Similarity search on metric data of outsourced lung images

Abstract

The setting in which similarity querying of metric data is outsourced to a service provider. Users query the server for the most similar data objects and data is revealed only to trusted users and not to anyone else. The need for privacy may be due to the data being sensitive (eg. in medicine), valuable (eg. in astronomy) or otherwise confidential. In this work, image retrieval on metric data of outsourced lung images using parallelism from various sources like hospitals, scan centers and public database available in internet are handled. The proposed similarity search for content based image retrieval involves dynamic similarity querying on metric data from segmented and extracted texture features database. With real data, the technique is capable of offering privacy while enabling efficient and accurate processing of similarity queries.