Computer and Machine Vision, 4th Edition

Computer and Machine Vision, 4th Edition

by E. R. Davies
Released April 2012
Publisher(s): Academic Press
ISBN: 9780123869913

Read it now on the O’Reilly learning platform with a 10-day free trial.

O’Reilly members get unlimited access to books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.

Start your free trial

Book description

Computer and Machine Vision: Theory, Algorithms, Practicalities (previously entitled Machine Vision) clearly and systematically presents the basic methodology of computer and machine vision, covering the essential elements of the theory while emphasizing algorithmic and practical design constraints. This fully revised fourth edition has brought in more of the concepts and applications of computer vision, making it a very comprehensive and up-to-date tutorial text suitable for graduate students, researchers and R&D engineers working in this vibrant subject.

Key features include:

  • Practical examples and case studies give the ‘ins and outs’ of developing real-world vision systems, giving engineers the realities of implementing the principles in practice
  • New chapters containing case studies on surveillance and driver assistance systems give practical methods on these cutting-edge applications in computer vision
  • Necessary mathematics and essential theory are made approachable by careful explanations and well-illustrated examples
  • Updated content and new sections cover topics such as human iris location, image stitching, line detection using RANSAC, performance measures, and hyperspectral imaging
  • The ‘recent developments’ section now included in each chapter will be useful in bringing students and practitioners up to date with the subject
  • Mathematics and essential theory are made approachable by careful explanations and well-illustrated examples
  • Updated content and new sections cover topics such as human iris location, image stitching, line detection using RANSAC, performance measures, and hyperspectral imaging
  • The ‘recent developments’ section now included in each chapter will be useful in bringing students and practitioners up to date with the subject

