Machine Vision Algorithms in Java: Techniques and Implementation

ISBN-13: 9781852332181 / Angielski / Twarda / 2000 / 284 str.

Paul F. Whelan; Derek Molloy; Derek Molloy

Opis

Machine Vision Algorithms in Java provides a comprehensive introduction to the algorithms and techniques associated with machine vision systems. The Java programming language is also introduced, with particular reference to its imaging capabilities. The book contains explanations of key machine vision techniques and algorithms, along with the associated Java source code.
Special features include:
- A complete self-contained treatment of the topics and techniques essential to the understanding and implementation of machine vision.
- An introduction to object-oriented programming and to the Java programming language, with particular reference to its imaging capabilities.
- Java source code for a wide range of practical image processing and analysis functions.
- Readers will be given the opportunity to download a fully functional Java-based visual programming environment for machine vision, available via the WWW. This contains over 200 image processing, manipulation and analysis functions and will enable users to implement many of the ideas covered in this book.
- Details relating to the design of a Java-based visual programming environment for machine vision.
- An introduction to the Java 2D imaging and Java Advanced Imaging (JAI) APIs
- A wide range of illustrative examples.
- Practical treatment of the subject matter.
This book is aimed at senior undergraduate and postgraduate students in engineering and computer science as well as practitioners in machine vision who may wish to update or expand their knowledge of the subject. The techniques and algorithms of machine vision are expounded in a way that will be understood not only by specialists but also by those who are less familiar with the topic.

