The Community for Technology Leaders
Green Image
Caching has been widely used in the mobile environments to improve system performance. However, traditional semantic caching methodology was proposed for structural data such as 2-D location, and cannot be directly used for image data accessing: First, traditional caching relies on exact match and therefore is unsuitable for similarity-based queries. Second, the description of cached data is defined based on query context instead of data content, which leads to inefficient use of storage. Third, the description of cached data does not reflect the popularity of the data, making it inefficient in providing QoS-related services. To facilitate content-based image retrieval in mobile environments, we propose a semantic-aware image caching scheme (SAIC) in this paper. The proposed scheme can efficiently utilize the cache space and significantly reduce the cost of image retrieval. The proposed SAIC scheme is based on several innovative ideas: 1) multi-level partitioning of the semantic space, 2) association and Bayesian probability based content prediction, 3) constraint-based representation method showing the semantic similarity between images, 4) non-flooding query processing, and 5) adaptive QoS-aware cache consistency maintenance. The proposed model is introduced and through extensive simulation its behavior has been compared against two state-of-the-art caching schemes as advanced in the literature.
Database semantics, Mobile Computing, Information Search and Retrieval, Image/video retrieval, Content Analysis and Indexing

A. R. Hurson and B. Yang, "Semantic-Aware and QoS-Aware Image Caching in Ad Hoc Networks," in IEEE Transactions on Knowledge & Data Engineering, vol. 19, no. , pp. 1694-1707, 2007.
95 ms
(Ver 3.3 (11022016))