(Imagen 4)
In a recent post on Biometric Update, “Why retail needs biometrics – the cameras aren’t working,” Professor Fraser Sampson, former UK Biometrics & Surveillance Camera Commissioner made several points about the applicability of biometrics to retail. Among the many points he addressed, he dealt with algorithmic inaccuracy and the proper use of facial recognition as an investigative lead:
“It’s true that some early police algorithms were poor, but the biometric matching algorithms offered by some providers is over 99.99% – that’s as close to perfect as anyone has ever got. That’s NASA-level accuracy, better than some medical or military procedures and light years away from people staring at CCTV monitors. What about errors and misidentification? Used properly, LFR is a decision support tool, it’s not making the identification itself. Ultimately, it’s helping shopkeepers make their decisions and that’s where the occasional misidentification happens – by human error, not technical.”
I offered an additional comment:
“One other point: for all those who complain about the lack of perfection of automated facial recognition, it’s much better than manual facial recognition. The U.S. Innocence Project recounts multiple cases of witness MISidentification, where people have been imprisoned due to faulty and inaccurate identification of suspects as perpetrators. I’d much rather have a top tier FR algorithm watching me than a person who knows nothing about facial recognition at all.”
In case you missed it, I’ve written several Bredemarket blog posts on witness MISidentification: two on Robert Williams’ misidentification alone.
- “Examples of Biometric Technology Misuse,” March 31, 2025.
- “We Survived Gummy Fingers. We’re Surviving Facial Recognition Inaccuracy. We’ll Survive Voice Spoofing,” June 27, 2023.
Heck, I addressed the topic back in 2021 in “The dangers of removing facial recognition and artificial intelligence from DHS solutions (DHS ICR part four).” This post covers the misidentification of Archie Williams (no relation).
So don’t toss out the automated facial recognition solution unless you have something better. I’ll wait.
Bredemarket 