From Global to Local Statistical Shape Priors

Novel Methods to Obtain Accurate Reconstruction Results with a Limited Amount of Training Shapes

Nonfiction, Computers, Advanced Computing, Engineering, Computer Vision, Artificial Intelligence, General Computing
Cover of the book From Global to Local Statistical Shape Priors by Carsten Last, Springer International Publishing
View on Amazon View on AbeBooks View on Kobo View on B.Depository View on eBay View on Walmart
Author: Carsten Last ISBN: 9783319535081
Publisher: Springer International Publishing Publication: March 14, 2017
Imprint: Springer Language: English
Author: Carsten Last
ISBN: 9783319535081
Publisher: Springer International Publishing
Publication: March 14, 2017
Imprint: Springer
Language: English

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.

View on Amazon View on AbeBooks View on Kobo View on B.Depository View on eBay View on Walmart

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.

More books from Springer International Publishing

Cover of the book East German Intellectuals and the Unification of Germany by Carsten Last
Cover of the book Fully Nonlinear PDEs in Real and Complex Geometry and Optics by Carsten Last
Cover of the book Engineering and Applied Sciences Optimization by Carsten Last
Cover of the book Numerical Software Verification by Carsten Last
Cover of the book Provisional Bibliography of Atlases, Floras and Faunas of European Cities: 1600–2014 by Carsten Last
Cover of the book Carbon Management, Technologies, and Trends in Mediterranean Ecosystems by Carsten Last
Cover of the book Ethnographies of Conferences and Trade Fairs by Carsten Last
Cover of the book Computer Vision in Control Systems-1 by Carsten Last
Cover of the book There Is No Theory of Everything by Carsten Last
Cover of the book Exploring Quantum Foundations with Single Photons by Carsten Last
Cover of the book Dynamic Systems Models by Carsten Last
Cover of the book The Feminist Fourth Wave by Carsten Last
Cover of the book Trends in Reconstructive Neurosurgery by Carsten Last
Cover of the book Arming the Confederacy by Carsten Last
Cover of the book Intelligence for Embedded Systems by Carsten Last
We use our own "cookies" and third party cookies to improve services and to see statistical information. By using this website, you agree to our Privacy Policy