Graph Convolutional Neural Networks for Computer Vision

Malini Alagarsamy, PhD is an assistant professor at the Thiagarajar College of Engineering. She has published more than 30 research papers in journals and national and international conferences. Her research interests include software engineering, mobile application development, green computing, Internet of Things, blockchain, and machine learning. Rajesh Kumar Dhanaraj, PhD is a Professor in the School of Computing Science and Engineering at Galgotias University. He has authored and edited more than 25 books and 53 articles in international journals and conferences and holds 21 patents. His research interests include machine learning, cyber-physical systems, and wireless sensor networks. J. Felicia Lilian is an Assistant Professor at the Thiagarajar College of Engineering. She has published more than 10 articles in international journals and conferences. Her research interests include natural language processing, machine learning, and deep learning. Vandana Sharma, PhD is an Associate Professor at the Amity Institute of Information Technology at the Amity University Noida Campus with more than 14 years of teaching experience. She has published 25 research papers in international journals and conferences. Her primary areas of interest include artificial intelligence, machine learning, blockchain technology, and the Internet of Things (IoT). Gheorghita Ghinea, PhD is a Professor in the Department of Computer Science at Brunel University London. He has more than 600 publications to his credit, including book chapters and research articles in international journals of repute. His research centers on extending the notion of multimedia with that of mulsemedia, a term to denote multiple sensorial media.

• Preface xv1 Role of Graph Convolutional Neural Networks (GCNN) in Computer Vision Applications 1A. Malini, Vandana Sharma, J. Felicia Lilian, Rajesh Kumar Dhanaraj, Sharangapriyan S. and Shrinivas S.1.1 Introduction 21.2 Understanding Convolutional Neural Network in Computer Vision 21.3 Core Components of CNN 31.4 Extending CNNs to Handle Graph-Structured Data 31.5 Application of GCNN in Computer Vision 61.6 Enhancing Performance and Interpretability with GCNN 81.7 Future Directions and Emerging Trends 101.8 Challenges and Open Research Questions 131.9 Case Studies: Real-World Applications 161.10 Conclusion 182 Scene Graph Generation from Static Images: Overview, Methods, and Applications 21K. Krishnakishore, R. Vijayarangan, V. Jagan Naveen and V. Kannan2.1 Introduction 222.2 Definition 242.3 Challenge 252.4 Scene Graph Generation 252.5 Static Image 252.6 Degradation of a Static Image 262.7 Method 1: Wavelet Feature Extraction 292.8 Psychological Perspective 322.9 Linguistic Perspective 332.10 Concepts and Conceptual Structures in Artificial Intelligence Perspective 352.11 Applications of CGS 372.12 Linguistic and Psychological Perspective 392.13 Image Synthesis from Layouts 412.14 Method Comparison 422.15 Conclusion 433 Transformation from CNN to Graph-Structured Data: Node Classification and Edge Prediction 47R. Vijayarangan, R. Satish Kumar, K. Umadevi and K. Ashok Kumar3.1 Why Graphs 483.2 SVM (Support Vector Machine) 573.3 XGBOOST 583.4 Artificial Neural Network (ANN) 593.5 Auto Encoder (AE) 623.6 Demographic and Related Data: Health Condition, Type of Gender, Age, Family Condition 633.7 Naïve Bayes (NB) 643.8 Random Forest (RF) 663.9 Conclusions 684 Research Trends and Challenges of GCNN Over CNN and Digital Image Processing Techniques 73Rithish Kanna S., Suganthi P. and Kavitha P.4.1 Introduction 744.2 Introduction to Convolutional Neural Network 754.3 Neural Style Transfer—Artistic View 784.4 Various Existing Works of NST 794.5 Hybrid Neural Style Transfer 814.6 Implementation of HNST 854.7 Results and Inference 864.8 Further Ideas of HNST 914.9 Conclusion 925 Classification of Graph Filtering Operations and Inductive Learning by Exploiting Multiple Graphs in GCNN 95S. Kayalvizhi, Harish Sekar and Prasanna Guptha M.P.5.1 Introduction 965.2 Graph Basics 965.3 Graph Convolutional Filters 985.4 Graph Filter Banks 1075.5 Graph Neural Networks 1105.6 Conclusion 1126 GCNN with Adaptive Filters for Hyperspectral Image Classification 117U. Moulali, R. Vijayarangan, S. Khaleel Ahamed and Kamakshaiah Kolli6.1 Introduction 1186.2 Related Works 1206.3 Classification of Graph Filtering Operations 1236.4 Experimental Analysis and Discussion 1346.5 Conclusion 1367 Graph Convolution Neural Network on Human Motion Prediction 141B. Subbulakshmi, M. Nirmala Devi and Srimadhi J.7.1 Introduction 1417.2 Graph Convolution Neural Network (GCN) 1467.3 Forms of GCN on Human Motion Prediction 1487.4 Types of Graphs Employed on GCN 1567.5 Conclusion 1578 GraphChXNet: A Graph Convolutional Neural Network-Based Model for Detecting Chest Diseases Using X-Ray Images 161D. Kiruthika, N. Vinothini, G. Jegan and G. Ananthi8.1 Introduction 1628.2 Proposed Methodology 1648.3 Results and Discussion 1718.4 Conclusion 1789 Aspect-Based Sentiment Analysis Using GCN 181Sachin K., Santhosh K.M.R., Sugindar A.D. and J. Felicia Lilian9.1 Introduction 1819.2 GCN and ABSA 1859.3 Advancements of GCN and ABSA over the Years 1899.4 Advancement of Technology with GCN and Algorithm Used 1969.5 Case Study on GCN Application: Recommendation Systems 1999.6 Summary 20210 Analysis and Classification Using Graph Convolutional Neural Networks in Medical Imaging 205M. Suguna and Priya Thiagarajan10.1 Introduction 20610.2 Literature Review—GCNN in Healthcare 21010.3 Methodology 21310.4 Results and Discussion 21810.5 Conclusion 22011 Case Studies and Real-World Applications of Graph Convolutional Networks in Computer Vision 225Yogeesh N.11.1 Introduction 22611.2 Graph Convolutional Networks: A Brief Review 22811.3 Case Study 1: Graph Convolutional Networks for Image Classification 23111.4 Case Study 2: Object Detection and Localization Using Graph Convolutional Networks 23611.5 Case Study 3: Semantic Segmentation with Graph Convolutional Networks 23811.6 Case Study 4: 3D Vision and Point Cloud Processing of Graph Convolutional Networks 24011.7 Case Study 5: Graph Convolutional Networks for Video Understanding and Action Recognition 24311.8 Other Notable Case Studies and Applications 24411.9 Discussion and Future Directions 24911.10 Conclusion 25012 Case Study and Use Cases of Dynamic Graphs in GCNN for Computer Vision 255S. Anubha Pearline and S. Geetha12.1 Introduction 25512.2 Graph Convolutional Neural Networks (GCNNs) 25912.3 GCNN Case Studies 26512.4 Challenges and Issues in GCNN for CV 27012.5 Conclusion 270References 271About the Editors 275Index 279