书籍详情
机器视觉教程：英文版
作者：（美）Wesley E.Snyder，（美）Hairong Qi著
出版社：机械工业出版社
出版时间：2005-01-01
ISBN：9787111158370
定价：¥49.00
购买这本书可以去
内容简介
本书是一本介绍机器视觉的书，内容丰富，通俗易懂。它提供了所有必需的理论工具，并且展示了如何将它们应用到实际的图像处理与机器视觉系统中。本书包含许多编程练习，有助子学生深入理解实用图像处理算法的发展。本书从回顾数学原理开始，继而讨论数字图像处理中的关键问题，比如图像描述与特征、边缘检测、特征提取、分割、纹理与形状等。本书还讨论了图像匹配、统计模式识别、语法模式识别、聚类、扩散、自适应轮廓、参数变换和连贯性标记，介绍了一些重要的应用，包括自动目标识别。连贯性（解决机器视觉问题的基本构架）和最优化（用来实现各种方法的数学工具）是本书反复陈述的两个主题。本书适用于电气与计算机工程、计算机科学以及数学专业的高年级本科生与研究生，对于相关的工程技术人员也极具参考价值。本书附带光盘中包括书中用到的所有软件与数据。
作者简介
Wesley E.Snyder在美国伊利诺伊大学获得博士学位，目前是北卡罗来纳州立大学电气与计计算机工程系教授。他发表了100多篇论文，并且著有Industrial Robots一书。他是IEEE机器人与自动化学会和IEEE神经网络协会的创始人，还是美国国家科学基金、美国国家航空和航天管理局、Sandia国家实验室以及美国陆军研究所的顾问。Hairong Qi在美国北卡罗来纳州立大学获得博士学位，目前美国田纳西大学诺克斯维尔分校电气与计算机工程系统助理教授。
目录
To the instructor
Acknowledgements
1 Introduction
1.1 Concerning this book
1.2 Concerning prerequisites
1.3 Some terminology
1.4 Organization of a machine vision system
1.5 The nature of images
1.6 Images: Operations and analysis
Reference
Review of mathematical principles
2.1 A brief review of probability
2.2 A review of linear algebra
2.3 Introduction to function minimization
2.4 Markov models
References
3 Writing programs to process images
3.1 Image File System (IFS) software
3.2 Basic programming structure for image processing
3.3 Good programming styles
3.4 Example programs
3.5 Makefiles
4 Images: Formation and representation
4.1 Image representations
4.2 The digital image
4.3 Describing image formation
4.4 The image as a surface
4.5 Neighborhood relations
4.6 Conclusion
4.7 Vocabulary
Topic 4A Image representations
4A.1 A variation on sampling: Hexagonal pixels
4A.2 Other types of iconic representations
References
5 Linear operators and kernels
5.1 What is a linear operator?
5.2 Application of kernel operators in digital images
5.3 Derivative estimation by function fitting
5.4 Vector representations of images
5.5 Basis vectors for images
5.6 Edge detection
5.7 A kernel as a sampled differentiable function
5.8 Computing convolutions
5.9 Scale space
5.10 Quantifying the accuracy of an edge detector
5.11 So how do people do it?
5.12 Conclusion
5.13 Vocabulary
Topic 5A Edge detectors
5A.1 The Canny edge detector
5A.2 Improvements to edge detection
5A.3 Inferring line segments from edge points
5A.4 Space/frequency representations
5A.5 Vocabulary
References
6 Image relaxation: Restoration and feature extraction
6.1 Relaxation
6.2 Restoration
6.3 The MAP approach
6.4 Mean field annealing
6.5 Conclusion
6.6 Vocabulary
Topic 6A Alternative and equivalent algorithms
6A.1 GNC: An alternative algorithm for noise removal
6A.2 Variable conductance diffusion
6A.3 Edge-oriented anisotropic diffusion
6A.4 A common description of image relaxation operators
6A.5 Relationship to neural networks
6A.6 Conclusion
Bibliography
7 Mathematical morphology
7.1 Binary morphology
7.2 Gray-scale morphology
7.3 The distance transform
7.4 Conclusion
7.5 Vocabulary
Topic 7A Morphology
7A.1 Computing erosion and dilation efficiently
7A.2 Morphological sampling theorem
7A.3 Choosing a structuring element
7A.4 Closing gaps in edges and surfaces
7A.5 Vocabulary
Bibliography
8 Segmentation
8.1 Segmentation: Partitioning an image
8.2 Segmentation by thresholding
8.3 Connected component analysis
8.4 Segmentation of curves
8.5 Active contours (snakes)
8.6 Segmentation of surfaces
8.7 Evaluating the quality of a segmentation
8.8 Conclusion
8.9 Vocabulary
Topic 8A Segmentation
8A.1 Texture segmentation
8A.2 Segmentation of images using edges
8A.3 Motion segmentation
8A.4 Color segmentation
8A.5 Segmentation using MAP methods
8A.6 Human segmentation
Bibliography
Shape
9.1 Linear transformations
9.2 Transformation methods based on the covariance matrix
9.3 Simple features
9.4 Moments
9.5 Chain codes
9.6 Fourier descriptors
9.7 The medial axis
9.8 Deformable templates
9.9 Quadric surfaces
9.10 Surface harmonic representations
9.11 Superquadrics and hyperquadrics
9.12 Generalized cylinders (GCs)
9.13 Conclusion
9.14 Vocabulary
Topic 9A Shape description
9A.1 Finding the diameter of nonconvex regions
9A.2 Inferring 3D shape from images
9A.3 Motion analysis and tracking
9A.4 Vocabulary
Bibliography
10 Consistent labeling
10.1 Consistency
10.2 Relaxation labeling
10.3 Conclusion
10.4 Vocabulary
Topic 10A 3D Interpretation of 2D line drawings
References
11 Parametric transforms
11.1 The Hough transform
11.2 Reducing computational complexity
11.3 Finding circles
11.4 The generalized Hough transform
11.5 Conclusion
11.6 Vocabulary
Topic 11A Parametric transforms
11A.1 Finding parabolae
11A.2 Finding the peak
11A.3 The Gauss map
11A.4 Parametric consistency in stereopsis
11A.5 Conclusion
11A.6 Vocabulary
References
12 Graphs and graph-theoretic concepts
12.1 Graphs
12.2 Properties of graphs
12.3 Implementing graph structures
12.4 The region adjacency graph
12.5 Using graph-matching: The subgraph isomorphism problem
12.6 Aspect graphs
12.7 Conclusion
12.8 Vocabulary
References
13 Image matching
13.1 Matching iconic representations
13.2 Matching simple features
13.3 Graph matching
13.4 Conclusion
13.5 Vocabulary
Topic 13A Matching
13A.1 Springs and templates revisited
13A.2 Neural networks for object recognition
13A.3 Image indexing
13A.4 Matching geometric invariants
13A.5 Conclusion
13A.6 Vocabulary
Bibliography
14 Statistical pattern recognition
14.1 Design of a classifier
14.2 Bayes' rule and the maximum likelihood classifier
14.3 Decision regions and the probability of error
14.4 Conditional risk
14.5 The quadratic classifier
14.6 The minimax rule
14.7 Nearest neighbor methods
14.8 Conclusion
14.9 Vocabulary
Topic 14A Statistical pattern recognition
14A.1 Matching feature vectors using statistical methods
14A.2 Support vector machines (SVMs)
