Human Face Recognition Using Third-Order Synthetic Neural Networks

  • Okechukwu A. Uwechue
  • Abhijit S. Pandya

Table of contents

  1. Front Matter
    Pages i-xv
  2. Okechukwu A. Uwechue, Abhijit S. Pandya
    Pages 1-20
  3. Okechukwu A. Uwechue, Abhijit S. Pandya
    Pages 21-35
  4. Okechukwu A. Uwechue, Abhijit S. Pandya
    Pages 37-45
  5. Okechukwu A. Uwechue, Abhijit S. Pandya
    Pages 47-55
  6. Okechukwu A. Uwechue, Abhijit S. Pandya
    Pages 57-90
  7. Okechukwu A. Uwechue, Abhijit S. Pandya
    Pages 91-109
  8. Okechukwu A. Uwechue, Abhijit S. Pandya
    Pages 111-114
  9. Okechukwu A. Uwechue, Abhijit S. Pandya
    Pages 115-117
  10. Back Matter
    Pages 119-123

About this book

Introduction

Human Face Recognition Using Third-Order Synthetic Neural Networks explores the viability of the application of High-order synthetic neural network technology to transformation-invariant recognition of complex visual patterns. High-order networks require little training data (hence, short training times) and have been used to perform transformation-invariant recognition of relatively simple visual patterns, achieving very high recognition rates. The successful results of these methods provided inspiration to address more practical problems which have grayscale as opposed to binary patterns (e.g., alphanumeric characters, aircraft silhouettes) and are also more complex in nature as opposed to purely edge-extracted images - human face recognition is such a problem.
Human Face Recognition Using Third-Order Synthetic Neural Networks serves as an excellent reference for researchers and professionals working on applying neural network technology to the recognition of complex visual patterns.

Keywords

neural networks pattern recognition training

Authors and affiliations

  • Okechukwu A. Uwechue
    • 1
  • Abhijit S. Pandya
    • 2
  1. 1.AT&T LaboratoriesUSA
  2. 2.Florida Atlantic UniversityUSA

Bibliographic information

  • DOI https://doi.org/10.1007/978-1-4615-4092-2
  • Copyright Information Kluwer Academic Publishers 1997
  • Publisher Name Springer, Boston, MA
  • eBook Packages Springer Book Archive
  • Print ISBN 978-1-4613-6832-8
  • Online ISBN 978-1-4615-4092-2
  • Series Print ISSN 0893-3405
  • About this book