Democratic Underground Latest Greatest Lobby Journals Search Options Help Login
Google

Computer Taught To Recognize Attractiveness In Women

Printer-friendly format Printer-friendly format
Printer-friendly format Email this thread to a friend
Printer-friendly format Bookmark this thread
This topic is archived.
Home » Discuss » Archives » General Discussion (1/22-2007 thru 12/14/2010) Donate to DU
 
Political Heretic Donating Member (1000+ posts) Send PM | Profile | Ignore Sat Apr-05-08 11:52 PM
Original message
Computer Taught To Recognize Attractiveness In Women
Funny, but also very interesting article on the evolution of AI


Computer Taught To Recognize Attractiveness In Women
ScienceDaily (Apr. 5, 2008) — "Beauty," goes the old saying, "is in the eye of the beholder." But does the beholder have to be human?

Not necessarily, say scientists at Tel Aviv University. Amit Kagian, an M.Sc. graduate from the TAU School of Computer Sciences, has successfully "taught" a computer how to interpret attractiveness in women. But there's a more serious dimension to this issue that reaches beyond mere vanity. The discovery is a step towards developing artificial intelligence in computers. Other applications for the software could be in plastic and reconstructive surgery and computer visualization programs such as face recognition technologies.

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 color were fed into the analysis as well. Based on human preferences, the machine "learned" the relation between facial features and attractiveness scores and was then put to the test on a fresh set of faces.

Says Kagian, "The computer produced impressive results -- its rankings were very similar to the rankings people gave." This is considered a remarkable achievement, believes Kagian, because it's as though the computer "learned" implicitly how to interpret beauty through processing previous data it had received.
Printer Friendly | Permalink |  | Top
jgraz Donating Member (1000+ posts) Send PM | Profile | Ignore Sun Apr-06-08 12:02 AM
Response to Original message
1. Yawn -- I can already do that
They should be working on a program that recognizes passive-aggressiveness in women. Or one that tells you if they have annoying ex-boyfriends hanging about.


Printer Friendly | Permalink |  | Top
 
readmoreoften Donating Member (1000+ posts) Send PM | Profile | Ignore Sun Apr-06-08 02:40 AM
Response to Reply #1
13. Hmmm passive aggressive. Well, I mean, if that's what you want to think about women go ahead.
No, it's cool. I know a lot of guys think that way about women. I just didn't expect you to be one of them. Ya know? No, it's cool. I'm fine. I said, I'm FINE. Why are you apologizing. I SAID I'M FINE!

And honey, it's your turn to fold the laundry. I can't do it this time. I have carpal tunnel from doing it the last three times. And the carpal tunnel really hurts.
Printer Friendly | Permalink |  | Top
 
jgraz Donating Member (1000+ posts) Send PM | Profile | Ignore Sun Apr-06-08 02:41 AM
Response to Reply #13
14. Um...why is my computer beeping?
Printer Friendly | Permalink |  | Top
 
MercutioATC Donating Member (1000+ posts) Send PM | Profile | Ignore Sun Apr-06-08 12:02 AM
Response to Original message
2. I wonder if the "Golden Ratio" is part of the programming.
Edited on Sun Apr-06-08 12:03 AM by MercutioATC
http://math.suite101.com/article.cfm/the_golden_ratio

"Most people surely don’t realize that a rectangle with sides of 8 inches and 12.944271912 has been mathematically more pleasing to the eye than, say, a rectangle with sides of 5 inches and 10 inches? While it may sound farfetched to believe that aesthetics are so intimately related so such a thing as the size of a rectangle, rest assured that, for some strange reason, it happens to be unavoidably true.

While scientists have been unable to determine exactly what it is that makes a rectangle of this size more palatable than other sizes from a neurological perspective, they have at least been able to explain it mathematically.

Mathematicians call this phenomenon the Golden Ratio (often denoted in mathematics by the Greek symbol “phi” – j), and, as such, the rectangle previously described would be considered a Golden Rectangle. The Golden Ratio is slightly easier to understand if one considers a line divided into two segments; a long segment (A) and a short segment (B).

This remarkable ratio occurs when the ratio of A to B is equal to the ratio of the entire line (A+B) to the longer segment (A). Perhaps this seems complicated, but only until one actually takes the time to draw these line segments and get a visual perspective of this.

In other words, the rectangle described above is a golden rectangle because the ratio of the length of the short side to the length of the long side is exactly equal to the ratio between both of them put together to the length of the long side. In exact terms, this “golden” ratio between the sides of the rectangle is 1.618033989. Exactly."



Printer Friendly | Permalink |  | Top
 
Quantess Donating Member (1000+ posts) Send PM | Profile | Ignore Sun Apr-06-08 12:19 AM
Response to Original message
3. How interesting that a similar study was not done on men's faces.
How predictable.
Printer Friendly | Permalink |  | Top
 
DavidDvorkin Donating Member (1000+ posts) Send PM | Profile | Ignore Sun Apr-06-08 12:29 AM
Response to Reply #3
5. You may be jumping to a false conclusion
The report says this at the end:

Nonetheless, the experiment only involved women's faces, as there is a greater variety of positions regarding male beauty.


