Computer Vision : Principles, Algorithms, Applications, Learning / E.R. Davies.

Format:

Book

Author/Creator:

(E. Roy) Davies.

Contributor:

E. R..

Language:

English

Subjects (All):

Computer vision.

Information visualization.

Physical Description:

1 online resource (902 pages)

Edition:

5th ed.

Place of Publication:

San Diego : Elsevier Science & Technology, 2017.

Summary:

Computer Vision: Principles, Algorithms, Applications, Learning (previously entitled Computer and Machine Vision) clearly and systematically presents the basic methodology of computer vision, covering the essential elements of the theory while emphasizing algorithmic and practical design constraints. This fully revised fifth edition has brought in more of the concepts and applications of computer vision, making it a very comprehensive and up-to-date text suitable for undergraduate and graduate students, researchers and R&D engineers working in this vibrant subject. See an interview with the author explaining his approach to teaching and learning computer vision - http: //scitechconnect.elsevier.com/computer-vision/ Three new chapters on Machine Learning emphasise the way the subject has been developing; Two chapters cover Basic Classification Concepts and Probabilistic Models; and the The third covers the principles of Deep Learning Networks and shows their impact on computer vision, reflected in a new chapter Face Detection and Recognition . A new chapter on Object Segmentation and Shape Models reflects the methodology of machine learning and gives practical demonstrations of its application. In-depth discussions have been included on geometric transformations, the EM algorithm, boosting, semantic segmentation, face frontalisation, RNNs and other key topics. Examples and applications--including the location of biscuits, foreign bodies, faces, eyes, road lanes, surveillance, vehicles and pedestrians--give the 'ins and outs' of developing real-world vision systems, showing the realities of practical implementation. Necessary mathematics and essential theory are made approachable by careful explanations and well-illustrated examples. The 'recent developments' sections included in each chapter aim to bring students and practitioners up to date with this fast-moving subject. Tailored programming examples--code, methods, illustrations, tasks, hints and solutions (mainly involving MATLAB and C++)

Contents:

