Recognizing relatedness in the face – could a super-recognizer perform better than software?

I believe that I probably could out-perform both of the interesting kinship recognition computer programs that are discussed in this most interesting recent article in New Scientist magazine, but there is still a lot to be learned from the researchers’ efforts to develop software that can detect whether two people in photographs are related. The first program described in this article had a success rate of 68% in detecting parent-child matches, the second program a 71% success rate, and people (presumably with average ability in face recognition) had a success rate of 67%. I’d love to see a similar study done with super-recognizers compared to normal human controls or pitted against a computer program. My money would be on nature’s best, rather than the latest technology.

It’s interesting to note that the first program described uses a method which I think is very different to natural face recognition, analysing fine details of the picture, while human face recognition is thought to be a process of identifying an overall pattern rather than looking at the picture piece-by-piece. The focus on details of this program appears to give the program a fair degree of robustness and flexibility in dealing with variations in the appearance of faces in photos. As researchers have found in another study (published online in the journal Cognition) , there can be considerable variability in the appearance of the same face in different photographs, and while people who are familiar with a face are able to identify the same face in different photos, people who were unfamiliar with that face did not have whatever it takes to be able to overcome variations among different photos of the same person to identify the photos as being of the same person. Clearly there is something in the memory of a person who is familiar with a face which gives their ability to recognize that face a great robustness and flexibility. I wonder what it is?

A quote from the New Scientist article: “Lu reckons that improved algorithms could be used to help determine kinship when DNA testing isn’t an option. “It can also help refugees find dispersed family members,” he suggests.” I believe that with my well above average ability in face recognition I would probably perform well in these types of tasks. I would love to work in a job or a business in which I was identifying faces or picking out related people from photographs or identifying people who have a genetic similarity (I can be contacted through leaving a comment on a blog post). Face recognition is an ability with applications that go way beyond personal socializing. Superior face recognition could be useful in many important areas of work, including law enforcement, private detective work, social work (working with adopted people or displaced families) and medicine (identifying genetic syndromes), and it appears that the current state of technological development of face photograph recognition technology is at a pretty basic level, only marginally better than the ability of the average person. In contrast, super-recognizers have a face recognition ability that far exceeds that of normal people, and I have good reason to believe that I could be a superrecognizer. I feel quite confident about my ability to detect kinship or genetic similarity from looking at people’s faces because I believe that is probably what I was involuntarily doing when I experienced The Strange Phenomenon, which I have described in the first post in this blog. Last month the British Sunday Times newspaper reported that London’s Metropolitan Police force have an elite squad of super-recognizers who have proven to be much more useful than face recogition technology. “The Met” are actively searching for more superrecognizers within their ranks to help with the huge task of identifying faces in many hours of CCTV images of the English riots. It seems odd to me that so much research is being done on creating and improving technology in face recognition when we have only just started to understand the naturally-occuring human ability in face recognition that has always existed.

Facial recognition software spots family resemblance
7 December 2011 by Kate McAlpine
Magazine issue 2842
New Scientist
http://www.newscientist.com/article/mg21228424.900-facial-recognition-software-spots-family-resemblance.html

Rob Jenkins, David White, Xandra Van Montfort, A. Mike Burton Variability in photos of the same face. Cognition. Available online 3 September 2011. http://www.sciencedirect.com/science/article/pii/S0010027711002022

A Most Peculiar Experience  https://superrecognizer.wordpress.com/2010/12/04/a-most-peculiar-experience/

Face photographs unsuitable as proof of identity due to within-person variability?  https://superrecognizer.wordpress.com/2011/10/14/face-photographs-unsuitable-as-proof-of-identity-due-to-within-person-variability/

Face photographs unsuitable as proof of identity due to within-person variability?

This new journal paper raises some uncomfortable questions about the widespread and long-standing reliance on photographs as a means of identification of individuals for security purposes, and I guess also in legal systems. This paper also possibly has some implications for understanding The Strange Phenomenon, which is extraordinarily sensitive to the angle at which one face is viewed. The Strange Phenomenon only ever happened fully when I viewed John’s face* from around a 45 degree angle in natural light (outdoors), from before he gained a bit of weight. These were the exact conditions that triggered The Strange Phenomenon, which I believe is a neurologically-based sensory experience that is a hybrid of synaesthesia and face recognition. John’s face viewed from other angles didn’t trigger the effect, so it is as though my unconscious mind saw his face from one particular angle as a quite different “thing” than his face viewed from other angles, which seems to be in accord with this study’s finding that different photos of the same face can look like different faces. This also supports my observation that John’s face is a bit of an curiousity in that it takes on a very different character from profile compared to full-face, the front view looking quite young and innocent, while his profile looks a bit villanous and more masculine. If you wish to read about The Strange Phenomenon, take a look at the first post in this blog.

