Visual Fashion-Product Search at SK Planet
This work addresses the challenge of visual search for fashion products in e-commerce, but it is incremental as it applies existing computer vision techniques to a specific domain.
The authors tackled the problem of defining similarity for fashion-product images without exact ground-truth by defining over 90 fashion-related attributes to represent thousands of styles and combining them with color and appearance features for visual similarity, resulting in a large-scale visual search system for e-commerce.
We build a large-scale visual search system which finds similar product images given a fashion item. Defining similarity among arbitrary fashion-products is still remains a challenging problem, even there is no exact ground-truth. To resolve this problem, we define more than 90 fashion-related attributes, and combination of these attributes can represent thousands of unique fashion-styles. The fashion-attributes are one of the ingredients to define semantic similarity among fashion-product images. To build our system at scale, these fashion-attributes are again used to build an inverted indexing scheme. In addition to these fashion-attributes for semantic similarity, we extract colour and appearance features in a region-of-interest (ROI) of a fashion item for visual similarity. By sharing our approach, we expect active discussion on that how to apply current computer vision research into the e-commerce industry.