Home | WebMail | Register or Login

      Calgary | Regions | Local Traffic Report | Advertise on Action News | Contact

Sign Up

Sign Up

Please fill this form to create an account.

Already have an account? Login here.

Posted: 2017-09-14T18:24:10Z | Updated: 2017-09-14T18:24:10Z

The facial recognition technology in the new iPhone X is supposed to help people easily unlock the device, but it may be most helpful to crime show writers looking for bizarre plot twists.

People who purchase the $1,000 smartphone will unlock it by simply by looking at it, thanks to sensors designed to create a highly accurate facial map.

The Face ID function supposedly works in the dark, isnt fooled by photos or even highly realistic masks, according to Phil Schiller, Apples senior vice president of worldwide marketing. It can even detect a person who decides to grow a beard.

But facial recognition experts like Herman Yau, the CEO of Tend, a San Francisco firm specializing in security camera, said the existing technology may not deter, say, Mary-Kate Olsen from accessing sister Ashleys phone for nefarious purposes (Law & Order: SVU writers, take note).

Since most facial recognition is built on visual pattern recognition, it wouldnt be able to reliably differentiate between identical twins, Yau told HuffPost. Basically, if parents have trouble telling their twins apart, so will facial recognition algorithms.

Phil Schiller, Apples vice president of product marketing, says the company worked with professional mask makers and makeup artists to ensure that lookalike forgeries would not trick the software. But he conceded , Of course, the statistics are lowered if that person shares a close genetic relationship with you.

Jason Chaikin, President of Vkansee , a biometric authentication company, said one of the challenges with facial recognition is the need for users to control their pose, angle and illumination.

Any movement makes it hard for high-res details to be captured, he told HuffPost. This makes false reject rates a continued challenge because you need a perfect picture with structured light especially when discriminating against identical twins, which is hard to do.

Hes skeptical Apple has overcome such problems.

It remains to be seen how successful this is in practice and in mass commercial production, which is why weve typically only seen this in government applications on a smaller scale, Chaikin said.

An iris scan or use of a fingerprint generally have proven more secure in testing than facial recognition, he said.

Support Free Journalism

Consider supporting HuffPost starting at $2 to help us provide free, quality journalism that puts people first.

Thank you for your past contribution to HuffPost. We are sincerely grateful for readers like you who help us ensure that we can keep our journalism free for everyone.

The stakes are high this year, and our 2024 coverage could use continued support. Would you consider becoming a regular HuffPost contributor?

Thank you for your past contribution to HuffPost. We are sincerely grateful for readers like you who help us ensure that we can keep our journalism free for everyone.

The stakes are high this year, and our 2024 coverage could use continued support. We hope you'll consider contributing to HuffPost once more.

Support HuffPost

But Steven Murdoch, a security researcher at the University College London and VASCO , a cyber-security firm, said Apples Face ID may be more secure than its fingerprint detection technology unless you have an evil twin.

Apple estimates that risk at one-in-50,000 for its Touch ID fingerprint sensor and one-in-one million for its new Face ID system, Murdoch told HuffPost. Between the two options, Face ID seems to be more secure except if youre related to the person trying to access your phone.

Genetically speaking, its more likely for people who are closely related to have similar faces than it is to have similar fingerprints .

Support Free Journalism

Consider supporting HuffPost starting at $2 to help us provide free, quality journalism that puts people first.

Thank you for your past contribution to HuffPost. We are sincerely grateful for readers like you who help us ensure that we can keep our journalism free for everyone.

The stakes are high this year, and our 2024 coverage could use continued support. Would you consider becoming a regular HuffPost contributor?

Thank you for your past contribution to HuffPost. We are sincerely grateful for readers like you who help us ensure that we can keep our journalism free for everyone.

The stakes are high this year, and our 2024 coverage could use continued support. We hope you'll consider contributing to HuffPost once more.

Support HuffPost