Preface xiii 1 Machine Learning-Based Virus Type Classification Using Transmission Electron Microscopy Virus Images 1Kalyan Kumar Jena, Sourav Kumar Bhoi, Soumya Ranjan Nayak and Chittaranjan Mallick 1.1 Introduction 2 1.2 Related Works 3 1.3 Methodology 4 1.4 Results and Discussion 6 1.5 Conclusion 16 References 16 2 Capsule Networks for Character Recognition in Low Resource Languages 23C. Abeysinghe, I. Perera and D.A. Meedeniya 2.1 Introduction 24 2.2 Background Study 25 2.2.1 Convolutional Neural Networks 25 2.2.2 Related Studies on One-Shot Learning 26 2.2.3 Character Recognition as a One-Shot Task 26 2.3 System Design 28 2.3.1 One-Shot Learning Implementation 31 2.3.2 Optimization and Learning 31 2.3.3 Dataset 32 2.3.4 Training Process 32 2.4 Experiments and Results 33 2.4.1 N-Way Classification 34 2.4.2 Within Language Classification 37 2.4.3 MNIST Classification 39 2.4.4 Sinhala Language Classification 41 2.5 Discussion 41 2.5.1 Study Contributions 41 2.5.2 Challenges and Future Research Directions 42 2.5.3 Conclusion 43 References 43 3 An Innovative Extended Method of Optical Pattern Recognition for Medical Images With Firm Accuracy—4f System-Based Medical Optical Pattern Recognition 47Dhivya Priya E.L., D. Jeyabharathi, K.S. Lavanya, S. Thenmozhi, R. Udaiyakumar and A. Sharmila 3.1 Introduction 48 3.1.1 Fourier Optics 48 3.2 Optical Signal Processing 50 3.2.1 Diffraction of Light 50 3.2.2 Biconvex Lens 51 3.2.3 4f System 51 3.2.4 Literature Survey 52 3.3 Extended Medical Optical Pattern Recognition 55 3.3.1 Optical Fourier Transform 55 3.3.2 Fourier Transform Using a Lens 55 3.3.3 Fourier Transform in the Far Field 56 3.3.4 Correlator Signal Processing 56 3.3.5 Image Formation in 4f System 57 3.3.6 Extended Medical Optical Pattern Recognition 58 3.4 Initial 4f System 59 3.4.1 Extended 4f System 59 3.4.2 Setup of 45 Degree 59 3.4.3 Database Creation 59 3.4.4 Superimposition of Diffracted Pattern 60 3.4.5 Image Plane 60 3.5 Simulation Output 60 3.5.1 MATLAB 60 3.5.2 Sample Input Images 61 3.5.3 Output Simulation 61 3.6 Complications in Real Time Implementation 64 3.6.1 Database Creation 64 3.6.2 Accuracy 65 3.6.3 Optical Setup 65 3.7 Future Enhancements 65 References 65 4 Brain Tumor Diagnostic System— A Deep Learning Application 69Kalaiselvi, T. and Padmapriya, S.T. 4.1 Introduction 69 4.1.1 Intelligent Systems 69 4.1.2 Applied Mathematics in Machine Learning 70 4.1.3 Machine Learning Basics 72 4.1.4 Machine Learning Algorithms 73 4.2 Deep Learning 75 4.2.1 Evolution of Deep Learning 75 4.2.2 Deep Networks 76 4.2.3 Convolutional Neural Networks 77 4.3 Brain Tumor Diagnostic System 80 4.3.1 Brain Tumor 80 4.3.2 Methodology 80 4.3.3 Materials and Metrics 84 4.3.4 Results and Discussions 85 4.4 Computer-Aided Diagnostic Tool 86 4.5 Conclusion and Future Enhancements 87 References 88 5 Machine Learning for Optical Character Recognition System 91Gurwinder Kaur and Tanya Garg 5.1 Introduction 91 5.2 Character Recognition Methods 92 5.3 Phases of Recognition System 93 5.3.1 Image Acquisition 93 5.3.2 Defining ROI 94 5.3.3 Pre-Processing 94 5.3.4 Character Segmentation 94 5.3.5 Skew Detection and Correction 95 5.3.6 Binarization 95 5.3.7 Noise Removal 97 5.3.8 Thinning 97 5.3.9 Representation 97 5.3.10 Feature Extraction 98 5.3.11 Training and Recognition 98 5.4 Post-Processing 101 5.5 Performance Evaluation 103 5.5.1 Recognition Rate 103 5.5.2 Rejection Rate 103 5.5.3 Error Rate 103 5.6 Applications of OCR Systems 104 5.7 Conclusion and Future Scope 105 References 105 6 Surface Defect Detection Using SVM-Based Machine Vision System with Optimized Feature 109Ashok Kumar Patel, Venkata Naresh Mandhala, Dinesh Kumar Anguraj and Soumya Ranjan Nayak 6.1 Introduction 110 6.2 Methodology 113 6.2.1 Data