Artificial Neural Networks for Computer Vision

  • Yi-Tong Zhou
  • Rama Chellappa

Part of the Research Notes in Neural Computing book series (NEURALCOMPUTING, volume 5)

Table of contents

  1. Front Matter
    Pages i-xi
  2. Yi-Tong Zhou, Rama Chellappa
    Pages 1-5
  3. Yi-Tong Zhou, Rama Chellappa
    Pages 6-14
  4. Yi-Tong Zhou, Rama Chellappa
    Pages 15-43
  5. Yi-Tong Zhou, Rama Chellappa
    Pages 44-62
  6. Yi-Tong Zhou, Rama Chellappa
    Pages 63-82
  7. Yi-Tong Zhou, Rama Chellappa
    Pages 83-121
  8. Yi-Tong Zhou, Rama Chellappa
    Pages 122-146
  9. Yi-Tong Zhou, Rama Chellappa
    Pages 147-150
  10. Back Matter
    Pages 151-170

About this book

Introduction

This monograph is an outgrowth of the authors' recent research on the de­ velopment of algorithms for several low-level vision problems using artificial neural networks. Specific problems considered are static and motion stereo, computation of optical flow, and deblurring an image. From a mathematical point of view, these inverse problems are ill-posed according to Hadamard. Researchers in computer vision have taken the "regularization" approach to these problems, where one comes up with an appropriate energy or cost function and finds a minimum. Additional constraints such as smoothness, integrability of surfaces, and preservation of discontinuities are added to the cost function explicitly or implicitly. Depending on the nature of the inver­ sion to be performed and the constraints, the cost function could exhibit several minima. Optimization of such nonconvex functions can be quite involved. Although progress has been made in making techniques such as simulated annealing computationally more reasonable, it is our view that one can often find satisfactory solutions using deterministic optimization algorithms.

Keywords

Stereo algorithms computer simulation computer vision filters image restoration model simulation

Authors and affiliations

  • Yi-Tong Zhou
    • 1
  • Rama Chellappa
    • 2
  1. 1.HNC, Inc.San DiegoUSA
  2. 2.Department of Electrical Engineering Center for Automation Research and Institute for Advanced Computer StudiesUniversity of MarylandCollege ParkUSA

Bibliographic information

  • DOI https://doi.org/10.1007/978-1-4612-2834-9
  • Copyright Information Springer-Verlag New York 1992
  • Publisher Name Springer, New York, NY
  • eBook Packages Springer Book Archive
  • Print ISBN 978-0-387-97683-9
  • Online ISBN 978-1-4612-2834-9
  • Series Print ISSN 0939-4818
  • About this book