This special compendium introduces the basic principles, typical methods and practical techniques of 2D computer vision. The volume comprehensively covers the introductory content of computer vision and the materials are selected based on courses conducted in the past 20 years.The useful textbook provides numerous examples and self-test questions (including hints and answers) through intuitive explanations to help readers understand abstract concepts.This unique reference text provides the first computer vision course service for undergraduates of related majors in university and colleges. It also allows teachers to carry out online courses and strengthen teacher-student interaction when teaching.
This book is a special textbook that introduces the basic principles, typical methods, and practical techniques of 2D computer vision. It can serve as the first computer vision course material for undergraduates of related majors in university and higher-engineering colleges, and then they can study “3D Computer Vision: Principle, Algorithm, and Applications”.
This book mainly covers the introductory content of computer vision from a selection of materials. This book is mainly for information majors but also useful for learners with different professional backgrounds. This book is self-contained in contents and also considers the needs of self-study readers. Readers can not only solve some specific problems in practical applications but also lay a foundation for further study and research on high-level computer vision technology.
This book generally considers the following three aspects from the knowledge requirements of the prerequisite courses: (i) mathematics, including linear algebra and matrix theory, as well as basic knowledge of statistics, probability theory, and random modeling; (ii) computer science, including the mastery of computer software technology, understanding of computer structure system, and application of computer programming methods; (iii) electronics, including on the one hand, the characteristics and principles of electronic equipment, and on the other hand, circuit design and other content. In addition, it is best to study this book after finishing the course on signal processing.
Author(s): Yu-Jin Zhang
Publisher: World Scientific Publishing
Year: 2023
Language: English
Pages: 556
Contents
Preface
About the Author
Chapter 1. Computer Vision Fundamentals
1.1 Vision Basis
1.1.1 Vision
1.1.2 Visual sensation and visual perception
1.1.3 Visual process
1.2 Vision and Image
1.2.1 Images and digital images
1.2.2 Pixel and image representation
1.2.3 Image storage and format
1.2.4 Image display and printing
1.3 Vision Systems and Image Techniques
1.3.1 Vision system flowchart
1.3.2 Three layers of image engineering
1.3.3 Categories of image technology
1.4 Overview of the Structure and Content of This Book
1.4.1 Structural framework and main content
1.4.2 Overview of each chapter
1.4.3 Prerequisites
1.5 Key Points and References for Each Section
Self-Test Questions
1.1 Vision Basis
1.2 Vision and Image
1.3 Vision Systems and Image Techniques
1.4 Overview of the Structure and Content of This Book
References
Chapter 2. 2D Image Acquisition
2.1 Acquisition Device and Performance Index
2.1.1 CCD sensor
2.1.2 CMOS sensor
2.1.3 Common performance indicators
2.1.4 Image acquisition process
2.2 Image Brightness Imaging Model
2.2.1 Fundamentals of photometry
2.2.2 Uniform illuminance
2.2.3 A simple brightness imaging model
2.3 Image Space Imaging Model
2.3.1 Projection imaging geometry
2.3.2 Basic imaging model
2.3.3 General imaging model
2.4 Sampling and Quantization
2.4.1 Spatial and amplitude resolutions
2.4.2 Image data volume and quality
2.5 Relationship Between Pixels
2.5.1 Pixel neighborhood and connectivity
2.5.2 Distance between pixels
2.6 Key Points and References for Each Section
Self-Test Questions
2.1 Acquisition Device and Performance Index
2.2 Image Brightness Imaging Model
2.3 Image Space Imaging Model
2.4 Sampling and Quantization
2.5 Relationship between Pixels
References
Chapter 3. Spatial Domain Enhancement
3.1 Operation Between Images
3.1.1 Arithmetic operations
3.1.2 Logical operation
3.2 Image Gray-scale Mapping
3.2.1 Image negation
3.2.2 Contrast stretching
3.2.3 Dynamic range compression
3.3 Histogram Equalization
3.3.1 Image histogram
3.3.2 Principles and steps
3.4 Histogram Specification
3.4.1 Principles and steps
3.4.2 Single mapping law and group mapping law
3.5 Spatial Domain Convolution Enhancement
3.5.1 Mask convolution
3.5.2 Spatial filtering
3.6 Key Points and References for Each Section
Self-Test Questions
3.1 Operation Between Images
3.2 Image Gray-scale Mapping
3.3 Histogram Equalization
3.4 Histogram Specification
3.5 Spatial Domain Convolution Enhancement
