If You Recognize This Face Just Know That I Know

Today, UH math professor Krešo Josić recognizes your face. The University of Houston presents this series about the machines that make our civilization run, and the people whose ingenuity created them.

We are gifted at recognizing faces. Nosotros perceive faces in clouds; we perceive faces in mandrake roots. Like magnets faces attract our attention, and they practise so from early infancy. An entire region of our encephalon seems devoted to telling our neighbor from our spouse, based on facial features. Imagine what would happen if we couldn�t! And so you will encounter why it�s so of import to be practiced at telling faces apart.

Mandragora, fromTacuinum Sanitatis (1474)

How is information technology possible for the states to recognize familiar people from dissimilar angles, or even wearing a Halloween costume? Nosotros don�t fully sympathize the process, but it does seem to be holistic. Our minds integrate all the features of a face up into a representation that we process as a whole. Face recognition has many surprising features: Did yous know that eyebrows are among the most important identifiers; or that it may be easier to recognize a extravaganza of a friend than an actual motion-picture show?

How do machines fare at this chore? Face recognition software has improved enormously in the last xv years. In some ways computers surpass humans in their ability to tell apart faces, and they�re getting better at information technology every day.

Only let�s wait at one of the first face recognition algorithms adult by mathematicians Larry Sirovich and Michael Kirby at Brownish University in the 1980s. They started by computing an average face up from a set of pictures.

25 faces

And then they used that same set of pictures to find the most common ways faces differ from their average. These differences were expressed using a set of images chosen eigenfaces.

Eigenfaces

Sirovich and Kirby managed to approximate any face equally a combination of a relatively minor set of eigenfaces. They used linear algebra, the same branch of mathematics that lets Netflix advise movies you may like.

The boilerplate of the 25 faces

At present neuroscientists discover that our brain might be doing something similar when we recognize a friend. Suppose we encounter her on the street. In one case our brain realizes that information technology�s observing a face, cells in sure parts of the cortex seem to answer to deviations of our friend�s face from the boilerplate. Certain brain cells might respond to her nose being shorter, while others indicate that her eyebrows are more peaked than those on an average face.

We have an amazing ability to discern faces even when they�re, say, equanimous of fruits or vegetables — equally in the paintings of Arcimboldo. We effortlessly pull the details before united states of america into an integrated representation. This representation is not only linked with the person we recognize, but it becomes that person in our heed. To usa people are their visage: When you think of somebody, y'all kickoff recall their face. Indeed we use faces to navigate our complex society. Only imagine a world of faceless beings! Our power to smoothly recognize and memorize faces has evolved hand in manus with our ability to role equally office of human guild. And an essential step in making our smart machines part of our society will be educational activity them to recognize u.s.a..

Vertumnus (Skoklosters Slott, Balsta, Sweden), and Summer (Louvre, Paris) past Arcimoboldo

I�m Krešo Josić, at the University of Houston, where we�re interested in the mode inventive minds work.
(Theme music)

For an interesting discussion of the problem of face recognition in humans you can look at http://www.nytimes.com/2007/02/xiii/health/psychology/13face.html.
It is nevertheless debated whether a particular part or parts of the brain are primarily used to tell apart faces. A pointer to some references is available at http://en.wikipedia.org/wiki/Fusiform_face_area. A good review of our current (as of early 2008) understanding of face recognition in humans and how it compares to commonly used algorithms can be constitute in Tsao and Livingstone. �Mechanisms of face perception.� Annu Rev Neurosci (2008) vol. 31 pp. 411-37 http://dx.doi.org/10.1146/annurev.neuro.30.051606.094238.

Face recognition in humans has many counterintuitive features. You tin read more about them here http://spider web.mit.edu/bcs/sinha/papers/20Results_2005.pdf.

At that place are many people at UH and in Houston working on different aspects of face recognition. I will just mention Prof. Kakadiaris at UH (http://www.cbl.uh.edu/URxD/research/urxd_overview), but a search on Google will lead you to many others.

Boosted information:

It seems that the regions of the brain responsible for face recognition remain plastic throughout life. This could mean that nosotros are always able to utilize these areas to efficiently add more faces to be processed by this circuitry.

Prosopagnosia is the inability to recognize faces. Surprisingly, it appears that the ability to recognize objects is intact in people thus afflicted, but their ability to integrate the unlike features of a face into the percept of a face up is impaired. On the other hand Tsao and Livingstone discuss the example of a patient who seems to be normal at recognizing faces, but has bug in recognizing objects. This suggests that a specialized and somewhat democratic circuitry in our brain is devoted to face recognition.

In 1994 the visage of the Virgin Mary appeared to Diane Duyser of Hollywood, FL on a grilled cheese sandwich. Mrs. Duyser was not alone in her belief, and x years later the sandwich fetched $28,000 when auctioned on eBay.

There is a surprising tendency for humans to encounter robots or artifical faces with revulsion if they become as well realistic. This consequence is chosen the uncanny valley http://en.wikipedia.org/wiki/Uncanny_valley.

Images from Wikipedia:

The Arcimboldo figures
http://en.wikipedia.org/wiki/Arcimboldo

Mandrake Image http://en.wikipedia.org/wiki/File:Mandragora_Tacuinum_Sanitatis.jpg

The Engines of Our Ingenuity is Copyright © 1988-2009 by John H. Lienhard.