HIERARCHICAL SEMANTIC-BASED INDEX FOR AD HOC IMAGE RETRIEVAL

Abstract

Ad hoc networks have received considerable research attention by provisions of wireless communications without location limitations and pre-built fixed infrastructure. Because of the absence of any static support infrastructure, ad hoc networks are prone to several limitations such as bandwidth, connectivity, and power. The traditional content-based image retrieval approaches employed in ad hoc networks may result in either high search cost or low fault tolerance. In this paper, we propose and analyze a decentralized nonflooding image retrieval scheme in multi-hop mobile ad hoc networks ─ Semantic Ad hoc Image Retrieval (SAIR). The novelty of SAIR stems from several factors including: (1) representation of image contents using first-order logic expressions; (2) clustering mobile nodes based on their data contents; (3) organizing image data with a hierarchical semantic-based indexing infrastructure; (4) performing content-based image retrieval within a reduced scope of mobile nodes. Through extensive simulations, we show that relative to the flooding strategy, SAIR can retrieve the semantically most similar image objects by accessing only a small portion of the mobile nodes with much lower search cost. Moreover, it is scalable to large network sizes and large number of data objects.