References
Chapter 4. Frequency Domain Enhancement
4.1 Fourier Transform and Frequency Domain Enhancement
4.1.1 Fourier transform
4.1.2 Fourier transform properties
4.1.3 Frequency domain enhancement
4.2 Frequency Domain Low-Pass Filter
4.2.1 Ideal low-pass filter
4.2.2 Butterworth low-pass filter
4.3 Frequency Domain High-Pass Filter
4.3.1 Ideal high-pass filter
4.3.2 Butterworth high-pass filter
4.4 Band-Pass Filter and Band-Stop Filter
4.4.1 Band-pass filter
4.4.2 Band-stop filter
4.4.3 Relation between band-pass filter and band-stop filter
4.4.4 Notch filter
4.4.5 Interactively eliminate periodic noise
4.5 Homomorphic Filter
4.5.1 Homomorphic filtering process
4.5.2 Homomorphic filter denoising
4.6 Key Points and References for Each Section
Self-Test Questions
4.1 Fourier Transform and Frequency Domain Enhancement
4.2 Frequency Domain Low-Pass Filter
4.3 Frequency Domain High-Pass Filter
4.4 Band-Pass Filter and Band-Stop Filter
4.5 Homomorphic Filter
References
Chapter 5. Image Restoration
5.1 Image Degradation and Model
5.1.1 Image degradation model
5.1.2 Properties of the image degradation model
5.2 Inverse Filtering
5.2.1 Unconstrained restoration
5.2.2 Inverse filtering model
5.3 Wiener Filtering
5.3.1 Constrained restoration
5.3.2 Wiener filter
5.4 Geometric Distortion Correction
5.4.1 Spatial transformation
5.4.2 Gray-level interpolation
5.5 Image Repairing
5.5.1 Principle of image repairing
5.5.2 Image repair examples
5.6 Key Points and References for Each Section
Self-Test Questions
5.1 Image Degradation and Model
5.2 Inverse Filtering
5.3 Wiener Filtering
5.4 Geometric Distortion Correction
5.5 Image Repairing
References
Chapter 6. Color Enhancement
6.1 Color Vision
6.1.1 Three primary colors and color representation
6.1.2 Chromaticity diagram
6.2 Color Model
6.2.1 RGB model
6.2.2 HSI model
6.2.3 Conversion from RGB to HSI
6.2.4 Conversion from HSI to RGB
6.3 Pseudo-Color Enhancement
6.3.1 Intensity slicing
6.3.2 Conversion from gray scale to color
6.3.3 Frequency domain filtering
6.4 True-Color Enhancement
6.4.1 Single-component true-color enhancement
6.4.2 Full-color enhancement
6.5 Key Points and References for Each Section
Self-Test Questions
6.1 Color Vision
6.2 Color Model
6.3 Pseudo-Color Enhancement
6.4 True-Color Enhancement
References
Chapter 7. Image Segmentation
7.1 Segmentation Definition and Method Classification
7.1.1 Image segmentation definition
7.1.2 Image segmentation algorithm classification
7.2 Differential Edge Detection
7.2.1 Principle of differential edge detection
7.2.2 Gradient operator
7.3 Active Contour Model
7.3.1 Active contour
7.3.2 Energy function
7.4 Thresholding Segmentation
7.4.1 Principles and steps
7.4.2 Threshold selection
7.5 Threshold Selection Based on Transition Region
7.5.1 Transition region and effective average gradient
7.5.2 Extreme points of effective average gradient and boundary of transition region
7.5.3 Threshold selection
7.6 Region Growing
7.6.1 Basic method
7.6.2 Problems and improvements
7.7 Key Points and References for Each Section
Self-Test Questions
7.1 Segmentation Definition and Method Classification
7.2 Differential Edge Detection
7.3 Active Contour Model
7.4 Thresholding segmentation
7.5 Threshold Selection Based on Transition Region
7.6 Region Growing
References
Chapter 8. Primitive Detection
8.1 Interest Point Detection
8.1.1 Corner detection by second derivative
8.1.2 Harris interest point operator
8.1.3 Integral corner detection
8.2 Elliptical Object Detection
8.2.1 Diameter bisection
8.2.2 Chord-tangent method
8.2.3 Other parameters of the ellipse
8.3 Hough Transform
8.3.1 Point–line duality
8.3.2 Calculation steps
8.3.3 Polar coordinate equation
8.4 Generalized Hough Transform
8.4.1 Principle of generation
8.4.2 Complete generalized Hough transform
8.5 Key Points and References for Each Section
Self-Test Questions
8.1 Interest Point Detection
8.2 Elliptical Object Detection
8.3 Hough Transform
8.4 Generalized Hough Transform
References
Chapter 9. Object Representation
9.1 Chain Code Representation of Contour
9.1.1 Chain code representation
9.1.2 Chain code normalization
9.2 Contour Signature
9.2.1 Distance-angle signature
9.2.2 Tangent angle-arc length signature
9.2.3 Slope density signature
9.2.4 Distance-arc length signature
9.3 Polygonal Approximation of Contour
9.3.1 Minimum perimeter polygon
9.3.2 Merging polygon
9.3.3 Splitting polygon
9.4 Hierarchical Representation of Objects
9.4.1 Quad-tree representation
9.4.2 Binary tree representation
9.5 Bounding Region of Objects
9.5.1 Feret box
9.5.2 Minimum enclosing rectangle
9.5.3 Convex hull
9.6 Skeleton Representation of the Object
9.6.1 Skeleton and skeleton point
9.6.2 Skeleton algorithm
9.7 Key Points and References for Each Section
Self-Test Questions
