Modern Metaheuristics in Image Processing

Description

The use of metaheuristic algorithms (MA) has been increasing in recent years, and the image processing field is not the exempted of their application. In the last two years a big amount of MA has been introduced as alternatives for solving complex optimization problems. This book collects the most prominent MA of the 2019 and 2020 and verifies its use in image processing tasks. In addition, literature review of both MA and digital image processing is presented as part of the introductory information. Each algorithm is detailed explained with special focus in the tuning parameters and the proper implementation for the image processing tasks. Besides several examples permits to the reader explore and confirm the use of this kind of intelligent methods. Since image processing is widely used in different domains, this book considers different kinds of datasets that includes, magnetic resonance images, thermal images, agriculture images, among others. The reader then can have some ideas of implementation that complement the theory exposed of each optimization mechanism. Regarding the image processing problems this book consider the segmentation by using different metrics based on entropies or variances. In the same way, the identification of different shapes and the detection of objects are also covered in the corresponding chapters. Each chapter is complemented with a wide range of experiments and statistical analysis that permits the reader to judge about the performance of the MA. Finally, there is included a section that includes some discussion and conclusions. This section also provides some open questions and research opportunities for the audience. Cover Title Page Copyright Page Preface Table of Contents 1. Introduction 1.1 Image Segmentation by Thresholding 1.1.1 Image segmentation quality metrics 1.2 Metaheuristic Algorithms 1.2.1 A generic explanation of metaheuristic algorithms 1.3 Conclusions Exercises References 2. Literature Review 2.1 Introduction 2.2 Multilevel Thresholding over the Years 2.3 Current Trends on Image Thresholding 2.3.1 New metaheuristics and modifications 2.3.2 Hyper-heuristics 2.3.3 Multi-objective thresholding 2.3.4 Multidimensional histograms 2.3.5 Energy curve 2.4 Benchmark Images 2.5 Conclusions Exercises References 3. The Political Optimizer for Image Thresholding 3.1 Introduction 3.2 The Political Optimizer 3.3 Otsu’s Methodology between Class Variance 3.4 Multilevel Thresholding with PO and Otsu 3.5 Experiments 3.6 Conclusions Exercises References 4. Multilevel Thresholding by Using Manta Ray Foraging Optimization 4.1 Introduction 4.2 The Manta Ray Foraging Optimization 4.3 The Kapur Entropy 4.4 Multilevel Thresholding with MRFO and Kapur 4.5 Experiments 4.6 Conclusions Exercises References 5. Archimedes Optimization Algorithm and Cross-entropy 5.1 Archimedes Optimization Algorithm 5.1.1 Initialization 5.1.2 Update 5.1.3 Exploration phase 5.1.4 Exploitation phase 5.2 Cross-Entropy 5.3 Multilevel Thresholding with AOA and Cross-entropy 5.4 Experiments 5.5 Conclusions Exercises References 6. Equilibrium Optimizer and Masi Entropy 6.1 Equilibrium Optimizer 6.1.1 Initializing 6.1.2 Pooling 6.1.3 Updating 6.2 Masi Entropy 6.2.1 Masi entropy 6.3 Multilevel Thresholding with EO and Masi Entropy 6.4 Experiments 6.5 Conclusions Exercises References 7. MATLAB® Codes 7.1 Equilibrium Optimizer (EO) 7.2 Political Optimizer (PO) 7.3 Manta Ray Foraging Optimization (MRFO) 7.4 Archimedes Optimization Algorithm (AOA) Index