-->

Summary and outlook

Scale-space theory provides a framework for modelling image structures at multiple scales, and the output from the scale-space representation can be used as input to a variety of early visual tasks. Operations like feature detection, feature classification and shape computation can be expressed directly in terms of (possibly non-linear) combinations of Gaussian derivatives at multiple scales. In this sense, the scale-space representation can serve as a basis for early vision. In the terminology of Kuhn [], scale-space theory can also be seen as a promising seed to a new paradigm for computer vision. During the last few decades a number of other approaches to multi-scale representations have been developed, which are more or less related to scale-space theory, notably the theories of pyramids [, , ], wavelets [, ] and multi-grid methods []. Despite their qualitative differences, the increasing popularity of each of these approaches indicates that the crucial notion of scale is increasingly appreciated by the computer vision community and by researchers in other fields. The goal of this presentation has been to provide a few selected pointers to central ideas behind the recently developed scale-space theory and to show examples of straightforward applications. Main issues of current research concern the incorporation of scale-space techniques into increasingly complex visual modules and the extension to non-linear scale-space concepts more committed to specific tasks at hand [].