From Global to Local Statistical Shape Priors : Novel Methods to Obtain Accurate Reconstruction Results with a Limited Amount of Training Shapes
Softcover reprint of the original 1st ed. 2017
by
Carsten Last
Book Details
Format
Paperback / Softback
Book Series
Studies in Systems, Decision and Control
ISBN-10
3319851691
ISBN-13
9783319851693
Edition
Softcover reprint of the original 1st ed. 2017
Publisher
Springer International Publishing AG
Imprint
Springer International Publishing AG
Country of Manufacture
GB
Country of Publication
GB
Publication Date
Jul 21st, 2018
Print length
259 Pages
Product Classification:
Artificial intelligenceArtificial intelligence (AI)Image processing
Ksh 16,200.00
Werezi Extended Catalogue
0 in stock
Delivery Location
Delivery fee: Select location
Secure
Quality
Fast
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.
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.
Get From Global to Local Statistical Shape Priors by at the best price and quality guaranteed only at Werezi Africa's largest book ecommerce store. The book was published by Springer International Publishing AG and it has pages.
