Paper Info
Title
Hierarchical Vibrations: A Structural Decomposition Approach for Image Analysis
Abstract
We present results demonstrating that using a hierarchy of finite element vibration modes in an evolutionary deformable shape search provides a new interesting approach for the localization and segmentation of specific objects in 2D images. The design and coupling of the different levels of the shape hierarchy results in a multi---resolution shape space, which can be exploited in top---down part---based shape matching. The proposed strategy allows for segmenting complex objects from images, classification, as well as localization of the desired object under occlusions. It avoids misregistration by resolving several drawbacks inherent to standard shape---based approaches, which either cannot adequately represent non---linear variations, or rely on exhaustive prior training.
Year
DOI
Venue
2009
10.1007/978-3-642-03641-5_24
EMMCVPR
Keywords
Field
DocType
standard shape,resolution shape space,different level,evolutionary deformable shape search,linear variation,finite element vibration mode,shape matching,shape hierarchy result,exhaustive prior training,complex object,structural decomposition approach,image analysis,hierarchical vibrations,image classification,top down,finite element
Computer vision,Active shape model,Coupling,Segmentation,Computer science,Finite element method,Artificial intelligence,Normal mode,Vibration,Hierarchy,Probability density function
Conference
Volume
ISSN
Citations 
5681
0302-9743
1
PageRank 
References 
Authors
0.34
30
2
Name
Order
Citations
PageRank
Karin Engel1314.88
Klaus D. Toennies28812.36