Quantum inspired meta-heuristics for image analysis /
Sandip Dey (Global Institute of Management and Technology, Krishnanagar, Nadia, West Bengal, India), Siddhartha Bhattacharyya (RCC Institute of Information Technology, Kolkata, India), Ujjwal Maulik (Jadavpur University, Kolkata, India).
- 1 online resource.
ABOUT THE AUTHORS SANDIP DEY, PHD, is an Associate Professor and Chair in the department of Computer Science & Engineering at the Global Institute of Management and Technology, Krishnanagar, Nadia, West Bengal, India.
SIDDHARTHA BHATTACHARYYA, PHD, is the Principal of RCC Institute of Information Technology, Kolkata, India.
UJJWAL MAULIK, PHD, is the Chair of and Professor in the Department of Computer Science and Engineering, Jadavpur University, Kolkata, India.
Includes bibliographical references and index.
TABLE OF CONTENTS Preface xiii
Acronyms xv
1 Introduction 1
1.1 Image Analysis 3
1.1.1 Image Segmentation 4
1.1.2 Image Thresholding 5
1.2 Prerequisites of Quantum Computing 7
1.2.1 Dirac’s Notation 8
1.2.2 Qubit 8
1.2.3 Quantum Superposition 8
1.2.4 Quantum Gates 9
1.2.4.1 Quantum NOT Gate (Matrix Representation) 9
1.2.4.2 Quantum Z Gate (Matrix Representation) 9
1.2.4.3 Hadamard Gate 10
1.2.4.4 Phase Shift Gate 10
1.2.4.5 Controlled NOT Gate (CNOT) 10
1.2.4.6 SWAP Gate 11
1.2.4.7 Toffoli Gate 11
1.2.4.8 Fredkin Gate 12
1.2.4.9 Quantum Rotation Gate 13
1.2.5 Quantum Register 14
1.2.6 Quantum Entanglement 14
1.2.7 Quantum Solutions of NP-complete Problems 15
1.3 Role of Optimization 16
1.3.1 Single-objective Optimization 16
1.3.2 Multi-objective Optimization 18
1.3.3 Application of Optimization to Image Analysis 18
1.4 Related Literature Survey 19
1.4.1 Quantum-based Approaches 19
1.4.2 Meta-heuristic-based Approaches 21
1.4.3 Multi-objective-based Approaches 22
1.5 Organization of the Book 23
1.5.1 Quantum Inspired Meta-heuristics for Bi-level Image Thresholding 24
1.5.2 Quantum Inspired Meta-heuristics for Gray-scale Multi-level Image Thresholding 24
1.5.3 Quantum Behaved Meta-heuristics for True Color Multi-level Thresholding 24
1.5.4 Quantum Inspired Multi-objective Algorithms for Multi-level Image Thresholding 24
1.6 Conclusion 25
1.7 Summary 25
Exercise Questions 26
2 Review of Image Analysis 29
2.1 Introduction 29
2.2 Definition 29
2.3 Mathematical Formalism 30
2.4 Current Technologies 30
2.4.1 Digital Image Analysis Methodologies 31
2.4.1.1 Image Segmentation 31
2.4.1.2 Feature Extraction/Selection 32
2.4.1.3 Classification 34
2.5 Overview of Different Thresholding Techniques 35
2.5.1 Ramesh’s Algorithm 35
2.5.2 Shanbag’s Algorithm 36
2.5.3 Correlation Coefficient 37
2.5.4 Pun’s Algorithm 38
2.5.5 Wu’s Algorithm 38
2.5.6 Renyi’s Algorithm 39
2.5.7 Yen’s Algorithm 39
2.5.8 Johannsen’s Algorithm 40
2.5.9 Silva’s Algorithm 40
2.5.10 Fuzzy Algorithm 41
2.5.11 Brink’s Algorithm 41
2.5.12 Otsu’s Algorithm 43
2.5.13 Kittler’s Algorithm 43
2.5.14 Li’s Algorithm 44
2.5.15 Kapur’s Algorithm 44
2.5.16 Huang’s Algorithm 45
2.6 Applications of Image Analysis 46
2.7 Conclusion 47
2.8 Summary 48
Exercise Questions 48
3 Overview of Meta-heuristics 51
3.1 Introduction 51
3.1.1 Impact on Controlling Parameters 52
3.2 Genetic Algorithms 52
3.2.1 Fundamental Principles and Features 53
3.2.2 Pseudo-code of Genetic Algorithms 53
3.2.3 Encoding Strategy and the Creation of Population 54
3.2.4 Evaluation Techniques 54
3.2.5 Genetic Operators 54
3.2.6 Selection Mechanism 54
3.2.7 Crossover 55
3.2.8 Mutation 56
3.3 Particle Swarm Optimization 56
3.3.1 Pseudo-code of Particle Swarm Optimization 57
3.3.2 PSO: Velocity and Position Update 57
3.4 Ant Colony Optimization 58
