Tag Archives: Face Recognition

Another pair of famous doppelgangers

Former Foreign Minister of Australia Gareth Evans and the stodgy male character in those annoying Kleenheat ads.

But I find the latter much more likeable.

On Nine tonight

Finding My Twin Stranger
https://www.9now.com.au/finding-my-twin-stranger

 

Radio stories from the US from last year about prosopagnosia and superrecognizers

http://www.npr.org/2016/11/22/502932399/some-people-are-great-at-recognizing-faces-others-not-so-much

http://www.npr.org/2016/11/24/503279180/researchers-explore-the-struggle-of-recognizing-faces

Australia’s Face Verification Service

News that I didn’t have time to write about in November last year. The federal government of Australia plans to create a database of photo-id images. I’m not sure if this is just the National Facial Biometric Matching Capability renamed.

“A Face Identification Service (FIS) is expected to commence in 2017 to help determine the identity of unknown persons. It will be used for investigations of serious offences by specialist officers.”

Couldn’t be less detail or description or explanation in this statement.

https://www.ag.gov.au/RightsAndProtections/IdentitySecurity/Pages/Face-verification-service.aspx

https://www.itnews.com.au/news/australias-new-facial-verification-system-goes-live-441484

http://www.zdnet.com/article/australian-face-verification-service-starts-with-citizenship-imagery/

 

Person recognition a crucial point in plotline in another classic movie?

We stayed up late to watch the 1940s classic movie Gaslight the other night. What an amazing story and brilliant acting from Boyer and Bergman! Charles Boyer was not an unusually handsome man, but her certainly knew how to use his eyes, and he also knew how to use his voice.

Was it the detective recognizing a family resemblance between Paula and her late aunt that caught the attention of the detective, or was it that combined with a visual recognition of Serges Bauer?

http://www.imdb.com/video/screenplay/vi1754531097

 

Interesting letter from last year re acquired prosopagnosia and the uncanny valley

Editor’s pick: Excluded from the uncanny valley
From Bob Cockshott

New Scientist. Issue 3100. November 19th 2016. p.60.

https://www.newscientist.com/letter/mg23231002-500-1-editors-pick-excluded-from-the-uncanny-valley/

The experience described in the letter seems to suggest that there is more to face recognition than simple memory or faces, or could it be that there are aspects of the perception of faces in particular that make them especially memorable? Faces are easy to personify because they are usually found on people. Perhaps it is the ability to detect the person behind the face that has become amiss in the letter’s author following his stroke, and maybe this ability feeds into face memory? Such a relationship would explain the author’s inability to notice the uncanny valley, and it would also explain why a personifying synaesthete like myself is also a super-recognizer.

P.S.

https://www.newscientist.com/article/mg23230970-500-exploring-the-uncanny-valley-why-almosthuman-is-creepy/

I’ve had a read of the interesting article by Laura Spinney that this letter was a comment about, and I think the Perceptual Mismatch Theory of the Uncanny Valley Effect probably offers a more plausible explanation of my a prosopagnosic might be unable to detect the uncanny valley than the competing Category Uncertainty Theory. The article explained the two theories and evidence supporting them. To summarise, the CUT explains the UVE as the result of confusion about what type of thing one is looking at (for example robot or human?), while the PMT explains the UVE as resulting from unease or perceptual confusion when different features or parts of the thing or being viewed have dissimilar levels of human-like appearance (for example the face and skin look realistic but the eyes do not move like human eyes). I think the case of a prosopagnosic not detecting the UVE when people with normal face perception do is support for the PMT theory rather than the other because as far as I know, prosopagnosia does not involve inability to classify faces or bodies as human or non-human, while I believe there is evidence supporting the idea that prosopagnosia can be the result of not being able to perceptually integrate the features of the face as a whole that is recognizable as a unique or distinctive mix of many attributes and features. A non-prosopagnosic person should be able to perceive a face or body as a whole made up of parts, and notice if one or more elements has a level of humanity that does not match other parts, as in the PMT, while a prosopagnosic might not. Of course, research is needed to investigate my armchair speculations.

