An approach to image retrieval for image databases

In this paper, a method is discussed to store and retrieve images efficiently from an image database on the basis of the data structure called E() representation. The E() representation is a spatial knowledge representation preserving the spatial information between objects embedded in symbolic images as an iconic index for the purpose of efficient image retrieval. The image retrieval method is invariant under, at least, the affine transformation (i.e. translation, rotation and scale) and is able to deal with substantional object occlusion. A metric is defined to express similarity between symbolic images. Initial experiments carried out for two applications show that the image retrieval method is very efficient and robust to similarity retrieval in image databases. Together with the inherent high parallelism, it makes the method a promising image retrieval method.