Collection 113 6.2.2 Data Pre-Processing 113 6.2.3 Feature Extraction 115 6.2.4 Feature Optimization 116 6.2.5 Model Development 119 6.2.6 Performance Evaluation 120 6.3 Conclusion 123 References 124 7 Computational Linguistics-Based Tamil Character Recognition System for Text to Speech Conversion 129Suriya, S., Balaji, M., Gowtham, T.M. and Rahul, Kumar S. 7.1 Introduction 130 7.2 Literature Survey 130 7.3 Proposed Approach 134 7.4 Design and Analysis 134 7.5 Experimental Setup and Implementation 136 7.6 Conclusion 151 References 151 8 A Comparative Study of Different Classifiers to Propose a GONN for Breast Cancer Detection 155Ankita Tiwari, Bhawana Sahu, Jagalingam Pushaparaj and Muthukumaran Malarvel 8.1 Introduction 156 8.2 Methodology 157 8.2.1 Dataset 157 8.2.2 Linear Regression 159 8.2.2.1 Correlation 160 8.2.2.2 Covariance 160 8.2.3 Classification Algorithm 161 8.2.3.1 Support Vector Machine 161 8.2.3.2 Random Forest Classifier 162 8.2.3.3 K-Nearest Neighbor Classifier 163 8.2.3.4 Decision Tree Classifier 163 8.2.3.5 Multi-Layered Perceptron 164 8.3 Results and Discussion 165 8.4 Conclusion 169 References 169 9 Mexican Sign-Language Static-Alphabet Recognition Using 3D Affine Invariants 171Guadalupe Carmona-Arroyo, Homero V. Rios-Figueroa and Martha Lorena Avendaño-Garrido 9.1 Introduction 171 9.2 Pattern Recognition 175 9.2.1 3D Affine Invariants 175 9.3 Experiments 177 9.3.1 Participants 179 9.3.2 Data Acquisition 179 9.3.3 Data Augmentation 179 9.3.4 Feature Extraction 181 9.3.5 Classification 181 9.4 Results 182 9.4.1 Experiment 1 182 9.4.2 Experiment 2 184 9.4.3 Experiment 3 184 9.5 Discussion 188 9.6 Conclusion 189 Acknowledgments 190 References 190 10 Performance of Stepped Bar Plate-Coated Nanolayer of a Box Solar Cooker Control Based on Adaptive Tree Traversal Energy and OSELM 193S. Shanmugan, F.A. Essa, J. Nagaraj and Shilpa Itnal 10.1 Introduction 194 10.2 Experimental Materials and Methodology 196 10.2.1 Furious SiO2/TiO2 Nanoparticle Analysis of SSBC Performance Methods 196 10.2.2 Introduction for OSELM by Use of Solar Cooker 198 10.2.3 Online Sequential Extreme Learning Machine (OSELM) Approach for Solar Cooker 199 10.2.4 OSELM Neural Network Adaptive Controller on Novel Design 199 10.2.5 Binary Search Tree Analysis of Solar Cooker 200 10.2.6 Tree Traversal of the Solar Cooker 205 10.2.7 Simulation Model of Solar Cooker Results 206 10.2.8 Program 207 10.3 Results and Discussion 210 10.4 Conclusion 212 References 214 11 Applications to Radiography and Thermography for Inspection 219Inderjeet Singh Sandhu, Chanchal Kaushik and Mansi Chitkara 11.1 Imaging Technology and Recent Advances 220 11.2 Radiography and its Role 220 11.3 History and Discovery of X-Rays 221 11.4 Interaction of X-Rays With Matter 222 11.5 Radiographic Image Quality 222 11.6 Applications of Radiography 225 11.6.1 Computed Radiography (CR)/Digital Radiography (DR) 225 11.6.2 Fluoroscopy 227 11.6.3 DEXA 228 11.6.4 Computed Tomography 229 11.6.5 Industrial Radiography 231 11.6.6 Thermography 234 11.6.7 Veterinary Imaging 235 11.6.8 Destructive Testing 235 11.6.9 Night Vision 235 11.6.10 Conclusion 236 References 236 12 Prediction and Classification of Breast Cancer Using Discriminative Learning Models and Techniques 241M. Pavithra, R. Rajmohan, T. Ananth Kumar and R. Ramya 12.1 Breast Cancer Diagnosis 242 12.2 Breast Cancer Feature Extraction 243 12.3 Machine Learning in Breast Cancer Classification 245 12.4 Image Techniques in Breast Cancer Detection 246 12.5 Dip-Based Breast Cancer Classification 248 12.6 RCNNs in Breast Cancer Prediction 255 12.7 Conclusion and Future Work 260 References 261 13 Compressed Medical Image Retrieval Using Data Mining and Optimized Recurrent Neural Network Techniques 263Vamsidhar