Table of contents

  1. Cover Image
  2. Contents
  3. Title
  4. Dedication
  5. Copyright
  6. Topics Covered in Application Case Studies
  7. Influences Impinging upon Integrated Vision System Design
  8. Foreword
  9. Preface
  10. About the Author
  11. Acknowledgements
  12. Glossary of Acronyms and Abbreviations
  13. Chapter 1: Vision, the Challenge
    1. 1.1 Introduction—Man and His Senses
    2. 1.2 The Nature of Vision
    3. 1.3 From Automated Visual Inspection to Surveillance
    4. 1.4 What This Book is About
    5. 1.5 The Following Chapters
    6. 1.6 Bibliographical Notes
  14. PART 1. Low-level Vision
    1. Chapter 2: Images and Imaging Operations
      1. 2.1 Introduction
      2. 2.2 Image Processing Operations
      3. 2.3 Convolutions and Point Spread Functions
      4. 2.4 Sequential Versus Parallel Operations
      5. 2.5 Concluding Remarks
      6. 2.6 Bibliographical and Historical Notes
      7. 2.7 Problems
    2. Chapter 3: Basic Image Filtering Operations
      1. 3.1 Introduction
      2. 3.2 Noise Suppression by Gaussian Smoothing
      3. 3.3 Median Filters
      4. 3.4 Mode Filters
      5. 3.5 Rank Order Filters
      6. 3.6 Reducing Computational Load
      7. 3.7 Sharp–Unsharp Masking
      8. 3.8 Shifts Introduced by Median Filters
      9. 3.9 Discrete Model of Median Shifts
      10. 3.10 Shifts Introduced by Mode Filters
      11. 3.11 Shifts Introduced by Mean and Gaussian Filters
      12. 3.12 Shifts Introduced by Rank Order Filters
      13. 3.13 The Role of Filters in Industrial Applications of Vision
      14. 3.14 Color in Image Filtering
      15. 3.15 Concluding Remarks
      16. 3.16 Bibliographical and Historical Notes
      17. 3.17 Problems
    3. Chapter 4: Thresholding Techniques
      1. 4.1 Introduction
      2. 4.2 Region-Growing Methods
      3. 4.3 Thresholding
      4. 4.4 Adaptive Thresholding
      5. 4.5 More Thoroughgoing Approaches to Threshold Selection
      6. 4.6 The Global Valley Approach to Thresholding
      7. 4.7 Practical Results Obtained Using the Global Valley Method
      8. 4.8 Histogram Concavity Analysis
      9. 4.9 Concluding Remarks
      10. 4.10 Bibliographical and Historical Notes
      11. 4.11 Problems
    4. Chapter 5: Edge Detection
      1. 5.1 Introduction
      2. 5.2 Basic Theory of Edge Detection
      3. 5.3 The Template Matching Approach
      4. 5.4 Theory of 3×3 Template Operators
      5. 5.5 The Design of Differential Gradient Operators
      6. 5.6 The Concept of a Circular Operator
      7. 5.7 Detailed Implementation of Circular Operators
      8. 5.8 The Systematic Design of Differential Edge Operators
      9. 5.9 Problems with the Above Approach—Some Alternative Schemes
      10. 5.10 Hysteresis Thresholding
      11. 5.11 The Canny Operator
      12. 5.12 The Laplacian Operator
      13. 5.13 Active Contours
      14. 5.14 Practical Results Obtained Using Active Contours
      15. 5.15 The Level Set Approach to Object Segmentation
      16. 5.16 The Graph Cut Approach to Object Segmentation
      17. 5.17 Concluding Remarks
      18. 5.18 Bibliographical and Historical Notes
      19. 5.19 Problems
    5. Chapter 6: Corner and Interest Point Detection
      1. 6.1 Introduction
      2. 6.2 Template Matching
      3. 6.3 Second-Order Derivative Schemes
      4. 6.4 A Median Filter-Based Corner Detector
      5. 6.5 The Harris Interest Point Operator
      6. 6.6 Corner Orientation
      7. 6.7 Local Invariant Feature Detectors and Descriptors
      8. 6.8 Concluding Remarks
      9. 6.9 Bibliographical and Historical Notes
      10. 6.10 Problems
    6. Chapter 7: Mathematical Morphology
      1. 7.1 Introduction
      2. 7.2 Dilation and Erosion in Binary Images
      3. 7.3 Mathematical Morphology
      4. 7.4 Grayscale Processing
      5. 7.5 Effect of Noise on Morphological Grouping Operations
      6. 7.6 Concluding Remarks
      7. 7.7 Bibliographical and Historical Notes
      8. 7.8 Problem
