Research Catalog

Recognizing planar objects using invariant image features

Title
Recognizing planar objects using invariant image features / Thomas H. Reiss.
Author
Reiss, Thomas H., 1966-
Publication
Berlin ; New York : Springer-Verlag, ©1993.

Items in the Library & Off-site

Filter by

1 Item

StatusFormatAccessCall NumberItem Location
TextUse in library TA1650 .R45 1993Off-site

Details

Description
x, 180 pages : illustrations; 24 cm.
Summary
"Given a familiar object extracted from its surroundings, we humans have little difficulty in recognizing it irrespective of its size, position and orientation in our field of view. Changes in lighting and the effects of perspective also pose no problems. How do we achieve this, and more importantly, how can we get a computer to do this? One very promising approach is to find mathematical functions of an object's image, or of an object's 3D description, that are invariant to the transformations caused by the object's motion. This book is devoted to the theory and practice of such invariant image features, so-called image invariants, for planar objects. It gives a comprehensive summary of the field, discussing methods for recognizing both occluded and partially occluded objects, and also contains a definitive treatment of moment invariants and a tutorial introduction to algebraic invariants, which are fundamental to affine moment invariants and to many projective invariants. A number of novel invariant functions are presented and the results of numerous experiments investigating the stability of new and old invariants are discussed. The main conclusion is that moment invariants are very effective, both for partially occluded objects and for recognizing objects in grey-level images."--PULISHER'S WEBSITE.
Series Statement
Lecture notes in computer science ; 676
Uniform Title
Lecture notes in computer science ; 676.
Subject
  • Optical pattern recognition
  • Computer vision
  • Image processing > Digital techniques
  • digital imaging
  • Patroonherkenning
  • Image processing
  • Pattern recognition systems
  • Computer graphics
  • Géométrie projective > Informatique
  • Reconnaissance optique des formes (informatique)
  • Transformations (mathématiques) > Informatique
Bibliography (note)
  • Includes bibliographical references (p. [171]-180).
Contents
1. Introduction -- 2. Translation, Rotation, Scale and Contrast Invariants -- 3. Algebraic and Projective Invariants -- 4. Invariance to Affine Transformations -- 5. Invariance to Projective Transformations -- 6. Recognizing Partially Occluded Objects -- 7. Summary and Conclusions -- A. Orthogonality of Rotation Invariants for Discrete Images -- B. Generating Algebraic and Moment Invariants -- C. Equations Relating Solid Motion in 3D to Affine Image Transformations -- D. Fourier Descriptor Experiment.
ISBN
  • 3540567135
  • 9783540567134
  • 0387567135
  • 9780387567136
LCCN
93019397
OCLC
  • ocm27937144
  • 27937144
  • SCSB-9199631
Owning Institutions
Princeton University Library