Mobile Content Based Image Retrieval Architectures

Arif Rahman, Edi Winarko, Moh. Edi Wibowo

Abstract


Mobile device features such as camera and other sensors are evolving rapidly nowadays. Supported by a reliable communications network, it raises new methods in information retrieval. Mobile devices can capture an image with its camera and pass it to the retrieval systems to get the information needed. This system, called Mobile Content-Based Image Retrieval (MCBIR), generally consists of two parts: Offline Database Construction, which create image features database and indexing structure, and Online Image Search, that search images in the database that similar to the user inputs. MCBIR system, based on its computational load and resource needs, can be categorized into three architectural models: client-side, client-server and distributed. These three models were analyzed in three aspects: scalability, latency, and resources. The results show that each architecture has its own characteristics in terms of these aspects and should be considered in the architecture selection phase for MCBIR development.


Full Text: PDF

Refbacks

  • There are currently no refbacks.