Spis treści

1. An Introduction to Machine Vision.- 1.1 Human, Computer and Machine Vision.- 1.2 Vision System Hardware.- 1.3 Vision System Software.- 1.4 Machine Vision System Design.- 1.4.1 Image Acquisition.- 1.4.2 Image Representation.- 1.4.3 Image Processing.- 1.4.4 Image Analysis.- 1.4.5 Image Classification.- 1.4.6 Systems Engineering.- 1.5 NeatVision: Where Java meets Machine Vision.- 1.5.1 NeatVisions Graphical User Interface (GUI).- 2. Java Fundamentals.- 2.1 The History of Java.- 2.1.1 What Makes Java Platform Independent?.- 2.1.2 The Just-In-Time Compiler.- 2.1.3 The Sun Java Software Development Kit (Java SDK).- 2.2 Object-oriented Programming.- 2.2.1 Encapsulation.- 2.2.2 Classes.- 2.2.3 Objects.- 2.2.4 Inheritance.- 2.2.5 Polymorphism.- 2.2.6 Abstract Classes.- 2.3 Java Language Basics.- 2.3.1 Variables.- 2.3.2 Access Control.- 2.3.3 Java Types.- 2.3.4 Java Operators.- 2.3.5 Java Comments.- 2.3.6 The super and this Keywords.- 2.3.7 Java Arrays.- 2.3.8 The “Object” and “Class” Classes.- 2.3.9 Interfaces.- 2.3.10 Packages.- 2.4 Applications and Applets.- 2.4.1 Writing Applications.- 2.4.2 Applets.- 2.4.3 An Applet and an Application?.- 2.5 Java and Image Processing.- 2.5.1 The Canvas Class.- 2.5.2 Java and Images.- 2.5.3 Image Producers and Image Consumers.- 2.5.4 Recovering Pixel Data from an Image Object.- 2.5.5 Recreating an Image Object from an Array of Pixels.- 2.6 Additional Classes.- 2.6.1 ColorModel.- 2.6.2 ImageFilter.- 2.6.3 CropImageFilter.- 2.6.4 RGBImageFilter.- 2.6.5 FilteredImageSource.- 2.7 Double Buffering.- 2.8 Recent Additions to Java for Imaging.- 2.8.1 Java2DAPI.- 2.8.2 Working with the Java 2D API.- 2.8.3 Renderable Layer and Rendered Layer.- 2.8.4 Java Advanced Imaging API (JAI).- 2.8.5 JAI Functionality.- 2.9 Additional Information on Java.- 2.10 Conclusion.- 3. Machine Vision Techniques.- 3.1 Elementary Image Processing Functions.- 3.1.1 Monadic, Point-by-point Operators.- 3.1.2 Intensity Histogram.- 3.1.3 Look-up Tables (LUT).- 3.1.4 Dyadic, Point-by-point Operators.- 3.2 Local Operators.- 3.2.1 Linear Local Operators.- 3.2.2 Non-linear Local Operators.- 3.2.3 Edge Detectors.- 3.2.4 N-tuple Operators.- 3.2.5 Edge Effects.- 3.2.6 Grey Scale Corner Detection.- 3.3 Binary Images.- 3.3.1 Boolean Operators.- 3.3.2 Connected Component (Blob) Analysis.- 3.3.3 Measurements on Binary Images.- 3.3.4 Run-length Coding.- 3.3.5 Shape Descriptors.- 3.4 Global Image Transforms.- 3.4.1 Geometric Transforms.- 3.4.2 Distance Transforms.- 3.4.3 Hough Transform.- 3.4.4 Two-dimensional Discrete Fourier Transform (DFT).- 3.5 Conclusion.- 4. Mathematical Morphology.- 4.1 Binary Mathematical Morphology.- 4.1.1 Dilation and Erosion.- 4.1.2 Hit-and-Miss Transform.- 4.1.3 Opening and Closing.- 4.1.4 Skeletonisation.- 4.1.5 Structuring Element Decomposition.- 4.1.6 Interval Coding.- 4.2 Grey Scale Mathematical Morphology.- 4.2.1 Basic Grey Scale Operators.- 4.2.2 Noise Removal using Grey Scale Morphology.- 4.2.3 Morphological Gradients.- 4.2.4 Point-Pairs.- 4.2.5 Top-Hat Transform.- 4.3 Morphological Reconstruction.- 4.3.1 Conditional Dilation.- 4.3.2 Geodesic Dilation.- 4.3.3 Geodesic Erosion.- 4.3.4 Reconstruction by Dilation.- 4.3.5 Reconstruction by Erosion.- 4.3.6 Ultimate Erosion.- 4.3.7 Double Threshold.- 4.3.8 Image Maxima.- 4.3.9 Image Minima.- 4.4 Morphological Segmentation.- 4.4.1 Skeleton Influence by Zones (SKIZ).- 4.4.2 Watershed Segmentation.- 4.5 Case Study: Geometric Packing.- 4.5.1 Geometric Packer Implementation.- 4.6 Morphological System Implementation.- 4.7 Conclusion.- 5. Texture Analysis.- 5.1 Texture and Images.- 5.2 Edge Density.- 5.3 Monte-Carlo Method.- 5.4 Auto-Correlation Function (ACF).- 5.5 Fourier Spectral Analysis.- 5.6 Histogram Features.- 5.7 Grey Level Run Length Method (GLRLM).- 5.8 Grey Level Difference Method (GLDM).- 5.9 Co-occurrence Analysis.- 5.9.1 Energy, or Angular Second Moment.- 5.9.2 Entropy.- 5.9.3 Inertia.- 5.9.4 Local Homogeneity (LH).- 5.10 Morphological Texture Analysis.- 5.10.1 Morphological Ratio.- 5.10.2 Granularity.- 5.11 Fractal Analysis.- 5.12 Textural Energy.- 5.13 Texture Spectrum Method.- 5.14 Local Binary Patterns (LBP).- 5.15 Random Field Models.- 5.16 Spatial/Frequency Methods.- 5.17 Autoregressive Model.- 5.18 Structural Approaches to Texture Analysis.- 5.19 Conclusion.- 6. Colour Image Analysis.- 6.1 Colour Cameras.- 6.2 Red-Green-Blue (RGB) Colour Representation.- 6.2.1 Maxwell’s Colour Triangle.- 6.2.2 One-dimensional Histograms: Colour Separations.- 6.2.3 Two-dimensional Scattergrams.- 6.3 Hue-Saturation-Intensity (HSI) Colour Representation.- 6.3.1 Colour Scattergrams.- 6.4 Opponent Process Representation.- 6.5 YIQ Colour Representation.- 6.6 YUV Colour Representation.- 6.7 CIE Chromaticity Diagram.- 6.8 CIEXYZ Colour Representation.- 6.9 CIELUV Colour Representation.- 6.10 CIELAB Colour Representation.- 6.11 Spatial CIELAB Colour Representation.- 6.11.1 Segmenting Colour Textures.- 6.12 Programmable Colour Filter (PCF).- 6.12.1 PCF Implementation.- 6.12.2 Recognising a Single Colour.- 6.12.3 Noise Effects.- 6.12.4 Colour Generalisation.- 6.13 Conclusion.- 7. NeatVision: Visual Programming for Machine Vision.- 7.1 Visual Programming in Neat Vision.- 7.1.1 Input and Output Components.- 7.1.2 Processing Components.- 7.1.3 Flow Control Components.- 7.1.4 System Development.- 7.1.5 Sample Programme.- 7.2 Java Programming in NeatVision.- 7.2.1 Data Flow Programming.- 7.2.2 Standard Component Architecture.- 7.2.3 Adding Functionality.- 7.2.4 Examples.- 7.3 The Neat Vision Application.- 7.3.1 Visual Programming in NeatVision.- 7.3.2 Image Processing.- 7.3.3 Other User Interfaces.- 7.3.4 The Integrated Software Development Environment.- 7.3.5 The Help Viewer.- 7.4 Sample Applications.- 7.4.1 Low-level Programming.- 7.4.2 High-level Programming.- 7.4.3 Isolating the Largest Item in an Image.- 7.4.4 Bottle-top Inspection.- 7.4.5 Plant-stem Location.- 7.5 Conclusion.- A. NeatVision Graphic File Formats.- B. NeatVision Imaging API Specification.- C. NeatVision Components.- References.