    7. Chapter 8: Texture
      1. 8.1 Introduction
      2. 8.2 Some Basic Approaches to Texture Analysis
      3. 8.3 Graylevel Co-Occurrence Matrices
      4. 8.4 Laws’ Texture Energy Approach
      5. 8.5 Ade’s Eigenfilter Approach
      6. 8.6 Appraisal of the Laws and Ade Approaches
      7. 8.7 Concluding Remarks
      8. 8.8 Bibliographical and Historical Notes
  15. PART 2. Intermediate-level Vision
    1. Chapter 9: Binary Shape Analysis
      1. 9.1 Introduction
      2. 9.2 Connectedness in Binary Images
      3. 9.3 Object Labeling and Counting
      4. 9.4 Size Filtering
      5. 9.5 Distance Functions and their Uses
      6. 9.6 Skeletons and Thinning
      7. 9.7 Other Measures for Shape Recognition
      8. 9.8 Boundary Tracking Procedures
      9. 9.9 Concluding Remarks
      10. 9.10 Bibliographical and Historical Notes
      11. 9.11 Problems
    2. Chapter 10: Boundary Pattern Analysis
      1. 10.1 Introduction
      2. 10.2 Boundary Tracking Procedures
      3. 10.3 Centroidal Profiles
      4. 10.4 Problems with the Centroidal Profile Approach
      5. 10.5 The (s, ψ) Plot
      6. 10.6 Tackling the Problems of Occlusion
      7. 10.7 Accuracy of Boundary Length Measures
      8. 10.8 Concluding Remarks
      9. 10.9 Bibliographical and Historical Notes
      10. 10.10 Problems
    3. Chapter 11: Line Detection
      1. 11.1 Introduction
      2. 11.2 Application of the Hough Transform to Line Detection
      3. 11.3 The Foot-of-Normal Method
      4. 11.4 Longitudinal Line Localization
      5. 11.5 Final Line Fitting
      6. 11.6 Using RANSAC for Straight Line Detection
      7. 11.7 Location of Laparoscopic Tools
      8. 11.8 Concluding Remarks
      9. 11.9 Bibliographical and Historical Notes
      10. 11.10 Problems
    4. Chapter 12: Circle and Ellipse Detection
      1. 12.1 Introduction
      2. 12.2 Hough-Based Schemes for Circular Object Detection
      3. 12.3 The Problem of Unknown Circle Radius
      4. 12.4 The Problem of Accurate Center Location
      5. 12.5 Overcoming the Speed Problem
      6. 12.6 Ellipse Detection
      7. 12.7 Human Iris Location
      8. 12.8 Hole Detection
      9. 12.9 Concluding Remarks
      10. 12.10 Bibliographical and Historical Notes
      11. 12.11 Problems
    5. Chapter 13: The Hough Transform and Its Nature
      1. 13.1 Introduction
      2. 13.2 The Generalized Hough Transform
      3. 13.3 Setting Up the Generalized Hough Transform—Some Relevant Questions
      4. 13.4 Spatial Matched Filtering in Images
      5. 13.5 From Spatial Matched Filters to Generalized Hough Transforms
      6. 13.6 Gradient Weighting Versus Uniform Weighting
      7. 13.7 Summary
      8. 13.8 Use of the GHT for Ellipse Detection
      9. 13.9 Comparing the Various Methods
      10. 13.10 Fast Implementations of the Hough Transform
      11. 13.11 The Approach of Gerig and Klein
      12. 13.12 Concluding Remarks
      13. 13.13 Bibliographical and Historical Notes
      14. 13.14 Problems
    6. Chapter 14: Pattern Matching Techniques
      1. 14.1 Introduction
      2. 14.2 A Graph-Theoretic Approach to Object Location
      3. 14.3 Possibilities for Saving Computation
      4. 14.4 Using the Generalized Hough Transform for Feature Collation
      5. 14.5 Generalizing the Maximal Clique and Other Approaches
      6. 14.6 Relational Descriptors
      7. 14.7 Search
      8. 14.8 Concluding Remarks
      9. 14.9 Bibliographical and Historical Notes
      10. 14.10 Problems
  16. PART 3. 3-D Vision and Motion
    1. Chapter 15: The Three-Dimensional World
      1. 3-D vision
      2. 15.1 Introduction
      3. 15.2 3-D Vision—The Variety of Methods
      4. 15.3 Projection Schemes for Three-Dimensional Vision
      5. 15.4 Shape from Shading
      6. 15.5 Photometric Stereo
      7. 15.6 The Assumption of Surface Smoothness
      8. 15.7 Shape from Texture
      9. 15.8 Use of Structured Lighting
      10. 15.9 Three-Dimensional Object Recognition Schemes