14A.3 Conclusion
14A.4 Vocabulary
References
15 Clustering
15.1 Distances between clusters
15.2 Clustering algorithms
15.3 Optimization methods in clustering
15.4 Conclusion
15.5 Vocabulary
References
16 Syntactic pattern recognition
16.1 Terminology
16.2 Types of grammars
16.3 Shape recognition using grannnatical structure
16.4 Conclusion
16.5 Vocabulary
References
17 Applications
17.1 Multispectral image analysis
17.2 Optical character recognition (OCR)
17.3 Automated/assisted diagnosis
17.4 Inspection/quality control
17.5 Security and intruder identification
17.6 Robot vision
Bibliography
18 Automatic target recognition
18.1 The hierarchy of levels of ATR
18.2 ATR system components
18.3 Evaluating performance of ATR algorithms
18.4 Machine vision issues unique to ATR
18.5 ATR algorithms
18.6 The Hough transform in ATR
18.7 Morphological techniques in ATR
18.8 Chain codes in ATR
18.9 Conclusion
Bibliography
Author index
Index
Acknowledgements
1 Introduction
1.1 Concerning this book
1.2 Concerning prerequisites
1.3 Some terminology
1.4 Organization of a machine vision system
1.5 The nature of images
1.6 Images: Operations and analysis
Reference
Review of mathematical principles
2.1 A brief review of probability
2.2 A review of linear algebra
2.3 Introduction to function minimization
2.4 Markov models
References
3 Writing programs to process images
3.1 Image File System (IFS) software
3.2 Basic programming structure for image processing
3.3 Good programming styles
3.4 Example programs
3.5 Makefiles
4 Images: Formation and representation
4.1 Image representations
4.2 The digital image
4.3 Describing image formation
4.4 The image as a surface
4.5 Neighborhood relations
4.6 Conclusion
4.7 Vocabulary
Topic 4A Image representations
4A.1 A variation on sampling: Hexagonal pixels
4A.2 Other types of iconic representations
References
5 Linear operators and kernels
5.1 What is a linear operator?
5.2 Application of kernel operators in digital images
5.3 Derivative estimation by function fitting
5.4 Vector representations of images
5.5 Basis vectors for images
5.6 Edge detection
5.7 A kernel as a sampled differentiable function
5.8 Computing convolutions
5.9 Scale space
5.10 Quantifying the accuracy of an edge detector
5.11 So how do people do it?
5.12 Conclusion
5.13 Vocabulary
Topic 5A Edge detectors
5A.1 The Canny edge detector
5A.2 Improvements to edge detection
5A.3 Inferring line segments from edge points
5A.4 Space/frequency representations
5A.5 Vocabulary
References
6 Image relaxation: Restoration and feature extraction
6.1 Relaxation
6.2 Restoration
6.3 The MAP approach
6.4 Mean field annealing
6.5 Conclusion
6.6 Vocabulary
Topic 6A Alternative and equivalent algorithms
6A.1 GNC: An alternative algorithm for noise removal
6A.2 Variable conductance diffusion
6A.3 Edge-oriented anisotropic diffusion
6A.4 A common description of image relaxation operators
6A.5 Relationship to neural networks
6A.6 Conclusion
Bibliography
7 Mathematical morphology
7.1 Binary morphology
7.2 Gray-scale morphology
7.3 The distance transform
7.4 Conclusion
7.5 Vocabulary
Topic 7A Morphology
7A.1 Computing erosion and dilation efficiently
7A.2 Morphological sampling theorem
7A.3 Choosing a structuring element
7A.4 Closing gaps in edges and surfaces
7A.5 Vocabulary
Bibliography
8 Segmentation
8.1 Segmentation: Partitioning an image
8.2 Segmentation by thresholding
8.3 Connected component analysis
