Follow for more talkers

Study: Your fashion sense can reveal trunkload of info about your life

A fashion recognition algorithm was used on photographs geolocated from 37 large cities

Avatar photo

Published

on
Beautiful woman standing on a crosswalk and holding a suitcase

By Joe Morgan via SWNS

Fashion trends can accurately predict which part of a city a person comes from, according to new research.

What you wear can also show whether a person thinks of themselves as trendy or progressive as well as what is happening in the city at that time as predicted by state-of-the-art artificial intelligence.

Computer scientists have been able to automatically draw 'underground maps' that can accurately segment cities into areas with similar fashion sense.

Style can also predict interests, discover events and forecast fashion trends in certain areas of the city, according to anthropologists.

The research uses a fashion recognition algorithm on photographs geolocated from 37 large cities and then the typical combination of those styles within a given radius.

Researchers were then able to find unique neighborhoods in a city, depending on how a person dressed, and find similar neighborhoods across cities, for example being able to translate Sydney's Bondi Beach to New York's Coney Island.

via GIPHY

Professor Kavita Bala, Dean at the University of Cornell college of computer science, said: "There’s just so much you learn about human beings by looking at the images they post about themselves.

“You learn about their culture, their style, how they interact with people, and what’s important to them.”

“There’s a lot of individual personality that comes across in how people dress, so analyzing fashion around the world was one of our first goals.

“The way anthropologists study culture is they go to a location, do interviews with local people and observe.

“An automated tool like this would empower them to do more.

"It could help them discover new phenomena that they didn’t even know about, and let them drill down deeper within their analysis of why this phenomenon exists.”

Utkarsh Mall, doctoral student at Cornell University, said: “The question I’ve been interested in is, can we use millions of images from social media or satellite images to discover something interesting about the world?

“We are excited about this idea that some future anthropologist could just run these tools and understand us – take the ‘underground pulse’ of the city – despite not having lived with us.”

The new AI was presented at the Winter Conference on Applications of Computer Vision.

Stories and infographics by ‘Talker Research’ are available to download & ready to use. Stories and videos by ‘Talker News’ are managed by SWNS. To license content for editorial or commercial use and to see the full scope of SWNS content, please email [email protected] or submit an inquiry via our contact form.

Top Talkers