      11. 15.10 Horaud’s Junction Orientation Technique4
      12. 15.11 An Important Paradigm—Location of Industrial Parts
      13. 15.12 Concluding Remarks
      14. 15.13 Bibliographical and Historical Notes
      15. 15.14 Problems
    2. Chapter 16: Tackling the Perspective -point Problem
      1. 16.1 Introduction
      2. 16.2 The Phenomenon of Perspective Inversion
      3. 16.3 Ambiguity of Pose Under Weak Perspective Projection
      4. 16.4 Obtaining Unique Solutions to the Pose Problem
      5. 16.5 Concluding Remarks
      6. 16.6 Bibliographical and Historical Notes
      7. 16.7 Problems
    3. Chapter 17: Invariants and Perspective
      1. 17.1 Introduction
      2. 17.2 Cross-Ratios: The “Ratio of Ratios” Concept
      3. 17.3 Invariants for Noncollinear Points
      4. 17.4 Invariants for Points on Conics
      5. 17.5 Differential and Semi-Differential Invariants
      6. 17.6 Symmetric Cross-Ratio Functions
      7. 17.7 Vanishing Point Detection
      8. 17.8 More on Vanishing Points
      9. 17.9 Apparent Centers of Circles and Ellipses
      10. 17.10 The Route to Face Recognition
      11. 17.11 Perspective Effects in Art and Photography*
      12. 17.12 Concluding Remarks
      13. 17.13 Bibliographical and Historical Notes
      14. 17.14 Problems
    4. Chapter 18: Image Transformations and Camera Calibration
      1. 18.1 Introduction
      2. 18.2 Image Transformations
      3. 18.3 Camera Calibration
      4. 18.4 Intrinsic and Extrinsic Parameters
      5. 18.5 Correcting for Radial Distortions
      6. 18.6 Multiple View Vision
      7. 18.7 Generalized Epipolar Geometry
      8. 18.8 The Essential Matrix
      9. 18.9 The Fundamental Matrix
      10. 18.10 Properties of the Essential and Fundamental Matrices
      11. 18.11 Estimating the Fundamental Matrix
      12. 18.12 An Update on the Eight-Point Algorithm
      13. 18.13 Image Rectification
      14. 18.14 3-D Reconstruction
      15. 18.15 Concluding Remarks
      16. 18.16 Bibliographical and Historical Notes
      17. 18.17 Problems
    5. Chapter 19: Motion
      1. 19.1 Introduction
      2. 19.2 Optical Flow
      3. 19.3 Interpretation of Optical Flow Fields
      4. 19.4 Using Focus of Expansion to Avoid Collision
      5. 19.5 Time-To-Adjacency Analysis
      6. 19.6 Basic Difficulties with the Optical Flow Model
      7. 19.7 Stereo from Motion
      8. 19.8 The Kalman Filter
      9. 19.9 Wide Baseline Matching
      10. 19.10 Concluding Remarks
      11. 19.11 Bibliographical and Historical Notes
      12. 19.12 Problem
  17. PART 4. Toward Real-time Pattern Recognition Systems
    1. Chapter 20: Automated Visual Inspection
      1. 20.1 Introduction
      2. 20.2 The Process of Inspection
      3. 20.3 The Types of Object to be Inspected
      4. 20.4 Summary: The Main Categories of Inspection
      5. 20.5 Shape Deviations Relative to a Standard Template
      6. 20.6 Inspection of Circular Products
      7. 20.7 Inspection of Printed Circuits
      8. 20.8 Steel Strip and Wood Inspection
      9. 20.9 Inspection of Products with High Levels of Variability
      10. 20.10 X-Ray Inspection
      11. 20.11 The Importance of Color in Inspection
      12. 20.12 Bringing Inspection to the Factory
      13. 20.13 Concluding Remarks
      14. 20.14 Bibliographical and Historical Notes
    2. Chapter 21: Inspection of Cereal Grains
      1. 21.1 Introduction
      2. 21.2 Case Study: Location of Dark Contaminants in Cereals
      3. 21.3 Case Study: Location of Insects
      4. 21.4 Case Study: High-Speed Grain Location
      5. 21.5 Optimizing the Output for Sets of Directional Template Masks
      6. 21.6 Concluding Remarks
      7. 21.7 Bibliographical and Historical Notes
    3. Chapter 22: Surveillance
      1. 22.1 Introduction
      2. 22.2 Surveillance—The Basic Geometry
      3. 22.3 Foreground–Background Separation
      4. 22.4 Particle Filters
      5. 22.5 Use of Color Histograms for Tracking