9.1 Chain Code Representation of Contour
9.2 Contour Signature
9.3 Polygonal Approximation of Contour
9.4 Hierarchical Representation of Objects
9.5 Bounding Region of Objects
9.6 Skeleton Representation of the Object
References
Chapter 10. Object Description
10.1 Basic Contour Description Parameters
10.1.1 Contour length
10.1.2 Contour diameter
10.1.3 Slope, curvature, and corner point
10.2 Basic Region Description Parameters
10.2.1 Region area
10.2.2 Centroid of region
10.2.3 Regional gray-scale characteristics
10.3 Fourier Description of Contour
10.3.1 Fourier description of contour
10.3.2 Fourier description changes with contour
10.4 Wavelet Description of Contour
10.4.1 Wavelet transform basics
10.4.2 Wavelet contour descriptor
10.5 Region Description with Invariant Moments
10.5.1 Central moment
10.5.2 Region invariant moments
10.5.3 Region affine invariant moments
10.6 Object Relationship Description
10.6.1 String description
10.6.2 Tree structure description
10.7 Key Points and References for Each Section
Self-Test Questions
10.1 Basic Contour Description Parameters
10.2 Basic Region Description Parameters
10.3 Fourier Description of Contour
10.4 Wavelet Description of Contour
10.5 Region Description with Region Invariant Moments
10.6 Object Relationship Description
References
Chapter 11. Texture Description
11.1 Statistical Description of Texture
11.1.1 Co-occurrence matrix
11.1.2 Texture descriptors based on co-occurrence matrix
11.1.3 Energy-based texture descriptor
11.2 Structural Description of Texture
11.2.1 Basis of structure description method
11.2.2 Texture tessellation
11.2.3 Local binary pattern
11.3 Spectral Description of Texture
11.3.1 Fourier spectrum
11.3.2 Bessel–Fourier spectrum
11.4 Key Points and References for Each Section
Self-Test Questions
11.1 Statistical Description of Texture
11.2 Structural Description of Texture
11.3 Spectral Description of Texture
References
Chapter 12. Shape Description
12.1 Shape Compactness Descriptor
12.1.1 Aspect ratio
12.1.2 Form factor
12.1.3 Eccentricity
12.1.4 Sphericity
12.1.5 Circularity
12.1.6 Descriptor comparison
12.2 Shape Complexity Descriptor
12.2.1 Simple descriptors of shape complexity
12.2.2 Using the histogram analysis of the blurred image to describe the shape complexity
12.2.3 Saturation
12.3 Descriptor Based on Discrete Curvature
12.3.1 Curvature and geometric features
12.3.2 Discrete curvature
12.3.3 Calculation of discrete curvature
12.3.4 Descriptor based on curvature
12.4 Topological Descriptor
12.4.1 Euler number
12.4.2 Crossing number and connectivity number
12.5 Key Points and References for Each Section
Self-Test Questions
12.1 Shape Compactness Descriptor
12.2 Shape Complexity Descriptor
12.3 Descriptor Based on Discrete Curvature
12.4 Topological Descriptor
References
Chapter 13. Object Classification
13.1 Invariant Cross-Ratio
13.1.1 Cross-ratio
13.1.2 Invariant of non-collinear points
13.1.3 Symmetrical cross-ratio function
13.1.4 Cross-ratio application examples
13.2 Statistical Pattern Classification
13.2.1 Principle of pattern classification
13.2.2 Minimum distance classifier
13.2.3 Optimum statistical classifier
13.2.4 AdaBoost
13.3 Support Vector Machines
13.3.1 Linearly separable classes
13.3.2 Linearly non-separable classes
13.4 Key Points and References for Each Section
Self-Test Questions
13.1 Invariant Cross-Ratio
13.2 Statistical Pattern Classification
13.3 Support Vector Machines
References
Appendix A. Mathematical Morphology
A.1 Basic Set Definition
A.2 Basic Operations of Binary Morphology
A.2.1 Binary dilation and erosion
A.2.2 Binary opening and closing
A.3 Combined Operations of Binary Morphology
A.3.1 Hit-or-miss transform
A.3.2 Binary combination operation
A.4 Practical Algorithm of Binary Morphology
A.4.1 Noise elimination
A.4.2 Corner detection
A.4.3 Contour extraction
A.4.4 Region filling
A.4.5 Object detection and positioning
A.4.6 Extraction of connected components
A.4.7 Regional skeleton extraction
A.5 Key Points and References for Each Section
References
Appendix B. Visual Constancy
B.1 Visual Constancy Theory
B.1.1 Various constancy
B.1.2 Retinex theory
B.2 Application to Image Enhancement
B.2.1 Foggy day image enhancement
B.2.2 Infrared image enhancement
B.3 Key Points and References for Each Section
References
Answers to Self-Test Questions
Chapter 1 Computer Vision Fundamentals
Chapter 2 2D Image Acquisition
Chapter 3 Spatial Domain Image Enhancement
Chapter 4 Frequency Domain Image Enhancement
Chapter 5 Image Restoration
Chapter 6 Color Image Enhancement
Chapter 7 Image Segmentation
Chapter 8 Primitive Detection
Chapter 9 Object Representation
Chapter 10 Object Description
Chapter 11 Texture Description Methods
Chapter 12 Shape Description Methods
Chapter 13 Object classification
Index
