| From Global to Local Statistical Shape Priors: Novel Methods to Obtain Accurate Reconstruction Results with a Limited Amount of Training Shapes 2017 Edition Contributor(s): Last, Carsten (Author) |
|
 |
ISBN: 3319535072 ISBN-13: 9783319535074 Publisher: Springer OUR PRICE: $104.49 Product Type: Hardcover - Other Formats Published: March 2017 |
| Additional Information |
| BISAC Categories: - Computers | Computer Vision & Pattern Recognition - Technology & Engineering | Engineering (general) - Computers | Image Processing |
| Dewey: 006.3 |
| Series: Studies in Systems, Decision and Control |
| Physical Information: 0.69" H x 6.14" W x 9.21" (1.27 lbs) 259 pages |
| Descriptions, Reviews, Etc. |
| Publisher Description: 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. |
