Computer-Oriented Approaches to Pattern Recognition
Published on 14. May 2014
263 pages
978-0-08-095592-6 (ISBN)
Description
Computer-Oriented Approaches to Pattern Recognition
More details
Series
Language
English
Place of publication
San Diego
United States
ISBN-13
978-0-08-095592-6 (9780080955926)
Copyright in bibliographic data and cover images is held by Nielsen Book Services Limited or by the publishers or by their respective licensors: all rights reserved.
Schweitzer Classification
Other editions
Additional editions
Book
05/1972
Academic Press
€69.33
Article exhausted; check different version
Content
- Front Cover
- Computer-Oriented Approaches to Pattern Recognition
- Copyright Page
- Contents
- Preface
- CHAPTER I. BASIC CONCEPTS AND METHODS IN MATHEMATICAL PATTERN RECOGNITION
- 1.1 What Is Pattern Recognition?
- 1.2 Computer-Oriented Approaches to Pattern Recognition
- 1.3 Examples of Pattern Recognition Applications
- 1.4 The Pattern Recognition Process
- 1.5 Basic Concepts in Pattern Classification
- 1.6 Basic Concepts in Feature Selection
- 1.7 Direct and Indirect Methods
- 1.8 Parametric and Nonparametric Methods
- 1.9 Some Simple Pattern Classification Algorithms
- 1.10 Overview
- Exercises
- Selected Bibliography
- CHAPTER II. THE STATISTICAL FORMULATION AND PARAMETRIC METHODS
- 2.1 Introduction
- 2.2 Statistical Decision Theory
- 2.3 Histograms
- 2.4 Parametric Methods
- 2.5 Conclusion
- Exercises
- Selected Bibliography
- CHAPTER III. INTRODUCTION TO OPTIMIZATION TECHNIQUES
- 3.1 Indirect Methods
- 3.2 Direct Methods
- 3.3 Linear Programming
- 3.4 A Localized Random Search Technique
- Exercises
- Selected Bibliography
- CHAPTER IV. LINEAR DISCRIMINANT FUNCTIONS AND EXTENSIONS
- 4.1 Introduction
- 4.2 Mathematical Preliminaries
- 4.3 Linear Discriminant Functions
- 4.4 Specifying the Loss Function
- 4.5 Minimizing the Approximate Risk
- 4.6 An Alternate Cost Function
- 4.7 The N-Class Problem
- 4.8 Solution by Linear Programming
- 4.9 Extension to General F Functions
- 4.10 Threshold Elements in the Realization of Linear Discriminant Functions
- Exercises
- Selected Bibliography
- CHAPTER V. INDIRECT APPROXIMATION OF PROBABILITY DENSITIES
- 5.1 Introduction
- 5.2 Integral-Square Approximation
- 5.3 Least-Mean-Square Approximation
- 5.4 Weighted Mean-Square Approximation
- 5.5 Relation to Linear Discriminant and F-Function Techniques
- 5.6 Extensions
- 5.7 Summary
- Exercises
- Selected Bibliography
- CHAPTER VI. DIRECT CONSTRUCTION OF PROBABILITY DENSITIES : POTENTIAL FUNCTIONS (PARZEN ESTIMATORS)
- 6.1 Introduction
- 6.2 An Alternate Interpretation
- 6.3 Generality of Potential Function Methods
- 6.4 Choosing the Form of Potential Function
- 6.5 Choosing Size and Shape Parameters
- 6.6 Efficient Decision Rules Based on Potential Function Methods
- 6.7 Generalized Potential Functions
- 6.8 Conclusion
- Exercises
- Selected Bibliography
- CHAPTER VII. PIECEWISE LINEAR DISCRIMINANT FUNCTIONS
- 7.1 Introduction
- 7.2 Implicit Subclasses
- 7.3 Perceptrons and Layered Networks
- 7.4 Indirect Approaches to Deriving Piecewise Linear Discriminant Functions
- 7.5 Piecewise Linear Decision Boundaries by Linear Programming
- 7.6 Limiting the Class of Acceptable Boundaries
- 7.7 Conclusion
- Exercises
- Selected Bibliography
- CHAPTER VIll. CLUSTER ANALYSIS AND UNSUPERVISED LEARNING
- 8.1 Introduction
- 8.2 Describing the Subregions
- 8.3 Cluster Analysis as Decomposition of Probability Densities
- 8.4 Mode Seeking on Probability Estimates
- 8.5 Iterative Adjustment of Clusters
- 8.6 Adaptive Sample Set Construction
- 8.7 Graph-Theoretic Methods
- 8.8 Indirect Methods in Clustering
- 8.9 Unsupervised and Decision-Directed Learning
- 8.10 Clustering as Data Analysis
- 8.11 Cluster Analysis and Pattern Classification
- Exercises
- Selected Bibliography
- CHAPTER IX. FEATURE SELECTION
- 9.1 Introduction
- 9.2 Direct Methods
- 9.3 Indirect Methods: Parameterized Transformations
- 9.4 Measures of Quality: Tnterset and Intraset Distances
- 9.5 Measures of Quality Utilizing Probability Estimates
- 9.6 Measures of Quality: The Preservation of Structure
- 9.7 Indirect Methods: Other Measures of Quality
- 9.8 Custom Orthonormal Transformations
- 9.9 Choosing n of m Features
- 9.10 Conclusion
- Exercises
- Selected Bibliography
- CHAPTER X. SPECIAL TOPICS
- 10.1 Introduction
- 10.2 Binary Variables
- 10.3 Sequential Feature Selection
- 10.4 Structural, Linguistic, and Heuristic Analysis of Patterns
- 10.5 Asymptotic Convergence and Stochastic Approximation
- 10.6 Nonstationary Pattern Recognition
- Exercises
- Selectcd Bibliography
- Appendix A. A SET OF ORTHONORMAL POLYNOMIALS
- Appendix B. EFFICIENT REPRESENTATION AND APPROXIMATION OF MULTIVARIATE FUNCTIONS
- B.1 Introduction
- B.2 Continuous Piecewise Linear Form Approximations
- B.3 Composed Functions
- Selected Bibliography
- Index