      6. 22.6 Implementation of Particle Filters
      7. 22.7 Chamfer Matching, Tracking, and Occlusion
      8. 22.8 Combining Views from Multiple Cameras
      9. 22.9 Applications to the Monitoring of Traffic Flow
      10. 22.10 License Plate Location
      11. 22.11 Occlusion Classification for Tracking
      12. 22.12 Distinguishing Pedestrians by their Gait
      13. 22.13 Human Gait Analysis
      14. 22.14 Model-Based Tracking of Animals
      15. 22.15 Concluding Remarks
      16. 22.16 Bibliographical and Historical Notes
      17. 22.17 Problem
    4. Chapter 23: In-Vehicle Vision Systems
      1. 23.1 Introduction
      2. 23.2 Locating the Roadway
      3. 23.3 Location of Road Markings
      4. 23.4 Location of Road Signs
      5. 23.5 Location of Vehicles
      6. 23.6 Information Obtained by Viewing Licence Plates and Other Structural Features
      7. 23.7 Locating Pedestrians
      8. 23.8 Guidance and Egomotion
      9. 23.9 Vehicle Guidance in Agriculture
      10. 23.10 Concluding Remarks
      11. 23.11 More Detailed Developments and Bibliographies Relating to Advanced Driver Assistance Systems
      12. 23.12 Problem
    5. Chapter 24: Statistical Pattern Recognition
      1. 24.1 Introduction
      2. 24.2 The Nearest Neighbor Algorithm
      3. 24.3 Bayes’ Decision Theory
      4. 24.4 Relation of the Nearest Neighbor and Bayes’ Approaches
      5. 24.5 The Optimum Number of Features
      6. 24.6 Cost Functions and Error–Reject Tradeoff
      7. 24.7 The Receiver Operating Characteristic
      8. 24.8 Multiple Classifiers
      9. 24.9 Cluster Analysis
      10. 24.10 Principal Components Analysis
      11. 24.11 The Relevance of Probability in Image Analysis
      12. 24.12 Another Look at Statistical Pattern Recognition: The Support Vector Machine
      13. 24.13 Artificial Neural Networks
      14. 24.14 The Back-Propagation Algorithm
      15. 24.15 MLP Architectures
      16. 24.16 Overfitting to the Training Data
      17. 24.17 Concluding Remarks
      18. 24.18 Bibliographical and Historical Notes
      19. 24.19 Problems
    6. Chapter 25: Image Acquisition
      1. 25.1 Introduction
      2. 25.2 Illumination Schemes
      3. 25.3 Cameras and Digitization
      4. 25.4 The Sampling Theorem
      5. 25.5 Hyperspectral Imaging
      6. 25.6 Concluding Remarks
      7. 25.7 Bibliographical and Historical Notes
    7. Chapter 26: Real-Time Hardware and Systems Design Considerations
      1. 26.1 Introduction
      2. 26.2 Parallel Processing
      3. 26.3 SIMD Systems
      4. 26.4 The Gain in Speed Attainable with N Processors
      5. 26.5 Flynn’s Classification
      6. 26.6 Optimal Implementation of Image Analysis Algorithms
      7. 26.7 Some Useful Real-Time Hardware Options
      8. 26.8 Systems Design Considerations
      9. 26.9 Design of Inspection Systems—the Status Quo
      10. 26.10 System Optimization
      11. 26.11 Concluding Remarks
      12. 26.12 Bibliographical and Historical Notes7
    8. Chapter 27: Epilogue—Perspectives in Vision
      1. 27.1 Introduction
      2. 27.2 Parameters of Importance in Machine Vision
      3. 27.3 Tradeoffs
      4. 27.4 Moore’s Law in Action
      5. 27.5 Hardware, Algorithms, and Processes
      6. 27.6 The Importance of Choice of Representation
      7. 27.7 Past, Present, and Future
      8. 27.8 Bibliographical and Historical Notes
  18. APPENDIX A. Robust Statistics
    1. A.1 Introduction
    2. A.2 Preliminary Definitions and Analysis
    3. A.3 The M-Estimator (Influence Function) Approach
    4. A.4 The Least Median of Squares Approach to Regression
    5. A.5 Overview of the Robustness Problem
    6. A.6 The RANSAC Approach
    7. A.7 Concluding Remarks
    8. A.8 Bibliographical and Historical Notes
    9. A.9 Problem
  19. Author Index
  20. Subject Index

Product information

  • Title: Computer and Machine Vision, 4th Edition
  • Author(s): E. R. Davies
  • Release date: April 2012
  • Publisher(s): Academic Press
  • ISBN: 9780123869913