This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
MDL patch correspondences on unlabeled images with occlusions
Anchorage, AK, USA
June 23-June 28
ISBN: 978-1-4244-2339-2
Johan Karlsson, Centre for Mathematical Sciences, Lund University, Sweden
Kalle Astrom, Centre for Mathematical Sciences, Lund University, Sweden
Automatic construction of Shape and Appearance Models from examples via establishing correspondences across the training set has been successful in the last decades. One successful measure for establishing correspondences of high quality is minimum description length (MDL). In other approaches it has been shown that parts+geometry models which model the appearance of parts of the object and the geometric relation between the parts have been successful for automatic model building. In this paper it is shown how to fuse the above approaches and use MDL to fully automatically build optimal parts+geometry models from unlabeled images.
Citation:
Johan Karlsson, Kalle Astrom, "MDL patch correspondences on unlabeled images with occlusions," cvprw, pp.1-8, 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, 2008
Usage of this product signifies your acceptance of the Terms of Use.