Steerable-scalable kernels for edge detection and junction analysis

Abstract

Families of kernels that are useful in a variety of early vision algorithms may be obtained by rotating and scaling in a continuum a 'template' kernel. These multiscale multi-orientation families may be approximated by linear interpolation of a discrete finite set of appropriate 'basis' kernels. A scheme for generating such a basis, together with the appropriate interpolation weights, is described. Unlike previous schemes by Perona and Simoncelli et al., it is guaranteed to generate the most parsimonious basic kernel. Additionally, it is shown how to exploit two symmetries in edge-detection kernels for reducing storage and computational costs, and for generating simultaneously endstop- and junction-tuned filters for free.