From Global to Local Statistical Shape Priors Novel Methods to Obtain Accurate Reconstruction Results with a Limited Amount of Training Shapes /

This book proposes a new approach to handle the problem of limited training data. Common approaches to cope with this problem are to model the shape variability independently across predefined segments or to allow artificial shape variations that cannot be explained through the training data, both o...

Full description

Bibliographic Details
Main Author: Last, Carsten (Author)
Corporate Author: SpringerLink (Online service)
Format: e-Book
Language:English
Published: Cham : Springer International Publishing : Imprint: Springer, 2017.
Edition:1st ed. 2017.
Series:Studies in Systems, Decision and Control, 98
Subjects:
Computational intelligence.
Artificial intelligence.
Image processing > Digital techniques.
Computer vision.
Computational Intelligence.
Artificial Intelligence.
Computer Imaging, Vision, Pattern Recognition and Graphics.
Online Access:Full-text access
View in OPAC
Description
Summary:This book proposes a new approach to handle the problem of limited training data. Common approaches to cope with this problem are to model the shape variability independently across predefined segments or to allow artificial shape variations that cannot be explained through the training data, both of which have their drawbacks. The approach presented uses a local shape prior in each element of the underlying data domain and couples all local shape priors via smoothness constraints. The book provides a sound mathematical foundation in order to embed this new shape prior formulation into the well-known variational image segmentation framework. The new segmentation approach so obtained allows accurate reconstruction of even complex object classes with only a few training shapes at hand.
Physical Description:XXI, 259 p. 84 illus., 64 illus. in color. online resource.
ISBN:9783319535081
ISSN:2198-4190 ;
DOI:10.1007/978-3-319-53508-1

Similar Items