Snap n' shop: Visual search-based mobile shopping made a breeze by machine and crowd intelligence

The increasing popularity of smartphones has significantly changed the way we live. Today's powerful mobile systems provide us with all kinds of convenient services. Thanks to the wide variety of available apps, it has never been so easy for people to shop, to navigate, and to communicate with others. However, for some tasks we can further improve the user experience by employing newly developed algorithms. In this work, we try to improve visual search based mobile shopping experience by using machine and crowd intelligence. In particular, our system enables precise object selection, which would lead to more accurate visual search results. We also use crowdsourcing to further extend the system's prowess. We conduct experiments on user interface design and retrieval performance, which validate the effectiveness and ease of use of the proposed system. Meanwhile, components in the system are quite modular, allowing the flexibility of adding or improving different modules of the whole system.