Structure Driven Image Database Retrieval

Abstract

A new algorithm is presented which approximates the perceived visual similarity between images. The images are initially transformed into a feature space which captures visual structure, texture and color using a tree of filters. Similarity is the inverse of the distance in this perceptual feature space. Using this algorithm we have constructed an image database system which can perform example based retrieval on large image databases. Using carefully constructed target sets, which limit variation to only a single visual characteristic, retrieval rates are quantitatively compared to those of standard methods. Accepted Advanced in Neural Information Processing 10 (1997). 1 Introduction Without supplementary information, there exists no way to directly measure the similarity between the content of images. In general, one cannot answer a question of the form: "is image A more like image B or image C?" without defining the criteria by which this comparison is to be made. People perform su...