Machine vision technology has revolutionised the process of automated inspection in manufacturing. The specialist techniques required for inspection of natural products, such as food, leather, textiles and stone is still a challenging area of research. Topological variations make image processing algorithm development, system integration and mechanical handling issues much more complex. The practical issues of making machine vision systems operate robustly in often hostile environments together with the latest technological advancements are reviewed in this volume. Features: - Case studies based on real-world problems to demonstrate the practical application of machine vision systems. - In-depth description of system components including image processing, illumination, real-time hardware, mechanical handling, sensing and on-line testing. - Systems-level integration of constituent technologies for bespoke applications across a variety of industries. - A diverse range of example applications that a system may be required to handle from live fish to ceramic tiles. Machine Vision for the Inspection of Natural Products will be a valuable resource for researchers developing innovative machine vision systems in collaboration with food technology, textile and agriculture sectors. It will also appeal to practising engineers and managers in industries where the application of machine vision can enhance product safety and process efficiency.
This book will sell because it enables manufacturers of products involving natural materials to do so more reliably, safely and efficiently while relieving humans of the tedious and repetitive tasks previously associated with the inspection of less regular or well ordered products.
List of Contributors
1. Like Two Peas in a Pod
B.G. Batchelor
Editorial Introduction
1.1 Advantages of Being Able to See
1.2 Machine Vision
1.2.1 Model for Machine Vision Systems
1.2.2 Applications Classified by Task
1.2.3 Other Applications of Machine Vision
1.2.4 Machine Vision Is Not Natural
1.3 Product Variability
1.3.1 Linear Dimensions
1.3.2 Shape
1.3.3 Why Physical Tolerances Matter
1.3.4 Flexible and Articulated Objects
1.3.5 Soft and Semi-fluid Objects
1.3.6 Colour Variations
1.3.7 Transient Phenomena
1.3.8 Very Complex Objects
1.3.9 Uncooperative Objects
1.3.10 Texture
1.4 Systems Issues
1.5 References
2. Basic Machine Vision Techniques
B.G. Batchelor and P.F. Whelan
Editorial Introduction
2.1 Representation of Images
2.2 Elementary Image Processing Functions
2.2.1 Monadic Point-by-point Operators
2.2.2 Dyadic Point-by-point Operators
2.2.3 Local Operators
2.2.4 Linear Local Operators
2.2.5 Non-linear Local Operators
2.2.6 N-tuple Operators
2.2.7 Edge Effects
2.2.8 Intensity Histogram [hpi, hgi, he, hgc}
2.3 Binary Images
2.3.1 Measurements on Binary Images
2.3.2 Shape Descriptors
2.4 Binary Mathematical Morphology
2.4.1 Opening and Closing Operations
2.4.2 Structuring Element Decomposition
2.5 Grey-scale Morphology
2.6 Global Image Transforms
2.6.1 Hough Transform
2.6.2 Two-dimensional Discrete Fourier Transform
2.7 Texture Analysis
2.7.1 Statistical Approaches
2.7.2 Co-occurrence Matrix Approach
2.7.3 Structural Approaches
2.7.4 Morphological Texture Analysis
2.8 Implementation Considerations
2.8.1 Morphological System Implementation
2.9 Commercial Devices
2.9.1 Plug-in Boards: Frame-grabbers
2.9.2 Plug-in Boards: Dedicated Function
2.9.3 Self-contained Systems
2.9.4 Turn-key Systems
2.9.5 Software
2.10 Further Remarks
2.11 References
3. Intelligent Image Processing
B.G. Batchelor
Editorial Introduction
3.1 Why We Need Intelligence
3.2 Pattern Recognition
3.2.1 Similarity and Distance
3.2.2 Compactness Hypothesis
3.2.3 Pattern Recognition Models
3.3 Rule-based Systems
3.3.1 How Rules are Used
3.3.2 Combining Rules and Image Processing
3.4 Colour Recognition
3.4.1 RGB Representation
3.4.2 Pattern Recognition
3.4.3 Programmable Colour Filter
3.4.4 Colour Triangle
