Scale-Space

Scale-space theory is a framework for multiscale image representation, which has been developed by the computer vision community with complementary motivations from physics and biologic vision. The idea is to handle the multiscale nature of real-world objects, which implies that objects may be perceived in different ways depending on the scale of observation. If one aims to develop automatic algorithms for interpreting images of unknown scenes, there is no way to know a priori what scales are relevant. Hence, the only reasonable approach is to consider representations at all scales simultaneously. From axiomatic derivations is has been shown that given the requirement that coarse-scale representations should correspond to true simplifications of fine scale structures, convolution with Gaussian kernels and Gaussian derivatives is singled out as a canonical class of image operators for the earliest stages of visual processing. These image operators can be used as basis to solve a large variety of visual tasks, including feature detection, feature classification, stereo matching, motion descriptors, shape cues, and image-based recognition. By complementing scale-space representation with a module for automatic scale selection based on the maximization of normalized derivatives over scales, early visual modules can be made scale invariant. In this way, visual modules can adapt automatically to the unknown scale variations that may occur because of objects and substructures of varying physical size as well as objects with varying distances to the camera. An interesting similarity to biologic vision is that the scale-space operators resemble closely receptive field profiles registered in neurophysiologic studies of the mammalian retina and visual cortex. Figure 1: (top left) A grey-level image of size 560 × 420 pixels. (top right)–(bottom right) Scale-space representations computed at scale levels t = 1, 8 and 64 (in pixel units).