By Dr. Andrew O’Brien
ICU Product Manager
How we recognise someone we know is something we generally take for granted. We see their face and our brains assimilate the information in front of our eyes – their mouth, their nose, their eyes and how they all come together. Let’s call it our ‘recognition data’.
Facial recognition technology registers the data in much the same way to recognise a human face. While we have our brains – the most powerful, sophisticated ‘computers’ on the planet – facial recognition technology uses biometrics and algorithms to map facial features and compare them to those from a database of photographs or videos.
It compares the information in front of its ‘eyes’ until it finds a match. Smartphone users know facial recognition well. Once it recognises the owner’s biometrics, access to the phone is granted. It’s a simple principle that can be applied to multiple uses.
Facial recognition technology has been found to have accuracy levels as high as 99.88 per cent, according to Laser Focus World magazine, which provides in-depth global coverage of optoelectronic technologies, applications, and markets for engineers, researchers, scientists, and technical professionals.
The global facial recognition sector is expected to grow to $7.7bn (£5.7bn) in 2022 - up $4bn (£2.97bn) - according to digital security giants Norton, given the breadth of its commercial applications and as markets bounce back from the Covid-19 pandemic.
How facial recognition is used
As we’ve alluded to already, facial recognition has multiple uses. They include:
Effective but controversial
While facial recognition technology is undoubtedly effective, it sometimes makes headlines for the wrong reasons, namely civil rights and privacy.
The technology made headlines when the court of appeal ruled that South Wales Police breached privacy rights and broke equalities law in capturing thousands of faces in crowds to compare them to images of people on a watchlist, which included suspects, missing people and other persons of interest to the police.
The ruling prompted the government’s Surveillance Camera Commissioner (SCC), Tony Porter, to issue best practice guidance to all police forces in England and Wales. South Wales Police, meanwhile, said the appeal court’s ruling was one ‘it could work with’.
The most recent and high-profile publicity has surrounded Facebook’s decision to shut down its facial recognition system, deleting face scans of one billion users whose faces will no longer be recognised. Writing in a blog, Jerome Presenti, VP of Artificial Intelligence at Meta – Facebook’s newly named parent company – said: “We need to weigh the positive use cases for facial recognition against growing societal concerns, especially as regulators have yet to provide clear rules.”
However, he was still supportive of the technology in a wider context, adding: “Looking ahead, we still see facial recognition technology as a powerful tool, for example, for people needing to verify their identity, or to prevent fraud and impersonation. We believe facial recognition can help for products like these with privacy, transparency and control in place, so you decide if and how your face is used. We will continue working on these technologies and engaging outside experts.”
ICU Intelligent Identification
Our ICU biometric solutions use local processing to provide a fast response with world leading levels of accuracy and no recurring transaction fees. Additionally, customers can benefit from our ITL cloud hosting. In this case, we will host the customer databases in the cloud (manage security and maintenance) and allow customers to remotely link all devices together to control all activity from a single point.
Visit Our Products page for the full details and benefits of our facial analysis and facial recognition technology options:
Both use our proprietary algorithms, design, trained and fine-tuned by ourselves.
We do not use publicly available databases for training or tuning like many other systems, favouring our own extensive datasets especially chosen to reduce gender and ethnic bias. Our algorithms are not publicly available, which makes our system, and customer data more secure.
And both ICU Lite and ICU Pro include spoof detection, the importance of which is featured in our blog ‘Spoof: A barrier to the acceptance of facial recognition systems’
Check out our previous blog: Facial Recognition: Friend or Foe?
You can request a free trial of our products by completing our
contact us form.