<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<item>
  <id>05858772</id>
  <dt>a</dt>
  <an>05858772</an>
  <augroup>
    <au>Heyvaert, Micha\"el</au>
    <au>Van Hamme, David</au>
    <au>Coppens, Jonas</au>
    <au>Veelaert, Peter</au>
  </augroup>
  <ti>Combining geometric edge detectors for feature detection.</ti>
  <so>Blanc-Talon, Jacques (ed.) et al., Advanced concepts for intelligent vision systems. 12th international conference, ACIVS 2010, Sydney, Australia, December 13--16, 2010. Proceedings, Part I. Berlin: Springer (ISBN 978-3-642-17687-6/pbk). Lecture Notes in Computer Science 6474, 221-232 (2010).</so>
  <py>2010</py>
  <pu>Berlin: Springer</pu>
  <lagroup>
    <la>EN</la>
  </lagroup>
  <ccgroup>
  </ccgroup>
  <utgroup>
  </utgroup>
  <cigroup>
  </cigroup>
  <ligroup>
    <li>doi:10.1007/978-3-642-17688-3_22</li>
  </ligroup>
  <abgroup>
    <ab>Summary: We propose a novel framework for the analysis and modeling of discrete edge filters, based on the notion of signed rays. This framework will allow us to easily deduce the geometric and localization properties of a family of first-order filters, and use this information to design custom filter banks for specific applications. As an example, a set of angle-selective corner detectors is constructed for the detection of buildings in video sequences. This clearly illustrates the merit of the theory for solving practical recognition problems.</ab>
    <rv></rv>
  </abgroup>
</item>