Оглавление
Группа авторов. Machine Vision Inspection Systems, Machine Learning-Based Approaches
Contents
List of Tables
List of Illustrations
Guide
Pages
Machine Vision Inspection Systems, Volume 2. Machine Learning-Based Approaches
Preface
1. Machine Learning-Based Virus Type Classification Using Transmission Electron Microscopy Virus Images
1.1 Introduction
1.2 Related Works
1.3 Methodology
1.4 Results and Discussion
1.5 Conclusion
References
2. Capsule Networks for Character Recognition in Low Resource Languages
2.1 Introduction
2.2 Background Study. 2.2.1 Convolutional Neural Networks
2.2.2 Related Studies on One-Shot Learning
2.2.3 Character Recognition as a One-Shot Task
2.3 System Design
2.3.1 One-Shot Learning Implementation
2.3.2 Optimization and Learning
2.3.3 Dataset
2.3.4 Training Process
2.4 Experiments and Results
2.4.1 N-Way Classification
2.4.2 Within Language Classification
2.4.3 MNIST Classification
2.4.4 Sinhala Language Classification
2.5 Discussion. 2.5.1 Study Contributions
2.5.2 Challenges and Future Research Directions
2.5.3 Conclusion
References
3. An Innovative Extended Method of Optical Pattern Recognition for Medical Images With Firm Accuracy—4f System-Based Medical Optical Pattern Recognition
3.1 Introduction. 3.1.1 Fourier Optics
3.2 Optical Signal Processing
3.2.1 Diffraction of Light
3.2.2 Biconvex Lens
3.2.3 4f System
3.2.4 Literature Survey
3.3 Extended Medical Optical Pattern Recognition. 3.3.1 Optical Fourier Transform
3.3.2 Fourier Transform Using a Lens
3.3.3 Fourier Transform in the Far Field
3.3.4 Correlator Signal Processing
3.3.5 Image Formation in 4f System
3.3.6 Extended Medical Optical Pattern Recognition
3.4 Initial 4f System
3.4.1 Extended 4f System
3.4.2 Setup of 45 Degree
3.4.3 Database Creation
3.4.4 Superimposition of Diffracted Pattern
3.4.5 Image Plane
3.5 Simulation Output. 3.5.1 MATLAB
3.5.2 Sample Input Images
3.5.3 Output Simulation
3.6 Complications in Real Time Implementation
3.6.1 Database Creation
3.6.2 Accuracy
3.6.3 Optical Setup
3.7 Future Enhancements
References
4. Brain Tumor Diagnostic System— A Deep Learning Application
4.1 Introduction. 4.1.1 Intelligent Systems
4.1.2 Applied Mathematics in Machine Learning
4.1.3 Machine Learning Basics
4.1.4 Machine Learning Algorithms
4.2 Deep Learning. 4.2.1 Evolution of Deep Learning
4.2.2 Deep Networks
4.2.3 Convolutional Neural Networks
4.3 Brain Tumor Diagnostic System. 4.3.1 Brain Tumor
4.3.2 Methodology
4.3.3 Materials and Metrics
4.3.4 Results and Discussions
4.4 Computer-Aided Diagnostic Tool
4.5 Conclusion and Future Enhancements
References
5. Machine Learning for Optical Character Recognition System
5.1 Introduction
5.2 Character Recognition Methods
5.3 Phases of Recognition System
5.3.1 Image Acquisition
5.3.2 Defining ROI
5.3.3 Pre-Processing
5.3.4 Character Segmentation
5.3.5 Skew Detection and Correction
5.3.6 Binarization
5.3.7 Noise Removal
5.3.8 Thinning
5.3.9 Representation
5.3.10 Feature Extraction
5.3.11 Training and Recognition
5.4 Post-Processing
5.5 Performance Evaluation
5.5.1 Recognition Rate
5.5.2 Rejection Rate
5.5.3 Error Rate
5.6 Applications of OCR Systems
5.7 Conclusion and Future Scope
References
6. Surface Defect Detection Using SVM-Based Machine Vision System with Optimized Feature
6.1 Introduction
6.2 Methodology
6.2.1 Data Collection
6.2.2 Data Pre-Processing
6.2.3 Feature Extraction
6.2.4 Feature Optimization
6.2.5 Model Development
6.2.6 Performance Evaluation
6.3 Conclusion
References
7. Computational Linguistics-Based Tamil Character Recognition System for Text to Speech Conversion
7.1 Introduction
7.2 Literature Survey
7.3 Proposed Approach
7.4 Design and Analysis
7.5 Experimental Setup and Implementation
7.6 Conclusion
References
8. A Comparative Study of Different Classifiers to Propose a GONN for Breast Cancer Detection
8.1 Introduction
8.2 Methodology
8.2.1 Dataset
8.2.2 Linear Regression
8.2.2.1 Correlation
8.2.2.2 Covariance
