'Magic Closet' Keeps You Work-Appropriate
A woman swipes through shirt suggestions from Magic Closet.
CREDIT: From "MagicCloset2 5" by NUS LV on YouTube
Not sure what to wear to that New Year's party? Give Si Liu and Shuicheng Yan's new "Magic Closet" a wave, and it'll come up with suggestions.
The Magic Closet is a computer program, under development at the National University of Singapore and the Chinese Academy of Science, which suggests outfits for different occasions. It's motion-controlled — like a Microsoft Kinect game — and has the artificial intelligence to suggest occasion- and color-appropriate outfits.
Although the Magic Closet is a lab project, it's almost ready for store shelves, Liu and Yan, computer scientists at the National University of Singapore, wrote to TechNewsDaily in a joint email.
"This kind of system is ready to use in the market," Liu and Yan said. "The Magic Closet can be used as a mobile personalized clothes management app. It can also be used as a plug-in system in online shops (e.g., amazon.com, ebay.com) to help customers to choose suitable clothes."
The closet software makes outfit suggestions for 10 different occasions, including weddings, funerals, work and dates. It can also match clothing to an item the user already knows he or she wants to wear, such as those lucky red pants. The software draws clothing suggestions from both the user's own wardrobe and from online shops. [SEE ALSO: The 10 Most Stunning Video Games]
To figure out rules for the Magic Closet to follow, Liu, Yan and their team gathered more than 24,000 photos of outfits from online shopping sites and photo-sharing communities such as Flickr. The scientists looked for photos that were highly rated by other people, in hopes of catching especially fashionable combinations. They also asked people on Amazon's Mechanical Turk, a website where people get paid to finish small tasks online, to match their photos with occasions and such keywords as "V-shape collar" or "plaid pattern."
The team then wrote a computer program to analyze the tagged photos, looking for rules the scientists could add to the Magic Closet's recommendation system.
The program could still use some work before it becomes a commercial product, Liu and Yan said. The researchers want to develop more sophisticated matching rules. They also want to improve the Magic Closet's ability to detect users' bodies.
Now, users may glam in front of the camera in different poses and the clothes they see on-screen will follow them. That only works if they face forward, however; if they try to get a side view, the program doesn't know where to overlay clothes on-screen. Liu and Yan said their team will work on fixing that.
This isn't the first time Yan and Liu have worked on computer programs that recognize clothes. In June, they presented a program that takes ordinary street photos, identifies what clothes are in the photo, and suggests similar clothes that users can buy in stores.
They're interested in getting computer programs to recognize clothes because there's a huge, growing market for clothes, especially in China, the researchers wrote in a paper about the Magic Closet. Surely some of those future shoppers would appreciate a little help.