Link here: http://www.haaretz.com/hasen/spages/966854.html



(By "positions" I assume they really mean parameters.)
Printer Friendly | Permalink |  | Top
 
aquart Donating Member (1000+ posts) Send PM | Profile | Ignore Sun Apr-06-08 02:33 AM
Response to Reply #5
11. "Positions"?
Does that mean it depends on where you look? Like, say, down?
Printer Friendly | Permalink |  | Top
 
Political Heretic Donating Member (1000+ posts) Send PM | Profile | Ignore Sun Apr-06-08 02:00 AM
Response to Reply #3
10. I believe the choice to start with women's face was more technical than sexist
Maybe not, but at the end of the article it sounds like the conditions for testing were more complicated for men's faces. If this is an early stage experiment, it makes sense to start with one, and to start with whichever one you can do with the least parameters.
Printer Friendly | Permalink |  | Top
 
Quantess Donating Member (1000+ posts) Send PM | Profile | Ignore Mon Apr-07-08 04:21 AM
Response to Reply #10
15. Well, of course it makes sense to do with the least parameters,
or anything else that might justify beginning your study in the way that you think is the right way to be done!

Men's faces are more complicated? Says who?

I don't think so.
Printer Friendly | Permalink |  | Top
 
Political Heretic Donating Member (1000+ posts) Send PM | Profile | Ignore Mon Apr-07-08 06:14 AM
Response to Reply #15
18. Sadly, I doubt its mens faces that is more complicated-its that mens reactions are LESS complicated
lol...

Hate to say it, but its probably that the parameters of gaging mens responses were much less complicated. :P

Printer Friendly | Permalink |  | Top
 
DavidDvorkin Donating Member (1000+ posts) Send PM | Profile | Ignore Sun Apr-06-08 12:26 AM
Response to Original message
4. But this assumes that those parameters are what the humans were also using to judge beauty
If the human beings were basing their judgments on other things, then the machine might not agree with humans in the case of a larger sample.
Printer Friendly | Permalink |  | Top
 
Political Heretic Donating Member (1000+ posts) Send PM | Profile | Ignore Sun Apr-06-08 01:58 AM
Response to Reply #4
9. Right. My first thought as well. Still.....
...a computer being able to organized and execute these sort of judgments, even if the programing reflects essentially a "copy" of an average subset of individual preferences, is still pretty cool.
Printer Friendly | Permalink |  | Top
 
readmoreoften Donating Member (1000+ posts) Send PM | Profile | Ignore Sun Apr-06-08 02:36 AM
Response to Reply #4
12. Too bad beauty involves love and admiration.
My girlfriend has the most beautiful face in the world but I doubt the computer would rank it properly.
Printer Friendly | Permalink |  | Top
 
Quantess Donating Member (1000+ posts) Send PM | Profile | Ignore Mon Apr-07-08 04:37 AM
Response to Reply #12
16. And I have a handsome boyfriend, but the computer doesn't give a fig!
Edited on Mon Apr-07-08 05:01 AM by quantessd
Not that I care what the computer says about a man's face, about my guy's face or whether it's attractive. I KNOW he is an attractive man, and I KNOW I am an attractive woman.
Printer Friendly | Permalink |  | Top
 
Beregond2 Donating Member (1000+ posts) Send PM | Profile | Ignore Sun Apr-06-08 12:59 AM
Response to Original message
6. well,
that's more than I've ever been able to do...
Printer Friendly | Permalink |  | Top
 
Guaranteed Donating Member (1000+ posts) Send PM | Profile | Ignore Sun Apr-06-08 01:05 AM
Response to Original message
7. Then it should also be able to create the "most" attractive face possible.
Alright, HAL, let's see it.

http://www.itousa.com/images/Ugly!.jpg
Printer Friendly | Permalink |  | Top
 
Quantess Donating Member (1000+ posts) Send PM | Profile | Ignore Mon Apr-07-08 05:35 AM
Response to Reply #7
17. The "ape" in us wants to see the most attractive female face!
Printer Friendly | Permalink |  | Top
 
dweller Donating Member (1000+ posts) Send PM | Profile | Ignore Sun Apr-06-08 01:09 AM
Response to Original message
8. still GIGO
This is considered a remarkable achievement, believes Kagian, because it's as though the computer "learned" implicitly how to interpret beauty through processing previous data it had received.

a rose is a rose.
dp
Printer Friendly | Permalink |  | Top
 
DU AdBot (1000+ posts) Click to send private message to this author Click to view 
this author's profile Click to add 
this author to your buddy list Click to add 
this author to your Ignore list Wed Apr 17th 2024, 08:17 PM
Response to Original message
Advertisements [?]
 Top

Home » Discuss » Archives » General Discussion (1/22-2007 thru 12/14/2010) Donate to DU

Powered by DCForum+ Version 1.1 Copyright 1997-2002 DCScripts.com
Software has been extensively modified by the DU administrators


Important Notices: By participating on this discussion board, visitors agree to abide by the rules outlined on our Rules page. Messages posted on the Democratic Underground Discussion Forums are the opinions of the individuals who post them, and do not necessarily represent the opinions of Democratic Underground, LLC.

Home  |  Discussion Forums  |  Journals |  Store  |  Donate

About DU  |  Contact Us  |  Privacy Policy

Got a message for Democratic Underground? Click here to send us a message.

© 2001 - 2011 Democratic Underground, LLC