8.2.3 Classification Algorithm
8.2.3.1 Support Vector Machine
8.2.3.2 Random Forest Classifier
8.2.3.3 K-Nearest Neighbor Classifier
8.2.3.4 Decision Tree Classifier
8.2.3.5 Multi-Layered Perceptron
8.3 Results and Discussion
8.4 Conclusion
References
9. Mexican Sign-Language Static-Alphabet Recognition Using 3D Affine Invariants
9.1 Introduction
9.2 Pattern Recognition
9.2.1 3D Affine Invariants
9.3 Experiments
9.3.1 Participants
9.3.2 Data Acquisition
9.3.3 Data Augmentation
9.3.4 Feature Extraction
9.3.5 Classification
9.4 Results. 9.4.1 Experiment 1
9.4.2 Experiment 2
9.4.3 Experiment 3
9.5 Discussion
9.6 Conclusion
Acknowledgments
References
10. Performance of Stepped Bar Plate-Coated Nanolayer of a Box Solar Cooker Control Based on Adaptive Tree Traversal Energy and OSELM
10.1 Introduction
10.2 Experimental Materials and Methodology. 10.2.1 Furious SiO2/TiO2 Nanoparticle Analysis of SSBC Performance Methods
10.2.2 Introduction for OSELM by Use of Solar Cooker
10.2.3 Online Sequential Extreme Learning Machine (OSELM) Approach for Solar Cooker
10.2.4 OSELM Neural Network Adaptive Controller on Novel Design
10.2.5 Binary Search Tree Analysis of Solar Cooker
10.2.6 Tree Traversal of the Solar Cooker
10.2.7 Simulation Model of Solar Cooker Results
10.2.8 Program
10.3 Results and Discussion
10.4 Conclusion
References
11. Applications to Radiography and Thermography for Inspection
11.1 Imaging Technology and Recent Advances
11.2 Radiography and its Role
11.3 History and Discovery of X-Rays
11.4 Interaction of X-Rays With Matter
11.5 Radiographic Image Quality
11.6 Applications of Radiography
11.6.1 Computed Radiography (CR)/Digital Radiography (DR)
11.6.2 Fluoroscopy
11.6.3 DEXA
11.6.4 Computed Tomography
11.6.5 Industrial Radiography
11.6.6 Thermography
11.6.7 Veterinary Imaging
11.6.8 Destructive Testing
11.6.9 Night Vision
11.6.10 Conclusion
References
12. Prediction and Classification of Breast Cancer Using Discriminative Learning Models and Techniques
12.1 Breast Cancer Diagnosis
12.2 Breast Cancer Feature Extraction
12.3 Machine Learning in Breast Cancer Classification
12.4 Image Techniques in Breast Cancer Detection
12.5 Dip-Based Breast Cancer Classification
12.6 RCNNs in Breast Cancer Prediction
12.7 Conclusion and Future Work
References
13. Compressed Medical Image Retrieval Using Data Mining and Optimized Recurrent Neural Network Techniques
13.1 Introduction
13.2 Related Work. 13.2.1 Approaches in Content-Based Image Retrieval (CBIR)
13.2.2 Medical Image Compression
13.2.3 Image Retrieval for Compressed Medical Images
13.2.4 Feature Selection in CBIR
13.2.5 CBIR Using Neural Network
13.2.6 Classification of CBIR
13.3 Methodology
13.3.1 Huffman Coding
13.3.2 Haar Wavelet
13.3.3 Sobel Edge Detector
13.3.4 Gabor Filter
13.3.5 Proposed Hybrid CS-PSO Algorithm
13.4 Results and Discussion
13.5 Conclusion and Future Enhancement. 13.5.1 Conclusion
13.5.2 Future Work
References
14. A Novel Discrete Firefly Algorithm for Constrained Multi-Objective Software Reliability Assessment of Digital Relay
14.1 Introduction
14.2 A Brief Review of the Digital Relay Software
14.3 Formulating the Constrained Multi-Objective Optimization of Software Redundancy Allocation Problem (CMOO-SRAP)
14.3.1 Mathematical Formulation
14.4 The Novel Discrete Firefly Algorithm for Constrained Multi-Objective Software Reliability Assessment of Digital Relay
14.4.1 Basic Firefly Algorithm
14.4.2 The Modified Discrete Firefly Algorithm
14.4.2.1 Generating Initial Population
14.4.2.2 Improving Solutions
14.4.2.3 Illustrative Example
14.4.3 Similarity-Based Parent Selection (SBPS)
14.4.4 Solution Encoding for the CMOO-SRAP for Digital Relay Software
14.5 Simulation Study and Results
14.5.1 Simulation Environment
14.5.2 Simulation Parameters
14.5.3 Configuration of Solution Vectors for the CMOO-SRAP for Digital Relay
14.5.4 Results and Discussion
14.6 Conclusion
References
Index
WILEY END USER LICENSE AGREEMENT