3.5 Methods and Applications
3.5.1 Human Artifacts
3.5.2 Plants
3.5.3 Semi-processed Natural Products
3.5.4 Food Products
3.6 Concluding Remarks
3.7 References
4. Using Natural Phenomena to Aid Food Produce Inspection
G. Long
Editorial Introduction
4.1 Introduction
4.2 Techniques to Exploit Natural Phenomena
4.3 Potato Sizing and Inspection
4.4 Stone Detection in Soft Fruit Using Auto-fluorescence
4.5 Brazil Nut Inspection
4.6 Intact Egg Inspection
4.7 Wafer Sizing
4.8 Enrobed Chocolates
4.9 Conclusion
4.10 References
5. Colour Sorting in the Food Industry
S.C. Bee and M.J. Honeywood
Editorial Introduction
5.1 Introduction
5.2 The Optical Sorting Machine
5.2.1 The Feed System
5.2.2 The Optical System
5.2.3 The Ejection System
5.2.4 The Image Processing Algorithms
5.3 Assessment of Objects for Colour Sorting
5.3.1 Spectrophotometry
5.3.2 Monochromatic Sorting
5.3.3 Bichromatic Sorting
5.3.4 Dual Monochromatic Sorting
5.3.5 Trichromatic Sorting
5.3.6 Fluorescence Techniques
5.3.7 Infrared Techniques
5.3.8 Optical Sorting with Lasers
5.4 The Optical Inspection System
5.4.1 Illumination
5.4.2 Background and Aperture
5.4.3 Optical Filters
5.4.4 Detectors
5.5 The Sorting System
5.5.1 Feed
5.5.2 Ejection
5.5.3 Cleaning and Dust Extraction
5.5.4 The Electronic Processing System
5.6 The Limitations of Colour Sorting
5.7 Future Trends
5.8 References
6. Surface Defect Detection on Ceramics
A.K. Forrest
Editorial Introduction
6.1 The Problem
6.2 Oblique Imaging
6.2.1 Oblique Lighting
6.2.2 Oblique Viewing
6.2.3 Image Rectification
6.2.4 Properties of Tile Surface
6.2.5 A Practical System
6.3 Obtaining More Information: Flying Spot Scanner
6.3.1 Introduction
6.3.2 Optical Layout
6.3.3 Detector Requirements
6.4 Image Processing of Multi-channels
6.5 Conclusion
6.6 References
7. On-line Automated Visual Grading of Fruit: Practical Challenges
P. Ngan, D. Penman and C. Bowman
Editorial Introduction
7.1 Introduction
7.2 Complete Surface Imaging
7.2.1 Introduction
7.2.2 Surface Feature Tracking
7.3 Stem/Calyx Discrimination
7.3.1 Concavity Detection Using Light Stripes
7.3.2 A New Approach to Structured Lighting
7.4 Conclusion
7.5 Acknowledgements
7.6 References
8. Vision-based Quality Control in Poultry Processing
W. Daley and D. Britton
Editorial Introduction
8.1 Introduction
8.2 Poultry Grading Application
8.2.1 Soft Computing: Fuzzy Logic and Neural Networks
8.2.2 Fuzzy Logic
8.2.3 Neural Networks
8.3 Algorithm Development
8.4 Bruise Detection
8.5 Fuzzy Logic Approach
8.6 The Minimum Distance Classifier
8.7 Comparing the Fuzzy Logic to the Minimum Distance Classifier Approach
8.8 Comparison with Human Operators
8.9 The Future
8.10 Conclusion
8.11 Acknowledgements
8.12 References
9. Quality Classification of Wooden Surfaces Using Gabor Filters and
Genetic Feature Optimisation
W. Polzleitner
Editorial Introduction
9.1 Introduction
9.1.1 Problem Statement
9.1.2 Algorithmic Approach
9.1.3 Trade-offs
9.2 Gabor Filters
9.2.1 Gabor Wavelet Functions
9.3 Optimisation Using a Genetic Algorithm
9.4 Experiments
9.5 Conclusion
9.6 References
10. An Intelligent Approach to Fabric Defect Detection in Textile
Processes
M. Mufti, G. Vachtsevanos and L. Dorrity
Editorial Introduction
10.1 Introduction
10.2 Architecture
10.3 Fuzzy Wavelet Analysis
10.4 Fuzzy Inferencing
10.5 Performance Metrics
10.6 Degree of Certainty
10.7 Reliability Index
10.8 Detectability and Identifiability Measures
10.9 Learning
10.10 Practical Implementation of Fuzzy Wavelet Analysis
10.11 Loom Control
10.12 Commercial Implementation
10.13 Conclusions
10.14 Acknowledgement
10.15 References
11. Automated Cutting of Natural Products: A Practical Packing Strategy
P.F. Whelan
Editorial Introduction
11.1 Introduction
11.2 The Packing/Cutting Problem
11.2.1 The One-dimensional Packing Problem
11.2.2 The Two-dimensional Packing Problem
11.2.3 The Three-dimensional Packing Problem
11.3 Review of Current Research