3.4.1 Stigmergy in Ants: Biological Inspiration 58
3.4.2 Pseudo-code of Ant Colony Optimization 59
3.4.3 Pheromone Trails 59
3.4.4 Updating Pheromone Trails 59
3.5 Differential Evolution 60
3.5.1 Pseudo-code of Differential Evolution 60
3.5.2 Basic Principles of DE 61
3.5.3 Mutation 61
3.5.4 Crossover 61
3.5.5 Selection 62
3.6 Simulated Annealing 62
3.6.1 Pseudo-code of Simulated Annealing 62
3.6.2 Basics of Simulated Annealing 63
3.7 Tabu Search 64
3.7.1 Pseudo-code of Tabu Search 64
3.7.2 Memory Management in Tabu Search 65
3.7.3 Parameters Used in Tabu Search 65
3.8 Conclusion 65
3.9 Summary 65
Exercise Questions 66
4 Quantum Inspired Meta-heuristics for Bi-level Image Thresholding 69
4.1 Introduction 69
4.2 Quantum Inspired Genetic Algorithm 70
4.2.1 Initialize the Population of Qubit Encoded Chromosomes 71
4.2.2 Perform Quantum Interference 72
4.2.2.1 Generate Random Chaotic Map for Each Qubit State 72
4.2.2.2 Initiate Probabilistic Switching Between Chaotic Maps 73
4.2.3 Find the Threshold Value in Population and Evaluate Fitness 74
4.2.4 Apply Selection Mechanism to Generate a New Population 74
7.3.5 Quantum Inspired Multi-objective Ant Colony Optimization 309
7.3.5.1 Complexity Analysis 310
7.4 Implementation Results 311
7.4.1 Experimental Results 311
7.4.1.1 The Results of Multi-Level Thresholding for QINSGA-II, NSGA-II, and SMS-EMOA 312
7.4.1.2 The Stability of the Comparable Methods 312
7.4.1.3 Performance Evaluation 315
7.5 Conclusion 327
7.6 Summary 327
Exercise Questions 328
Coding Examples 329
8 Conclusion 333
Bibliography 337
Index 355
Introduces quantum inspired techniques for image analysis for pure and true gray scale/color images in a single/multi-objective environment
This book will entice readers to design efficient meta-heuristics for image analysis in the quantum domain. It introduces them to the essence of quantum computing paradigm, its features, and properties, and elaborates on the fundamentals of different meta-heuristics and their application to image analysis. As a result, it will pave the way for designing and developing quantum computing inspired meta-heuristics to be applied to image analysis.
Quantum Inspired Meta-heuristics for Image Analysis begins with a brief summary on image segmentation, quantum computing, and optimization. It also highlights a few relevant applications of the quantum based computing algorithms, meta-heuristics approach, and several thresholding algorithms in vogue. Next, it discusses a review of image analysis before moving on to an overview of six popular meta-heuristics and their algorithms and pseudo-codes. Subsequent chapters look at quantum inspired meta-heuristics for bi-level and gray scale multi-level image thresholding; quantum behaved meta-heuristics for true color multi-level image thresholding; and quantum inspired multi-objective algorithms for gray scale multi-level image thresholding. Each chapter concludes with a summary and sample questions.
Provides in-depth analysis of quantum mechanical principles Offers comprehensive review of image analysis Analyzes different state-of-the-art image thresholding approaches Detailed current, popular standard meta-heuristics in use today Guides readers step by step in the build-up of quantum inspired meta-heuristics Includes a plethora of real life case studies and applications Features statistical test analysis of the performances of the quantum inspired meta-heuristics vis-à-vis their conventional counterparts Quantum Inspired Meta-heuristics for Image Analysis is an excellent source of information for anyone working with or learning quantum inspired meta-heuristics for image analysis.