Maximally Stable Corner Clusters: A novel distinguished region detector and descriptor

1st Austrian Cognitive Vision Workshop, OCG-Schriftenreihe, ISBN 3-85403-186-6, pp. 59-66, <a href="http://www.acin.tuwien.ac.at/groups/robtec/acvw/index.html" target="New">ACVW 05</a>

OCG Oesterreichische Computer Gesellschaft

Vienna, Austria

OCG: Oesterreichische Computer Gesellschaft

We propose a novel distinguished region detector called Maximally Stable Corner Cluster
detector (MSCC). It is complementary to existing approaches like Harris-corner detectors,
Difference of Gaussian detectors (DoG) or Maximally Stable Extremal Regions (MSER). The
basic idea is to find distinguished regions by looking at clusters of interest points and using the
concept of maximal stableness across scale. Additionally, we propose a novel descriptor ideally
suited for regions detected by MSCC. It is based on the 2D joint occurrence histograms of
corner orientations. We demonstrate its performance and compare it against other competitive
detectors and descriptors recently evaluated by Mikolajczyk and Schmidt.