From Global to Local Statistical Shape Priors

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

  • Carsten Last

Part of the Studies in Systems, Decision and Control book series (SSDC, volume 98)

Table of contents

  1. Front Matter
    Pages i-xxi
  2. Carsten Last
    Pages 1-19
  3. Carsten Last
    Pages 21-51
  4. Carsten Last
    Pages 207-209
  5. Back Matter
    Pages 211-259

About this book

Introduction

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.

Keywords

Global Statistical Shape Priors Pattern Recognition Image Processing Computer Vision Object Segmentation Image Segmentation

Authors and affiliations

  • Carsten Last
    • 1
  1. 1.Institut für Robotik und ProzessinformatTechnische Universität BraunschweigBraunschweigGermany

Bibliographic information

  • DOI https://doi.org/10.1007/978-3-319-53508-1
  • Copyright Information Springer International Publishing AG 2017
  • Publisher Name Springer, Cham
  • eBook Packages Engineering
  • Print ISBN 978-3-319-53507-4
  • Online ISBN 978-3-319-53508-1
  • Series Print ISSN 2198-4182
  • Series Online ISSN 2198-4190
  • About this book