000217259 001__ 217259
000217259 005__ 20180913063630.0
000217259 037__ $$aSTUDENT
000217259 245__ $$aDeformable shape models for 2D object segmentation
000217259 269__ $$a2011
000217259 260__ $$c2011
000217259 336__ $$aStudent Projects
000217259 520__ $$aGiven a set of images showing individual 2D instances of an object class, the goal is to learn object class deformation in 2D for segmentation automatically. Class deformation is modelled by linear combinations of basis shapes. Usually, given segmentation data and correspondences, such basis shapes can be easily learned with Principal Component Analysis. Here, we are dealing with unsegmented RGB images. We show how to learn segmentations and deformation sequentially in an iterative framework. Variations of the basic algorithm are explained, tested and compared. In order to introduce smoothness priors and data dependent pairwise terms, Graph-cut can be incorporated. The final results show that explicitly restricting segmentations by a linear subspace of shape deformation, leads to significant improvements.
000217259 6531_ $$aImage segmentation
000217259 6531_ $$aPrincipal Component Analysis
000217259 700__ $$0246809$$aThandiackal, Robin$$g227502
000217259 720_2 $$aPrasad, Mukta$$edir.
000217259 720_2 $$aFerrari, Vittorio$$edir.
000217259 8564_ $$s3314216$$uhttps://infoscience.epfl.ch/record/217259/files/SemesterThesis_RobinThandiackal.pdf$$yn/a$$zn/a
000217259 909C0 $$0252444$$pIBI
000217259 909CO $$ooai:infoscience.tind.io:217259$$pSV$$pSTI
000217259 917Z8 $$x227502
000217259 917Z8 $$x148230
000217259 937__ $$aEPFL-STUDENT-217259
000217259 973__ $$aOTHER
000217259 980__ $$aSTUDENT$$bSEMESTER