Communications of the ACM
Computer 'anthropologists' Study Global Fashion
Cornell University researchers are figuring out ways to analyze the billions of photographs uploaded to photo-sharing services and social media platforms each day, through deep-learning methods.
Credit: Cornell Chronicle
Researchers at Cornell University are using deep-learning methods to analyze billions of photos uploaded to photo-sharing services and social media platforms.
"We present a framework for visual discovery at scale, analyzing clothing and fashion across millions of images of people around the world and spanning several years," says Cornell professor Kavita Bala.
The researchers used deep learning to detect attributes such as the color or sleeve length of shirts in millions of images.
Bala says they produced an analysis of global and per-city fashion choices and spatiotemporal trends.
The researchers focused on fashion trends based on time and location, and used facial-recognition technology to exclude photos that lacked people in them. The team then developed an object-recognition program to identify items of clothing.
"The combination of big data, machine learning, computer vision, and automated-analysis algorithms makes for a very powerful analysis tool in visual discovery of fashion and other areas," says Cornell's Kevin Matzen.
From Cornell Chronicle
View Full Article
Abstracts Copyright © 2017 Information Inc., Bethesda, Maryland, USA
No entries found