Saturday, 5 April 2008

Beer Goggles and Super Science Saturday.

With a little help from Science Daily

I stumbled across a piece of research a couple of days ago that brought to mind the youthful exploits of some of my friends way back when.

Like most chaps in our younger 20’s who, being financially independent, single and able to cope with and even enjoy nights out in the City centre, we used to go out quite a bit to pubs and clubs. A few drinks, a bit of mild flirting with the young ladies present and general banter about football or (being mostly muso types) whose band was the best was the general order of business.

A couple of our number though were normally slightly more drunken and slightly more flirtatious than the rest of us and would often end up escorting young ladies home at the end of the evening.

‘Nudge nudge we’re off now Gren. Call you tomorrow’. Of course on more than a few occasions the ’beer goggles’ had been in full operation and the promised call was one of despair.

‘Mate, you could have told me she was boss eyed, pimply and about the size of a bifa bin!’

Which I’m thoroughly ashamed to say now was rather amusing at the time.

However with a little careful application work undertaken by scientists at Tel Aviv University may provide a solution to the current generation of marauding 20 somethings.

In the study undertaken led by Amit Kagian a computer has successfully been taught to interpret and recognise interpret attractiveness in women.

As Kagian explained "Until now, computers have been taught how to identify basic facial characteristics, such as the difference between a woman and a man, and even to detect facial expressions. But our software lets a computer make an aesthetic judgment. Linked to sentiments and abstract thought processes, humans can make a judgment, but they usually don't understand how they arrived at their conclusions."

In the first step of the study, 30 men and women were presented with 100 different faces of Caucasian women, roughly of the same age, and were asked to judge the beauty of each face. The subjects rated the images on a scale of 1 through 7 and did not explain why they chose certain scores. Kagian and his colleagues then went to the computer and processed and mapped the geometric shape of facial features mathematically.

Additional features such as face symmetry, smoothness of the skin and hair colour were fed into the analysis as well. Based on human preferences, the machine "learned" the relation between facial features and attractiveness scores. It was then put to the test on a fresh set of faces from which it produced virtually identical results to a human panel.

Of course the real story here is that this research is a useful step towards developing artificial intelligence.

However I wonder if a module could be produced that would plug into a digital camera and provide an instant assessment of a subjects attractiveness. This might mean that the worse thing one would wake up to on a Sunday morning would be a stinking hangover.

And the really good news for the chaps is that according to Kagian, it would be a lot more difficult to produce software to recognise beauty in men as there was much less agreement as to what this is amongst the human panel.

Shallow insensitivity possibly, but beauty, no.


CherryPie said...

Beauty is in the eye of the beholder :-)and well personality features too ;-)

Semaj Mahgih said...

This will never work because beauty comes through the physical features from the character and attitude. No photo is going to capture that beauty and to judge on a photo is dangerous.

Video is better but there are still so many nuances lost.

Liz said...

George Clooney with that smile. Or Johnny Wilkinson. See, easy.