8.4 Segmentation of curves
8.5 Active contours (snakes)
8.6 Segmentation of surfaces
8.7 Evaluating the quality of a segmentation
8.8 Conclusion
8.9 Vocabulary
Topic 8A Segmentation
8A.1 Texture segmentation
8A.2 Segmentation of images using edges
8A.3 Motion segmentation
8A.4 Color segmentation
8A.5 Segmentation using MAP methods
8A.6 Human segmentation
Bibliography
Shape
9.1 Linear transformations
9.2 Transformation methods based on the covariance matrix
9.3 Simple features
9.4 Moments
9.5 Chain codes
9.6 Fourier descriptors
9.7 The medial axis
9.8 Deformable templates
9.9 Quadric surfaces
9.10 Surface harmonic representations
9.11 Superquadrics and hyperquadrics
9.12 Generalized cylinders (GCs)
9.13 Conclusion
9.14 Vocabulary
Topic 9A Shape description
9A.1 Finding the diameter of nonconvex regions
9A.2 Inferring 3D shape from images
9A.3 Motion analysis and tracking
9A.4 Vocabulary
Bibliography
10 Consistent labeling
10.1 Consistency
10.2 Relaxation labeling
10.3 Conclusion
10.4 Vocabulary
Topic 10A 3D Interpretation of 2D line drawings
References
11 Parametric transforms
11.1 The Hough transform
11.2 Reducing computational complexity
11.3 Finding circles
11.4 The generalized Hough transform
11.5 Conclusion
11.6 Vocabulary
Topic 11A Parametric transforms
11A.1 Finding parabolae
11A.2 Finding the peak
11A.3 The Gauss map
11A.4 Parametric consistency in stereopsis
11A.5 Conclusion
11A.6 Vocabulary
References
12 Graphs and graph-theoretic concepts
12.1 Graphs
12.2 Properties of graphs
12.3 Implementing graph structures
12.4 The region adjacency graph
12.5 Using graph-matching: The subgraph isomorphism problem
12.6 Aspect graphs
12.7 Conclusion
12.8 Vocabulary
References
13 Image matching
13.1 Matching iconic representations
13.2 Matching simple features
13.3 Graph matching
13.4 Conclusion
13.5 Vocabulary
Topic 13A Matching
13A.1 Springs and templates revisited
13A.2 Neural networks for object recognition
13A.3 Image indexing
13A.4 Matching geometric invariants
13A.5 Conclusion
13A.6 Vocabulary
Bibliography
14 Statistical pattern recognition
14.1 Design of a classifier
14.2 Bayes' rule and the maximum likelihood classifier
14.3 Decision regions and the probability of error
14.4 Conditional risk
14.5 The quadratic classifier
14.6 The minimax rule
14.7 Nearest neighbor methods
14.8 Conclusion
14.9 Vocabulary
Topic 14A Statistical pattern recognition
14A.1 Matching feature vectors using statistical methods
14A.2 Support vector machines (SVMs)
14A.3 Conclusion
14A.4 Vocabulary
References
15 Clustering
15.1 Distances between clusters
15.2 Clustering algorithms
15.3 Optimization methods in clustering
15.4 Conclusion
15.5 Vocabulary
References
16 Syntactic pattern recognition
16.1 Terminology
16.2 Types of grammars
16.3 Shape recognition using grannnatical structure
16.4 Conclusion
16.5 Vocabulary
References
17 Applications
17.1 Multispectral image analysis
17.2 Optical character recognition (OCR)
17.3 Automated/assisted diagnosis
17.4 Inspection/quality control
17.5 Security and intruder identification
17.6 Robot vision
Bibliography
18 Automatic target recognition
18.1 The hierarchy of levels of ATR
18.2 ATR system components
18.3 Evaluating performance of ATR algorithms
18.4 Machine vision issues unique to ATR
18.5 ATR algorithms
18.6 The Hough transform in ATR
18.7 Morphological techniques in ATR
18.8 Chain codes in ATR
18.9 Conclusion
Bibliography
Author index
Index
猜您喜欢