We still have so much to discover about a cognitive function as ordinary and taken-for-granted as face recognition. We have yet to fully comprehend how amazing our brains really are.

* Not his real name.

Rob Jenkins, David White, Xandra Van Montfort, A. Mike Burton Variability in photos of the same face. Cognition. Available online 3 September 2011. http://www.sciencedirect.com/science/article/pii/S0010027711002022

I can’t believe it’s not synaesthesia! – embodied cognition

Yes indeed, this is a fascinating article from New Scientist magazine. This is the article that made me feel incredulous the first time that I read it last year, that the word “synaesthesia” was not even once mentioned in it, because it seemed to be an article about a number of different types of synaesthesia. I could go into details about why I believe this, but I’d risk restating most of the text of this two-page article. Basically, this is an article about embodied cognition. It is clear to me that the researchers studying embodied cognition have a lot to gain from sharing ideas with synaesthesia researchers (and synaesthetes), and vice versa.

A study by Australian academic Tobias Loetscher that was published in the journal Current Biology and another study by Daniel Casasanto, an academic in the Netherlands, which was published in the journal Cognition are discussed in this article. The “metaphor theory” of George Lakoff and Mark Johnson is discussed. Much of this article seems to be very relevant to the idea proposed by some synaesthesia researchers that synaesthesia is the origin of metaphorical language. Wouldn’t synaesthesia or some very similar mental process be the link between study subjects’ emotional feelings of being socially isolated and their reported physical sensations of feeling physically colder?

Other parts of this article seem to be very relevant to, or a description of, number form synaesthesia and other mental mappings of concepts onto “spatial schema”. The study by Casasanto is about a psychological process that is very similar to the forward and backward vection that was the subject of the study in PLoS ONE that I discussed in a previous blog posting, in that it shows an influence on abstract thought from performing a physical task that focused the mind on one or other spatial directions. The vection study that I previously discussed was about backward and forward motion influencing abstract thought. The Casasanto study was about moving something upwards and moving something downwards influencing abstract thought.

Many of the more general conclusions in this article, based on the study findings, also seemed to be very relevant to my experiences of fine motor performances determining the content of my thoughts, often involving links with conceptual thinking, by a process that I believe is synaesthesia. “The results also led to a deeper question: does physical movement have the power to change not just the speed at which people talk, but also what they choose to talk – or even think – about?” A study by Casasanto found this to be true. “Isn’t that somewhat scary?” Casasanto asked. Yes, I think it is scary, but it is only by being aware of the irrational and arbitrary things that can influence cognition that we can ever hope to detect, control and transcend such influences.

Ananthaswamy, Anil Let your body do the thinking. New Scientist. Number 2753 March 27th 2010 p.8-9.
http://www.newscientist.com/article/mg20527535.100-mind-over-matter-how-your-body-does-your-thinking.html

Two articles about embodied cognition from Miller-McCune:

Jacobs, Tom To feel good, reach for the sky. Miller-McCune. February 4th 2010. http://www.miller-mccune.com/health/to-feel-good-reach-for-the-sky-8445/

Hilo, Jessica Power poses really work. Miller-McCune. November 15th 2010. http://www.miller-mccune.com/culture-society/power-poses-really-work-25322/

Another interesting recent article in a science magazine about face recognition – why does the ability mature so late in life?

It isn’t clear why face recognition ability should mature so much later in life than other abilities. Research published in the journal Cognition by a team that includes Laura Germine of Harvard University and face recognition researchers Ken Nayayama and Bradley Duchaine has been discussed in ScienceNews. One of the tests used in the study is the Cambridge Face Memory Test. The original paper can be viewed in full text, not behind a paywall.

Bower, Bruce Face memory peaks late, after age 30: Finding challenges view that all mental faculties max out in young adulthood. ScienceNews. January 1^st 2011. Vol. 179 No. 1 p.16.

http://www.sciencenews.org/view/generic/id/67410/title/Face_memory_peaks_late,_after_age_30

Germine, Laura T., Duchaine, Bradley, Nakayama, Ken Where cognitive development and aging meet: Face learning ability peaks after age 30. Cognition, Volume 118, Issue 2, February 2011, Pages 201-210.  http://www.sciencedirect.com/science/article/pii/S0010027710002611