Interactive Clothes Searching in Online Stores (12110N)
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 method to automatically analyze clothing images according to a number of characteristics including color, pattern, material, sleeve style, collar style, trouser shape and skirt shape and style. Such a method can be used to classify and organize an online retailer’s stock in order to provide an alternative procedure to browse clothing according to the characteristics mentioned. A user could thus be presented with additional clothing items (i.e., recommendations) based on any clothing characteristic selected.
This method consists of three basic steps: 1) automatic visual recognition of clothing components using a shape-based tree-structure model; 2) a user interface to query a database in order to retrieve items matching a clothing part or design selected by the user; and 3) a clothing database that holds clothing items previously sorted and organized from which the system will retrieve those matching the clothing part or design selected by the user.
Technology Readiness Level 4 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.