Front Cover

Computer Vision

Copyright Page

Dedication

Contents

About the Author

Foreword

Preface to the Fifth Edition

Preface to the First Edition

Acknowledgments

Topics Covered in Application Case Studies

Influences Impinging Upon Integrated Vision System Design

Glossary of Acronyms and Abbreviations

1 Vision, the challenge

1.1 Introduction-Man and His Senses

1.2 The Nature of Vision

1.2.1 The Process of Recognition

1.2.2 Tackling the Recognition Problem

1.2.3 Object Location

1.2.4 Scene Analysis

1.2.5 Vision as Inverse Graphics

1.3 From Automated Visual Inspection to Surveillance

1.4 What This Book Is About

1.5 The Part Played by Machine Learning

1.6 The Following Chapters

1.7 Bibliographical Notes

1 Low-level vision

2 Images and imaging operations

2.1 Introduction

2.1.1 Gray Scale Versus Color

2.2 Image Processing Operations

2.2.1 Some Basic Operations on Grayscale Images

2.2.2 Basic Operations on Binary Images

2.3 Convolutions and Point Spread Functions

2.4 Sequential Versus Parallel Operations

2.5 Concluding Remarks

2.6 Bibliographical and Historical Notes

2.7 Problems

3 Image filtering and morphology

3.1 Introduction

3.2 Noise Suppression by Gaussian Smoothing

3.3 Median Filters

3.4 Mode Filters

3.5 Rank Order Filters

3.6 Sharp-Unsharp Masking

3.7 Shifts Introduced by Median Filters

3.7.1 Continuum Model of Median Shifts

3.7.2 Generalization to Grayscale Images

3.7.3 Discrete Model of Median Shifts

3.8 Shifts Introduced by Rank Order Filters

3.8.1 Shifts in Rectangular Neighborhoods

3.9 The Role of Filters in Industrial Applications of Vision

3.10 Color in Image Filtering

3.11 Dilation and Erosion in Binary Images

3.11.1 Dilation and Erosion

3.11.2 Cancellation Effects.

3.11.3 Modified Dilation and Erosion Operators

3.12 Mathematical Morphology

3.12.1 Generalized Morphological Dilation

3.12.2 Generalized Morphological Erosion

3.12.3 Duality Between Dilation and Erosion

3.12.4 Properties of Dilation and Erosion Operators

3.12.5 Closing and Opening

3.12.6 Summary of Basic Morphological Operations

3.13 Morphological Grouping

3.14 Morphology in Grayscale Images

3.15 Concluding Remarks

3.16 Bibliographical and Historical Notes

3.16.1 More Recent Developments

3.17 Problems

4 The role of thresholding

4.1 Introduction

4.2 Region-Growing Methods

4.3 Thresholding

4.3.1 Finding a Suitable Threshold

4.3.2 Tackling the Problem of Bias in Threshold Selection

4.4 Adaptive Thresholding

4.4.1 Local Thresholding Methods

4.5 More Thoroughgoing Approaches to Threshold Selection

4.5.1 Variance-Based Thresholding

4.5.2 Entropy-Based Thresholding

4.5.3 Maximum Likelihood Thresholding

4.6 The Global Valley Approach to Thresholding

4.7 Practical Results Obtained Using the Global Valley Method

4.8 Histogram Concavity Analysis

4.9 Concluding Remarks

4.10 Bibliographical and Historical Notes

4.10.1 More Recent Developments

4.11 Problems

5 Edge detection

5.1 Introduction

5.2 Basic Theory of Edge Detection

5.3 The Template Matching Approach

5.4 Theory of 3×3 Template Operators

5.5 The Design of Differential Gradient Operators

5.6 The Concept of a Circular Operator

5.7 Detailed Implementation of Circular Operators

5.8 The Systematic Design of Differential Edge Operators

5.9 Problems With the Above Approach-Some Alternative Schemes

5.10 Hysteresis Thresholding

5.11 The Canny Operator

5.12 The Laplacian Operator

5.13 Concluding Remarks

5.14 Bibliographical and Historical Notes.

5.14.1 More Recent Developments

5.15 Problems

6 Corner, interest point, and invariant feature detection

6.1 Introduction

6.2 Template Matching

6.3 Second-Order Derivative Schemes

6.4 A Median Filter-based Corner Detector

6.4.1 Analyzing the Operation of the Median Detector

6.4.2 Practical Results

6.5 The Harris Interest Point Operator

6.5.1 Corner Signals and Shifts for Various Geometric Configurations

6.5.2 Performance With Crossing Points and T-junctions

6.5.3 Different Forms of the Harris Operator

6.6 Corner Orientation

6.7 Local Invariant Feature Detectors and Descriptors

6.7.1 Geometric Transformations and Feature Normalization

6.7.2 Harris Scale and Affine Invariant Detectors and Descriptors

6.7.3 Hessian Scale and Affine Invariant Detectors and Descriptors

6.7.4 The Scale Invariant Feature Transforms Operator

6.7.5 The Speeded-Up Robust Features Operator

6.7.6 Maximally Stable Extremal Regions

