Vernon's Machine Vision: Table of Contents

Preface & Table of Contents

1. An introduction to computer vision (Page 1)

1.1 Computer vision: image processing or artificial intelligence? (Page 1)

1.2 Industrial machine vision vs. image understanding (Page )

1.3 Sensory feedback for manufacturing systems: why vision? (Page 3)

1.4 Examples of industrial machine vision problems and solutions (Page 4)

1.4.1 Measurement of steel bars (Page 4)

1.4.2 Inspection of computer screens (Page 5)

1.5 A typical system architecture (Page 5)

2. Illumination and sensors (Page 1)

2.1 Illumination (Page 1)

2.2 Sensors (Page 2)

2.2.1 Image formation: elementary optics (Page 2)

2.2.2 Camera sensors (Page 3)

2.2.3 Camera interfaces and video standards (Page 5)

2.2.4 Characteristics of camera sensors (Page 5)

2.2.5 Commercially available cameras (Page 7)

3. Image acquisition and representation (Page 1)

3.1 Sampling and quantization (Page 1)

3.1.1 Spatial frequency and the effects of sampling (Page 1)

3.2 Inter-pixel distances (Page 4)

3.3 Adjacency conventions (Page 4)

3.4 Image acquisition hardware (Page 5)

3.5 Speed considerations (Page 7)

4. Fundamentals of digital image processing (Page 1)

4.1 Point operations (Page 1)

4.1.1 Contrast stretching (Page 2)

4.1.2 Thresholding (Page 3)

4.1.3 Noise suppression by image addition (Page 4)

4.1.4 Background subtraction (Page 5)

4.2 Neighbourhood operations (Page 5)

4.2.1 Convolution (Page 5)

4.2.2 Noise suppression (Page 7)

4.2.3 Thinning, erosion and dilation (Page 9)

4.3 Geometric operations (Page 12)

4.3.1 Spatial warping (Page 12)

4.3.1.1 The spatial transformation (Page 13)

4.3.1.2 Grey-level interpolation (Page 14)

4.3.2 Registration and geometric decalibration (Page 16)

4.4 Mathematical morphology (Page 16)

4.4.1 Basic set theory (Page 16)

4.4.2 Structuring elements and hit or miss transformations (Page 16)

4.4.3 Erosion and dilation (Page 17)

4.4.4 Opening and closing (Page 18)

4.4.5 Thinning and the extraction of endpoints (Page 18)

4.4.6 Application: identification of endpoints of electrical wires (Page 19)

4.4.7 A brief introduction to grey-scale mathematical morphology (Page 19)

5. The segmentation problem (Page 1)

5.1 Introduction: region- and boundary-based approaches (Page 1)

5.2 Thresholding (Page 2)

5.2.1 Global, local, and dynamic approaches (Page 2)

5.2.2 Threshold selection (Page 2)

5.3 An overview of edge detection techniques (Page 4)

5.3.1 Gradient- and difference-based operators (Page 5)

5.3.2 Template matching (Page 8)

5.3.3 Edge fitting (Page 10)

5.3.4 Statistical techniques (Page 11)

5.3.5 Assessment of edge detection (Page 12)

5.4 Region growing (Page 12)

5.4.1 The split and merge procedure using quad-trees (Page 12)

5.5 Boundary detection (Page 13)

5.5.1 Boundary refining (Page 13)

5.5.2 Graph-theoretic techniques (Page 13)

5.5.3 Dynamic programming (Page 14)

5.5.4 Contour following (Page 14)

6. Image Analysis (Page 1)

6.1 Introduction: inspection, location, and identification (Page 1)

6.2 Template matching (Page 1)

6.2.1 Measures of similarity (Page 1)

6.2.2 Local template matching (Page 2)

6.3 Decision-theoretic approaches (Page 3)

6.3.1 Components of statistical pattern recognition process (Page 3)

6.3.2 Simple feature extraction (Page 3)

6.3.3 Classification (Page 4)

6.3.3.1 A synopsis of classification using Bayes' rule (Page 5)

6.4 The Hough transform (Page 7)

6.4.1 Hough transform for line detection and circle detection (Page 7)

6.4.2 The generalized Hough transform (Page 9)

6.5 Histogram analysis (Page 10)

7. An overview of techniques for shape description (Page 1)

7.1 A taxonomy of shape detectors (Page 1)

7.2 External scalar transform descriptors: features of the boundary (Page 1)

7.3 Internal scalar transform descriptors: features of the region (Page 2)

7.4 External space domain descriptors: spatial organization of the boundary (Page 3)

7.4.1 An algorithm for resampling the boundary chain codes (Page 5)

7.5 Internal space domain descriptors: spatial organization of the region (Page 6)

8. Robot programming and robot vision (Page 1)

8.1 A brief review of robot programming methodologies (Page 1)

8.2 Description of object pose with homogeneous transformations (Page 2)

8.3 Robot programming: a wire crimping task specification (Page 5)

8.4 A simple robot-programming language (Page 13)

8.5 Two vision algorithms for identifying ends of wires (Page 17)

8.5.1 A binary vision algorithm (Page 17)

8.5.2 A grey-scale vision algorithm (Page 19)

8.5.3 The vision/manipulator interface (Page 20)

8.6 The camera model and the inverse perspective transformation (Page 21)

8.6.1 The camera model (Page 21)

8.6.2 The inverse perspective transformation (Page 23)

8.6.3 Recovery of the third dimension (Page 24)

8.7 Three-dimensional vision using structured light (Page 24)

9. An introduction to image understanding (Page 1)

9.1 Representations and information processing: from images to object models (Page 1)

9.2 Organization of visual processes (Page 2)

9.3 Visual representations (Page 3)

9.3.1 The raw primal sketch (Page 3)

9.3.2 The full primal sketch (Page 3)

9.3.3 The two-and-a-half dimensional sketch (Page 6)

9.3.4 Three-dimensional models (Page 8)

9.3.4.1 Volumetric representations (Page 8)

9.3.4.2 Skeletal representations (Page 8)

9.3.4.3 Surface representations (Page 9)

9.3.5 The extended Gaussian image (Page 10)

9.4 Visual processes (Page 11)

9.4.1 Stereopsis (Page 11)

9.4.2 Camera motion (Page 11)

9.4.3 Shading (Page 17)

9.5 Concluding remarks (Page 20)

Appendix: Separability of the Laplacian of Gaussian Operator (Page 22)

Index (Page 23)

Return to front page