In which a group of graying eternal amateurs discuss their passions, interests and obsessions, among them: movies, art, politics, evolutionary biology, taxes, writing, computers, these kids these days, and lousy educations.

E-Mail Donald
Demographer, recovering sociologist, and arts buff

E-Mail Fenster
College administrator and arts buff

E-Mail Francis
Architectural historian and arts buff

E-Mail Friedrich
Entrepreneur and arts buff
E-Mail Michael
Media flunky and arts buff


We assume it's OK to quote emailers by name.







Try Advanced Search



  2. Another Technical Note
  3. La Ligne Maginot
  4. Actress Notes
  5. Technical Day
  6. Peripheral Explanation
  7. More Immigration Links
  8. Another Graphic Detournement
  9. Peripheral Artists (5): Mikhail Vrubel
  10. Illegal Update


CultureBlogs
• Sasha Castel
• AC Douglas
• Out of Lascaux
• The Ambler
• PhilosoBlog
• Modern Art Notes
• Cranky Professor
• Mike Snider on Poetry
• Silliman on Poetry
• Felix Salmon
• Gregdotorg
• BookSlut
• Polly Frost
• Polly and Ray's Forum
• Cronaca
• Plep
• Stumbling Tongue
• Brian's Culture Blog
• Banana Oil
• Scourge of Modernism
• Visible Darkness
• Seablogger
• Thomas Hobbs
• Blog Lodge
• Leibman Theory
• Goliard Dream
• Third Level Digression
• Here Inside
• My Stupid Dog
• W.J. Duquette

Politics, Education, and Economics Blogs
• Andrew Sullivan
• The Corner at National Review
• Steve Sailer
• Samizdata
• Junius
• Joanne Jacobs
• CalPundit
• Natalie Solent
• A Libertarian Parent in the Countryside
• Rational Parenting
• Public Interest.co.uk
• Colby Cosh
• View from the Right
• Pejman Pundit
• Spleenville
• God of the Machine
• One Good Turn
• CinderellaBloggerfella
• Liberty Log
• Daily Pundit
• InstaPundit
• MindFloss
• Catallaxy Files
• Greatest Jeneration
• Glenn Frazier
• Jane Galt
• Jim Miller
• Limbic Nutrition
• Innocents Abroad
• Chicago Boyz
• James Lileks
• Cybrarian at Large
• Hello Bloggy!
• Setting the World to Rights
• Travelling Shoes

Miscellaneous
• Redwood Dragon
• IMAO
• The Invisible Hand
• ScrappleFace
• Daze Reader
• Lynn Sislo
• The Fat Guy
• Jon Walz

Links


Our Last 50 Referrers







« Holiday Tug o' Wars | Main | Auto Yak »

December 16, 2005

 The Mona Lisa Algorithm

Michael Blowhard writes:

Dear Blowhards --


Woman of no more mystery?

Scientists at the University of Amsterdam had the inspired idea of scanning the Mona Lisa, and feeding the resulting file into cutting-edge "emotion-recognition" software. The computer made sense of her legendarily hard-to-interpret expression in this way, reports AP:

83 percent happy, 9 percent disgusted, 6 percent fearful and 2 percent angry. She was less than 1 percent neutral, and not at all surprised.

How long until a "Mona Lisa" Photoshop plug-in goes on the market?

Best,

Michael

posted by Michael at December 16, 2005




Comments

Mona Lisa sounds schizophrenic--how can she be 15% "disgusted and fearful" and 83% "happy"? And how would they determine she was 83% happy instead of 84%? Unless she was repelled by Leonardo and relieved that the local constable just showed up to keep them company in the studio. Personally, I've never found the expression that mysterious---I think she's just kind of an emptyhead who got paid some bucks to pose for Leonardo. I think there is very little going on behind those eyes. Really---she just seems kind of blank and vacant, and therefore a good "canvas" for people to "project" all kinds of wonders onto. Probably exactly what Leonardo saw.

Posted by: annette on December 16, 2005 12:26 PM

The most interesting recent research on the Mona Lisa that I've heard about is Margaret Livingstone's. I think it's a pretty convincing explanation of the enigmatic smile.

Posted by: Ken Hirsch on December 16, 2005 01:41 PM

<Tongue partially in cheek> Who taught the software to recognize emotion on faces? Computer geeks? Probably male computer geeks, most likely? Since I work in the industry I think I can safely say that it probably isn't a very good measure. </Tongue partially in cheek>

Posted by: Yahmdallah on December 16, 2005 01:42 PM

The mystery of ML is why she is 83% happy. To describe it is not to explain it.

That's the problem with the scientist's dingbat ideal of "if it ain't measurable it don't exist". Behaviors can be measured, but the intentions behind them can't. So hell, just ignore ‘em! That's why science winds up viewing man as a zombie reacting to stimuli; they've blinkered themselves to the rest of the situation because it's not quantifiable.

I grew up around scientists and I swear I never met a smart one.

Posted by: Brian on December 16, 2005 01:52 PM

Brian wrote:
Behaviors can be measured, but the intentions behind them can't. So hell, just ignore ‘em! That's why science winds up viewing man as a zombie reacting to stimuli; they've blinkered themselves to the rest of the situation because it's not quantifiable.

Behaviorism hasn't been popular among scientists for decades, so I don't know what you're on about. As for this story, "83% happy" isn't supposed to reflect her inner emotional state,it's just talking about the characteristic facial expressions associated with different emotions. And the press likes to introduce these stories in a way that make them sound sillier than they actually are when you read the fine print--it's safe to assume the numbers reported were never intended to be anything more than the response of their particular facial-recognition program, rather than any sort of "objective" measure. The article did say In what they viewed as a fun demonstration of technology rather than a serious experiment, and later it said Harro Stokman, a professor at the University of Amsterdam involved in the experiment, said the researchers knew the results would be unscientific — the software isn't designed to register subtle emotions. So it couldn't detect the hint of sexual suggestion or disdain many have read into Mona Lisa's eyes. and Jim Wayman, a biometrics researcher at San Jose State University agreed.

"It's hocus pocus, not serious science," Wayman said. "But it's good for a laugh, and it doesn't hurt anybody.

Posted by: Jesse M. on December 16, 2005 03:43 PM

This type of research has been around for a long time. I've been meaning inter-library loan a copy of Paul Ekman's book, Unmasking the Face: A Guide to Recognizing Emotions from Facial Clues.

I came across another book by him: Telling Lies: Clues to deceit in the marketplace, politics, and marriage which is related and rather interesting.

His research suggests that there are basic emotions which translate into certain expressions regardless of your geography, and it's possible to get better at identifying them. It doesn't give you the why behind Mona Lisa's smile, but I still find it intriguing.

Posted by: claire on December 16, 2005 03:45 PM

Jesse: I don't know what you're on about.

That's okay, it takes decades for the world to appreciate genius.

Posted by: Brian on December 16, 2005 05:43 PM

It looks to me like she *really* has to go to the bathroom and is desparate for Leonardo to hurry up and finish the modeling session!

Posted by: Peter on December 16, 2005 07:55 PM

Taking the emotions in reverse order.

"Did the baby just kick?"

"This sitting's taking too long."

"Oh God, the inlaws are coming over tonight."

"That's the filthiest joke he's told yet. It's funny. But it's filthy."

"We're having a baby."

Posted by: Alan Kellogg on December 17, 2005 03:46 AM


Post a comment
Name:


Email Address:


URL:


Comments:


Remember your info?