481 test subjects participated in the research of Theo Gevers and Albert Ali Salah. The researchers made a video recording of a posed smile and a spontaneous smile for each participant. The subjects also were also asked to look angry, happy, sad, surprised and scared. Gevers and Salah analysed certain characteristics, such as how quickly the corners of the mouth turn upwards. This knowledge can be applied to computer software which guesses ages, recognise emotions and analyse human behaviour.
The researchers also asked the test subjects to look at images of other test subjects. They had to guess the age of those people and state how attractive they found them. They were also asked to judge character traits, such as whether the person is helpful by nature, or if that person is perhaps in love?
The data collected allowed the researchers to develop software that can estimate people's age. The software takes into account whether someone is happy, sad or angry, and adjusts its estimate accordingly. The software appears to be slightly better at estimating ages than humans. On average, humans' estimates are seven years off , while the computer is six years off on average .
The research of Gevers and Salah also shows that you look younger when you smile, but only if you are over forty. If you are under forty, you should look neutral if you want to come across younger.
Smile Database: http://www.uva-nemo.org/
Share this story on Facebook, Twitter, and Google:Other social bookmarking and sharing tools:
Story Source:
The above story is reprinted from materials provided by Universiteit van Amsterdam (UVA).
Note: Materials may be edited for content and length. For further information, please contact the source cited above.
Note: If no author is given, the source is cited instead.
Disclaimer: This article is not intended to provide medical advice, diagnosis or treatment. Views expressed here do not necessarily reflect those of ScienceDaily or its staff.
