Colloquium/Seminar

YearMonth
2017 Jan   Feb   Mar   Apr   May   Jun   Jul   Aug   Oct   Nov   Dec  
2016 Jan   Feb   Mar   Apr   May   Jun   Jul   Aug   Oct   Nov   Dec  
2015 Jan   Feb   Mar   Apr   May   Jun   Aug   Sep   Oct   Nov   Dec  
2014 Jan   Feb   Mar   Apr   May   Jun   Jul   Aug   Sep   Oct   Nov   Dec  
2013 Jan   Feb   Mar   Apr   May   Jun   Aug   Sep   Nov   Dec  
2012 Jan   Feb   Apr   May   Jun   Jul   Aug   Sep   Nov   Dec  
2011 Jan   Feb   Mar   Apr   May   Jun   Jul   Aug   Sep   Oct   Nov   Dec  
2010 Jan   Feb   Mar   Apr   May   Jun   Sep   Oct   Nov   Dec  
2009 Jan   Feb   Mar   Apr   May   Jun   Jul   Aug   Sep   Oct   Nov   Dec  
2008 Jan   Feb   Mar   Apr   May   Jun   Jul   Aug   Sep   Oct   Nov   Dec  
2007 Jan   Feb   Mar   Apr   May   Jun   Jul   Aug   Sep   Oct   Nov   Dec  
2006 Jan   Feb   Mar   Apr   May   Jun   Jul   Sep   Oct   Nov   Dec  
2005 Jan   Feb   Mar   Apr   May   Jun   Jul   Aug   Sep   Oct   Nov   Dec  
2004 Jan   Feb   Mar   Apr   May   Aug   Sep   Oct   Nov   Dec  

Event(s) on October 2005


  • Tuesday, 25th October, 2005

    Title: Tracking Edges, Corners and Vertices in an Image.
    Speaker: Dr. Christian Rau, Department of Mathematics, Hong Kong Baptist University and, Mathematical Sciences Institute, Australian National University, Australia
    Time/Place: 11:30  -  12:30
    FSC1217
    Abstract: An ever-recurring task in image processing and spatial statistics is the recovery of edges. We interpret an edge as a curve of discontinuity points in an otherwise smooth regression surface observed with noise, with the design points representing planar observation sites. In earlier work, we developed an estimator of a single (connected) edge, which is based on the idea of 'tracking' the edge through the plane once a point near enough to it has been found. This method uses a locally parametric model and least-squares to estimate the tangent at a given point on the edge. In most cases of practical interest, however, the edges may join at points called 'corners' and 'vertices' at which the edge has no unique tangent, and tracking may either introduce bias or miss part of the edge altogether. In this talk, we extend the tracking approach to cater for this situation. A theoretical analysis as well as artificial and real-world numerical examples are given, along with some open problems for future research.