6.7.7 Comparison of the Various Invariant Feature Detectors

6.7.8 Histograms of Oriented Gradients

6.8 Concluding Remarks

6.9 Bibliographical and Historical Notes

6.9.1 More Recent Developments

6.10 Problems

7 Texture analysis

7.1 Introduction

7.2 Some Basic Approaches to Texture Analysis

7.3 Graylevel Co-occurrence Matrices

7.4 Laws' Texture Energy Approach

7.5 Ade's Eigenfilter Approach

7.6 Appraisal of the Laws and Ade approaches

7.7 Concluding Remarks

7.8 Bibliographical and Historical Notes

7.8.1 More Recent Developments

2 Intermediate-level vision

8 Binary shape analysis

8.1 Introduction

8.2 Connectedness in Binary Images

8.3 Object Labeling and Counting

8.3.1 Solving the Labeling Problem in a More Complex Case

8.4 Size Filtering

8.5 Distance Functions and Their Uses

8.5.1 Local Maxima and Data Compression.

8.6 Skeletons and Thinning

8.6.1 Crossing Number

8.6.2 Parallel and Sequential Implementations of Thinning

8.6.3 Guided Thinning

8.6.4 A Comment on the Nature of the Skeleton

8.6.5 Skeleton Node Analysis

8.6.6 Application of Skeletons for Shape Recognition

8.7 Other Measures for Shape Recognition

8.8 Boundary Tracking Procedures

8.9 Concluding Remarks

8.10 Bibliographical and Historical Notes

8.10.1 More Recent Developments

8.11 Problems

9 Boundary pattern analysis

9.1 Introduction

9.2 Boundary Tracking Procedures

9.3 Centroidal Profiles

9.4 Problems With the Centroidal Profile Approach

9.4.1 Some Solutions

9.5 The (s,ψ) Plot

9.6 Tackling the Problems of Occlusion

9.7 Accuracy of Boundary Length Measures

9.8 Concluding Remarks

9.9 Bibliographical and Historical Notes

9.9.1 More Recent Developments

9.10 Problems

10 Line, circle, and ellipse detection

10.1 Introduction

10.2 Application of the Hough Transform to Line Detection

10.2.1 Longitudinal Line Localization

10.3 The Foot-of-Normal Method

10.3.1 Application of the Foot-of-Normal Method

10.4 Using RANSAC for Straight Line Detection

10.5 Location of Laparoscopic Tools

10.6 Hough-Based Schemes for Circular Object Detection

10.7 The Problem of Unknown Circle Radius

10.7.1 Practical Results

10.8 Overcoming the Speed Problem

10.8.1 Practical Results

10.9 Ellipse Detection

10.9.1 The Diameter Bisection Method

10.9.2 The Chord-Tangent Method

10.9.3 Finding the Remaining Ellipse Parameters

10.10 Human Iris Location

10.11 Concluding Remarks

10.12 Bibliographical and Historical Notes

10.12.1 More Recent Developments

10.13 Problems

11 The generalized Hough transform

11.1 Introduction

11.2 The Generalized Hough Transform.

11.3 The Relevance of Spatial Matched Filtering

11.4 Gradient Weighting Versus Uniform Weighting

11.4.1 Calculation of Sensitivity and Computational Load

11.4.2 Summary

11.5 Use of the GHT for Ellipse Detection

11.5.1 Practical Details

11.6 Comparing the Various Methods for Ellipse Detection

11.7 A Graph-Theoretic Approach to Object Location

11.7.1 A Practical Example-Locating Cream Biscuits

11.8 Possibilities for Saving Computation

11.9 Using the GHT for Feature Collation

11.9.1 Computational Load

11.10 Generalizing the Maximal Clique and Other Approaches

11.11 Search

11.12 Concluding Remarks

11.13 Bibliographical and Historical Notes

11.13.1 More Recent Developments

11.14 Problems

12 Object segmentation and shape models

12.1 Introduction

12.2 Active Contours

12.3 Practical Results Obtained Using Active Contours

12.4 The Level-Set Approach to Object Segmentation

12.5 Shape Models

12.5.1 Locating Objects Using Shape Models

12.6 Concluding Remarks

12.7 Bibliographical and Historical Notes

3 Machine learning and deep learning networks

13 Basic classification concepts

13.1 Introduction

13.2 The Nearest Neighbor Algorithm

13.3 Bayes' Decision Theory

13.3.1 The Naïve Bayes' Classifier

13.4 Relation of the Nearest Neighbor and Bayes' Approaches

13.4.1 Mathematical Statement of the Problem

13.4.2 The Importance of the Nearest Neighbor Algorithm

13.5 The Optimum Number of Features

13.6 Cost Functions and Error-Reject Tradeoff

13.7 Supervised and Unsupervised Learning

13.8 Cluster Analysis

13.9 The Support Vector Machine

13.10 Artificial Neural Networks

13.11 The Back-Propagation Algorithm

13.12 Multilayer Perceptron Architectures

13.13 Overfitting to the Training Data

13.14 Concluding Remarks.

13.15 Bibliographical and Historical Notes.

Notes:

Description based on publisher supplied metadata and other sources.

ISBN:

0-12-809284-X