11.3.1 Packing of Regular Shapes
11.3.2 Packing of Irregular Shapes
11.4 System Implementation
11.4.1 Geometric Packer: Implementation
11.4.2 Heuristic Packer: Implementation
11.5 Performance Measures
11.6 System Issues
11.6.1 Packing Scenes with Defective Regions
11.7 Packing of Templates on Leather Hides
11.7.1 Packing of Templates on Defective Hides
11.7.2 Additional Points on Packing in the Leather Industry
11.8 Conclusion
11.9 References
12. Model-based Stereo Imaging for Estimating the Biomass of Live Fish
R.D. Tillett, J.A. Lines, D. Chan, N.J.B. McFarlane and L.G. Ross
Editorial Introduction
12.1 Introduction
12.2 Typical Sea-cage Images
12.3 Stereo Image Collection
12.3.1 Stereo Cameras
12.3.2 Calibration
12.3.3 Accuracy Achieved
12.3.4 Tank-based Trials
12.4 Locating Fish with a Trainable Classifier
12.5 Taking Measurments Using a Model-based Approach
12.6 Estimating Fish Mass
12.7 Conclusions
12.8 References
13. A System for Estimating the Size and Shape of Live Pigs
J.A. Marchant and C.P. Schofield
Editorial Introduction
13.1 Introduction
13.2 Description of the System
13.3 Calibration
13.3.1 General Method
13.3.2 Lense Distortion
13.3.3 Magnification
13.3.4 Curvature of the Animal's Surface
13.4 Image Analysis
13.4.1 Image Preparation
13.4.2 Initial and Improved Boundary
13.4.3 Division into Rump and Abdomen
13.4.4 Shoulder Estimation
13.4.5 Quality Control Checks
13.5 Experiments and Results
13.5.1 Experimental Arrangement
13.5.2 Initial Filtering of the Data
13.5.3 Image Analysis Repeatability
13.5.4 Relationship with Weight
13.6 Commercial Development
13.7 Conclusions
13.8 References
14. Sheep Pelt Inspection
P. Hilton, W. Power, M. Hayes and C. Bowman
Editorial Introduction
14.1 Introduction
14.2 Pelt Defects
14.3 Pelt Grading System
14.3.1 Laser Imaging
14.3.2 Laser Imager
14.3.3 Pelt Images
14.3.4 Processing System Architecture
14.3.5 Trials
14.4 Automated Defect Recognition and Classification
14.4.1 Defect Appearance
14.4.2 Supervised Learning
14.5 Pelt Identification
14.5.1 Pelt Branding
14.5.2 The Code Structure
14.5.3 Automated Code Reading
14.6 Conclusion and Future Work
14.7 Acknowledgements
14.8 References
15. Design of Object Location Algorithms and Their Use for Food and Cereals Inspection
E.R. Davies
Editorial Introduction
15.1 Introduction
15.2 The Inspection Milieu
15.3 Object Location
15.3.1 Feature Detection
15.3.2 The Hough Transform
15.3.3 The Maximal Clique Graph Matching Technique
15.4 Case Study: Jaffa Cake Inspection
15.5 Case Study: Inspection of Cream Biscuits
15.5.1 Problems with Maximal Cliques
15.6 Case Study: Location of Insects in Consignments of Grain
15.7 Case Study: Location of Non-insect Contaminants in Consignments of Grain
15.7.1 Problems with Closing
15.8 Case Study: High-speed Grain Location
15.9 Design of Template Masks
15.10 Concluding Remarks
15.11 Acknowledgements
15.12 References
16. X-ray Bone Detection in Further Processed Poultry Production
M. Graves
Editorial Introduction
16.1 Introduction
16.2 The Extent of the Problem
16.2.1 Data for the Occurrence of Bones in Poultry Meat
16.2.2 Future Trends Which Will Increase the Problem
16.3 The Technical Challenge
16.3.1 Attempts to Homogenise the Poultry Product
16.4 The BoneScan(tm) Solution
16.4.1 Design Requirements
16.4.2 Accuracy of Bone Detection
16.4.3 Low Level of False Rejection
16.4.4 Robustness of System Performance over Time
16.4.5 Cleanability of the System
16.4.6 High-volume Throughput
16.4.7 Ease of Use of the System
16.4.8 Robust Rejection Technology
16.4.9 Ability to Provide Management Information
16.4.10 Future Upgradability of the System
16.5 Applications Overview
16.5.1 The Inspection of Chicken Breast Butterflies
16.5.2 Chicken Thigh Meat Inspection
16.6 Stripped Cooked Chicken Meat Inspection
16.7 Future Work
16.8 Conclusions
16.9 Acknowledgements
16.10 References
17. Final Remarks
B.G. Batchelor and M. Graves
17.1 General Comments
17.2 Proverbs
Index