Magic closet helps unsure dressers

Scientists at the Chinese Academy of Science and the National University of Singapore have developed a clothing-selection system that help people decide what to wear by suggesting clothing from their own wardrobes based on the event they plan to attend.

Scientists at the Chinese Academy of Science and the National University of Singapore have developed a clothing-selection system that help people decide what to wear by suggesting clothing from their own wardrobes based on the event they plan to attend.

HT Image

The Magic Closet first catalogues clothes in a wardrobe, using a Microsoft Kinect camera to identify defining features such as sleeve length, colour and collar type.

Then, when the user asks it for an outfit, the software selects the best matches from its database of 25,000 outfit images, from online shopping websites and photo-sharing site Flickr — and presents pictures of selected items of clothing.

Those database images are then fed into Amazon’s Mechanical Turk labour market, where online workers categorise the outfits.
An attribute or occasion was deemed legitimate when more than half the workers agreed.