e perceive objects in the world as meaningful entities only over certain ranges of scale. A simple example is the concept of a branch of a tree, which makes sense only at a scale from, say, a few centimeters to at most a few meters, It is meaningless to discuss the tree concept at the nanometer or kilometer level. At those scales, it is more relevant to talk about the molecules that form the leaves of the tree, and the forest in which the tree grows, respectively.
This fact that objects in the world appear in different ways depending on the scale of observation has important implications if one aims at describing them. It shows that the notion of scale is of utmost importance when processing unknown measurement data by automatic methods. In their seminal works, Witkin (1983) and Koenderink (1984) proposed to approach this problem by representing image structures at different scales in a so-called scale-space representation. Traditional scale-space theory building on this work, however, does not address the problem of how to select local appropriate scales for further analysis.
After a brief review of the main ideas behind a scale-space representation, I will in this talk describe a recently developed systematic methodology for generating hypotheses about interesting scale levels in image data---based on a general principle stating that local extrema over scales of different combinations of normalized derivatives are likely candidates to correspond to interesting image structures. Specifically, it will be shown how this idea can be used for formulating feature detectors which automatically adapt their local scales of processing to the local image structure.
Support for the proposed methodology will be presented in terms of general study of the scale selection method under rescalings of the input data, as well as more detailed analysis of how the scale selection method performs when integrated with various types of feature detection modules and then applied to characteristic image patterns. Moreover, it will be illustrated by a rich set of experiments how this scale selection approach applies to various types of feature detection problems in early vision.
In many computer vision applications, the poor performance of the low-level vision modules constitutes a major bottle-neck. It will be argued that the inclusion of mechanisms for automatic scale selection is essential if we are to construct vision systems to analyse complex unknown environments.
1996. 490-490 p.