Toward perception-based image retrieval

Abstract

Since a content based image retrieval (CBIR) system services people, its image characterization and similarity measure must closely follow perceptual characteristics. The authors enumerate a few psychological and physiological invariants and show how they can be considered by a CBIR system. They propose distance functions to measure perceptual similarity for color, shape and spatial distribution. In addition, the authors believe that an image search engine should model after their visual system, which adjusts to the environment and adapts to the visual goals. They show that they can decompose the visual front-end into filters of different functions and resolutions. A pipeline of filters can be dynamically constructed to meet the requirement of a search task and to adapt to an individual's search objectives.