
Want to test it yourself? Try a live face recognition demo (based on 3DiVi’s algorithms) directly on 3divi.ai.
