Beyond Query by Example Meaningless Responses

This paper considers some of the problems we found trying to extract meaning from images in database applications, and proposes some ways to solve them. We argue that the meaning of an image is an ill-deened entity, and it is not in general possible to derive from an image the meaning that the user of the database wants. Rather, we should be content with a correlation between the intended meaning and simple perceptual clues that databases can extract. Rather than working on the impossible task of extracting unambigu-ous meaning from images, we should provide the user with the tools he needs to drive the database in the areas of the feature space where \interesting" images are. It is a common experience for the user of image databases to be somehow frustrated by the results of their searches. Consider Fig. 1. This is the Figure 1: result of a query done with one of the best image database engines currently available. (The image on the top left corner is the query.) Some of the images returned are somewhat disappointing. Yet, if you look at them closely, you