Beyond query by example

摘要: This paper considers some of the problems we found trying to extract meaning from images in database applications, and proposes ways solve them. We argue that an image is ill-defined entity, it not general possible derive user wants. Rather, should be content with a correlation between intended simple perceptual clues databases can extract. Rather than working on impossible task extracting unambiguous images, provide tools he needs drive areas feature space where "interesting" are.