Interesting questions and serious concerns

Revell, Timothy Concerns as face recognition tech used to ‘identify’ criminals. New Scientist. December 1st 2016.

https://www.newscientist.com/article/2114900-concerns-as-face-recognition-tech-used-to-identify-criminals/

Garvie, Clare, Bedoya, Alvaro and Frankle, Jonathan The perpetual line-up: unregulated police face recognition in America. Center on Privacy & Technology at Georgetown Law. OCTOBER 18th 2016.

https://www.perpetuallineup.org/

Is there really a criminal face? I don’t think the research discussed in the New Scientist article settles the debate by any means, but at least the controversial idea is opened up for investigation. If there is one my guess is that it is a look that coincides with the Australian face (every race and nation has a distinctive averaged facial type, apparently). European colonisation of Australia began as a penal colony and thus a good part of the white genetics of Australians arrived in this country through people identified as criminals. My best guess is that the crim face has a large straight nose, thin lips and puffy, small eyes. I’d guess this unattractive face could in itself be a social and economic disadvantage, or could be symptomatic of a phenotype that includes some degree of intellectual impairment. I think if there is a crim face it might have little to do with personality but a lot to do with disadvantage, but this is all speculation.

I think it is worth noting that claims made in the print version of this article about supposed advantages of AI over humans in face recognition skills such as identifying age, gender, ethnicity and tiredness by looking at faces presumably only apply to humans of average face recognition ability who maybe are not as exhaustively trained in these skills as the AI systems have been. One cannot compare human ability with AI in face recognition until appropriately trained super-recognizers (representing the top end of human ability) have been pitted against machines. I’m guessing this hasn’t been done.

Perhaps the most important part of this article is right at the end; “…the majority of US police departments using face recognition do little to ensure that the software is accurate.” That certainly is not good enough. Human super-recognizers have abilities that have been proven in scientific testing and also in practice in policing in the UK. Why do so many people persist in the assumption that machines must be better than humans in visual processing, in the face of an abundance of evidence? The link in the New Scientist article to the website of the researchers who have criticized the use of face recognition technology in law enforcement in the United States of America is worth a look for sure.

Surprising explanation for why face recognition matures unusually late in human development!

I didn’t expect to be reading this but I can recognize that this discovery seems to explain why face recognition is human cognitive ability that hits its peak surprisingly late in human development, and I’m now wondering how this fits into my theories about the relationship between my super-recognition and my synaesthesia, and that includes wondering how this discovery fits with my immune hypothesis of synaesthesia (which is all about pruning rather than proliferation), and of course I’m wondering how this fits in with what is known about super-recognizers. I guess I should just calm down and read the full text.

Coghlan, Andy Brain’s face recognition area grows much bigger as we get older. New Scientist. January 5th 2017.
https://www.newscientist.com/article/2117259-brains-face-recognition-area-grows-much-bigger-as-we-get-older/

Jesse Gomez, Michael A. Barnett, Vaidehi Natu, Aviv Mezer, Nicola Palomero-Gallagher, Kevin S. Weiner, Katrin Amunts, Karl Zilles, Kalanit Grill-Spector Microstructural proliferation in human cortex is coupled with the development of face processing. Science. January 6th 2017.

http://science.sciencemag.org/content/355/6320/68

 

Wouldn’t say it’s a positive or a negative experience

The experience of being a super-recognizer is often interesting. I wouldn’t say it is necessarily a positive experience or a negative experience. Like most human abilities it adds a layer of complexity to my life. There are occasionally some strange moments, like the time when I was chatting about our favourite hobby with a kind and humble foreign lady who I’d never met before and probably wont ever meet again, who had almost but not quite the same dentition as my late mother, who has been gone for something like four decades. And just the other day I was striding out of Kmart with an armful of unnecessary items and in the corner of my eye spotted a doppelganger of my late father. When I turned my head for a second glance the old buzzard wriggled uncomfortably in just the same way that Dad used to. We are all nothing more than twigs of the great tree of humanity. Please be kind and please be good in 2017.

True that skulls can be used to create recognizable faces

Wardrop, Ian and Neave, Richard I know that face. New Scientist. No 3101 November 26th 2016.
https://www.newscientist.com/topic/lastword/i-know-that-face/