Advances in Computer Vision and Pattern Recognition

Hierarchical Perceptual Grouping for Object Recognition

Theoretical Views and Gestalt-Law Applications

Authors: Michaelsen, Eckart, Meidow, Jochen

Free Preview
  • The first and only book to describe the approach to nested hierarchical perceptual grouping
  • Presents a roundup of all relevant Gestalt laws in a single source
  • Discusses all theoretical views on the problem, including syntactic, probabilistic, and algebraic perspectives
see more benefits

Buy this book

eBook $89.00
price for USA in USD (gross)
  • ISBN 978-3-030-04040-6
  • Digitally watermarked, DRM-free
  • Included format: PDF, EPUB
  • ebooks can be used on all reading devices
  • Immediate eBook download after purchase
Hardcover $119.99
price for USA in USD
  • ISBN 978-3-030-04039-0
  • Free shipping for individuals worldwide
  • Usually dispatched within 3 to 5 business days.
About this book

This unique text/reference presents a unified approach to the formulation of Gestalt laws for perceptual grouping, and the construction of nested hierarchies by aggregation utilizing these laws. The book also describes the extraction of such constructions from noisy images showing man-made objects and clutter. Each Gestalt operation is introduced in a separate, self-contained chapter, together with application examples and a brief literature review. These are then brought together in an algebraic closure chapter, followed by chapters that connect the method to the data – i.e., the extraction of primitives from images, cooperation with machine-readable knowledge, and cooperation with machine learning.

Topics and features: offers the first unified approach to nested hierarchical perceptual grouping; presents a review of all relevant Gestalt laws in a single source; covers reflection symmetry, frieze symmetry, rotational symmetry, parallelism and rectangular settings, contour prolongation, and lattices; describes the problem from all theoretical viewpoints, including syntactic, probabilistic, and algebraic perspectives; discusses issues important to practical application, such as primitive extraction and any-time search; provides an appendix detailing a  general adjustment model with constraints.

This work offers new insights and proposes novel methods to advance the field of machine vision, which will be of great benefit to students, researchers, and engineers active in this area.

About the authors

Dr.-Ing. Eckart Michaelsen is a researcher at the Object Recognition Department of Fraunhofer IOSB, Ettlingen, Germany.

Dr.-Ing. Jochen Meidow is a researcher at the Scene Analysis Department of the same institution.

Table of contents (13 chapters)

Table of contents (13 chapters)

Buy this book

eBook $89.00
price for USA in USD (gross)
  • ISBN 978-3-030-04040-6
  • Digitally watermarked, DRM-free
  • Included format: PDF, EPUB
  • ebooks can be used on all reading devices
  • Immediate eBook download after purchase
Hardcover $119.99
price for USA in USD
  • ISBN 978-3-030-04039-0
  • Free shipping for individuals worldwide
  • Usually dispatched within 3 to 5 business days.
Loading...

Recommended for you

Loading...

Bibliographic Information

Bibliographic Information
Book Title
Hierarchical Perceptual Grouping for Object Recognition
Book Subtitle
Theoretical Views and Gestalt-Law Applications
Authors
Series Title
Advances in Computer Vision and Pattern Recognition
Copyright
2019
Publisher
Springer International Publishing
Copyright Holder
Springer Nature Switzerland AG
eBook ISBN
978-3-030-04040-6
DOI
10.1007/978-3-030-04040-6
Hardcover ISBN
978-3-030-04039-0
Series ISSN
2191-6586
Edition Number
1
Number of Pages
XI, 195
Number of Illustrations
91 b/w illustrations, 9 illustrations in colour
Topics