Enireddy, Karthikeyan C., Rajesh Kumar T. and Ashok Bekkanti 13.1 Introduction 264 13.2 Related Work 265 13.2.1 Approaches in Content-Based Image Retrieval (CBIR) 265 13.2.2 Medical Image Compression 266 13.2.3 Image Retrieval for Compressed Medical Images 267 13.2.4 Feature Selection in CBIR 268 13.2.5 CBIR Using Neural Network 268 13.2.6 Classification of CBIR 269 13.3 Methodology 269 13.3.1 Huffman Coding 270 13.3.2 Haar Wavelet 271 13.3.3 Sobel Edge Detector 273 13.3.4 Gabor Filter 273 13.3.5 Proposed Hybrid CS-PSO Algorithm 276 13.4 Results and Discussion 277 13.5 Conclusion and Future Enhancement 282 13.5.1 Conclusion 282 13.5.2 Future Work 283 References 283 14 A Novel Discrete Firefly Algorithm for Constrained Multi-Objective Software Reliability Assessment of Digital Relay 287Madhusudana Rao Nalluri, K. Kannan and Diptendu Sinha Roy 14.1 Introduction 288 14.2 A Brief Review of the Digital Relay Software 291 14.3 Formulating the Constrained Multi-Objective Optimization of Software Redundancy Allocation Problem (CMOO-SRAP) 293 14.3.1 Mathematical Formulation 294 14.4 The Novel Discrete Firefly Algorithm for Constrained Multi-Objective Software Reliability Assessment of Digital Relay 297 14.4.1 Basic Firefly Algorithm 298 14.4.2 The Modified Discrete Firefly Algorithm 299 14.4.2.1 Generating Initial Population 299 14.4.2.2 Improving Solutions 299 14.4.2.3 Illustrative Example 301 14.4.3 Similarity-Based Parent Selection (SBPS) 303 14.4.4 Solution Encoding for the CMOO-SRAP for Digital Relay Software 305 14.5 Simulation Study and Results 305 14.5.1 Simulation Environment 305 14.5.2 Simulation Parameters 306 14.5.3 Configuration of Solution Vectors for the CMOOSRAP for Digital Relay 306 14.5.4 Results and Discussion 306 14.6 Conclusion 317 References 317 Index 323

The overall aim of the book is to extend recent concepts, methodologies, and empirical research advances of various machine vision inspection systems through image processing approaches. Machine Vision Inspection Systems (MVIS) is a multidisciplinary research field that emphasizes the image processing, machine vision and pattern recognition for industrial applications. Inspection techniques are generally used in destructive and non-destructive evaluation industry. Recently, the current automated vision research on machine inspection has gained more popularity with researchers and engineers, because the manual assessment of the inspection may fail and turn into false assessment due to a large number of examinations during the inspection process, leading to potential disaster. Machine Vision Inspection Systems (MVIS) is better able to avoid false assessment. This volume 2 covers machine learning-based approaches in MVIS applications and it can be employed to a wide diversity of problems particularly in non-destructive testing (NDT), presence/absence detection, defect/fault detection (weld, textile, tiles, wood, etc.), automated vision test & measurement, pattern matching, optical character recognition & verification (OCR/OCV), natural language processing, medical diagnosis, etc. The book is designed to address various aspects of recent methodologies, concepts, and research so readers will gain more in-depth insights in machine vision using machine learning-based approaches. Audience The book will have much interest in the industrial engineering manufacturing sector, especially the non-destructive testing industries such as defence, aerospace, remote sensing, defect/fault inspection specialists, medical diagnosis labs and instrument makers. Industry engineers and as well researchers in computer science associated with image processing, machine vision and pattern recognition, artificial intelligence, data analytics, will find this book valuable.