Automatic Tagging of Clothing Images

Abstract

This paper presents a computer vision clothing auto-tagging algorithm. Tagging is highly demanded in e-commerce as a tool to create a rich uniform set of annotations. The annotations improve catalog organization, statistics, and can be used for interactive catalog search by consumer photos. The proposed algorithm predicts length, design, and color attributes for an arbitrary number of clothing items in an image. The modular structure of the proposed system allows reconfiguration for other sets of tags and tagging tasks not related to clothing.