Researchers from ETH Zurich's Computer Vision have developed an iOS smartphone app that employs adaptive algorithms to redirect users to online shops selling products they like using a database and assigning number combinations to specific clothing traits.
"Our goal is to make [it] possible to buy every fashion photo on the Internet," says Matthias Dantone, who along with the two other researchers founded Fashwell to continue working on the app. Dantone notes the app enables users to "like" a photo on Instagram or comment on it with the hashtag #wtfash and then immediately receive a message with the outfit and similar items of apparel. "With one click, you are then directed to the online shop that offers the product," he says.
Once someone posts a photo on Instagram, the adaptive algorithm registers it and instantly determines whether it is a fashion image, and it can make all of the articles of clothing available for purchase, according to Dantone. The database the researchers compiled includes the full inventory of more than 70 Swiss online shops.
Dantone says the algorithm then assigns certain number combinations for each specific clothing characteristic. Once a photo is liked or commented on, the algorithm automatically looks for similar items in the database and transmits the online shop and price to the app user.
From ETH Zurich
View Full Article
Abstracts Copyright © 2015 Information Inc., Bethesda, Maryland, USA