Extending SQL to Support Image Content-based Retrieval

M.R.B. Araujo, A. Traina, and C. Traina, Jr. (Brazil)

Keywords

Contentbased image retrieval, Extended SQL, feature extraction, image databases

Abstract

This paper shows a technique to support images in a relational database, so it can fulfill the requirements to be used as the storage mechanism of a PACS (Picture Archiving and Communication System). This support includes the ability to answer similarity queries based on the image content, allowing fast image retrieval based on indexing structures. The main concept enabling this support is the definition of distance functions based on features, which are extracted from the images as they are stored in the database. The proposed extension to the SQL language enables the construction of an interpreter that intercepts the extended commands and translate them to standard SQL, allowing the technique to be used with any relational database server. This extension incorporates the image type to be used as a native data type inside relational database, and provides resources to enable the retrieval of images based on their contents.

Important Links:



Go Back