Virtual touring: A Content Based Image Retrieval application

This paper proposes a Content Based Image Retrieval (CBIR) application for searching landmarks and buildings in a city using a smartphone. A user can snap a picture of the building using his smartphone. The application is able to quickly and accurately find the name of the building along with many other interesting information, such as the history of the building and its Wi-Fi availability. We present a novel client-server CBIR application that combines Laplacian-SIFT for feature descriptor, multiple kd-trees for indexing and two levels of geometric verification. We present back-end and front-end Application Programming Interfaces (API) for client-server CBIR applications and we propose a distributed system architecture to support multiple client requests. The application consists of two user interfaces, a web interface and a mobile interface. Image retrieval results demonstrate the accuracy of the system in recognizing buildings.