Magic Closet: An Occasion-Oriented Clothing Recommendation System (12380N)
IDA Technology Roadmap 2012
This technology falls in the following categories of Singapore's IDA Infocomm Technology Roadmap 2012:
For more information on this technology contact:
This invention is a system for automatic occasion-oriented clothes recommendation. Given a user-input occasion, e.g., wedding, shopping or dating, magic closet intelligently suggests clothing based on a user's own clothes photo album, or automatically pairs the user-specified reference clothes (top or bottoms) with the most suitable combination from online catalogues. Magic Closet recommendations are based on two criteria. One criterion is appropriateness, e.g., compared to suit pants, a cocktail dress is a more appropriate selection for a banquet occasion. The other criterion is aesthetics, e.g., a red t-shirt better matches white pants than green pants.
To narrow the semantic gap between the low-level features of clothes and the high-level occasion categories, middle-level clothes attributes (e.g., clothes category, color, pattern) are adopted as a bridge. More specifically, the clothes attributes are treated as latent variables in a latent Support Vector Machine (SVM)-based recommendation model. The wearing appropriately criterion is described in the model through a feature-occasion potential and an attribute-occasion potential, while the aesthetics criterion is expressed by an attribute-attribute potential.
Technology Readiness Level 6 on the scale by the Ministry of Defence Singapore.
About the Research Group
Prof. Yan Shuicheng leads the Learning and Vision Research Group in the Department of Electrical and Computer Engineering at NUS. In the past five years, Prof. Yan and his team have secured over 7M in funding from various research grants.