BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Geodesic Methods for Interactive Image Segmentation using Finsler 
 metrics - Laurent Cohen (CNRS & Université Paris-Dauphine )
DTSTART:20170906T080000Z
DTEND:20170906T085000Z
UID:TALK78061@talks.cam.ac.uk
CONTACT:INI IT
DESCRIPTION:<span><span>Minimal paths have been used for long as an intera
 ctive tool to find edges or tubular structures as cost minimizing curves. 
 The user usually provides start and end points on the image and gets the m
 inimal path as output. These minimal paths correspond to minimal geodesics
  according to some adapted metric. They are a way to find a (set of) curve
 (s) globally minimizing the geodesic active contours energy. Finding a geo
 desic distance can be solved by the Eikonal equation using the fast and ef
 ficient Fast Marching method. <br>Different metrics can be adapted to vari
 ous problems. In the past years we have introduced different extensions of
  these minimal paths that improve either the interactive aspects or the re
 sults. For example\, the metric can take into account both scale and orien
 tation of the path. This leads to solving an anisotropic minimal path in a
  2D or 3D+radius space. <br>We recently introduced the use of Finsler metr
 ics allowing to take into account the local curvature in order to smooth t
 he path. It can also be adapted to take into account a region term inside 
 the closed curve formed by a set of minimal geodesics. &nbsp\;<br></span><
 span><br>Co-authors: Da Chen and J.-M. Mirebeau</span><span><br><br></span
 ></span>
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR