Toward Feature Algebras in Visual Databases: The Case for a Histogram Algebra

Abstract

Searching and managing large archives of visual data, such as images and video, is made hard by the lack of proper integration between the visual aspects of the problem (image processing, motion estimation, feature extraction ...) and its database aspects (defining visual data as data types in a database). In this paper, we argue that image database languages can be built based on feature algebras, and demonstrate how such a feature algebra can be built in the case of one of the most popular image characterization techniques: histograms.