Image Segmentation. Principles, Techniques, and Applications

Cover
Title Page
Copyright Page
Brief Contents
Contents
About the Authors
Preface
Acknowledgment
List of Symbols and Abbreviations
List of Acronyms
Part I Principles
	Chapter 1 Introduction
		1.1 Preliminary Concepts
		1.2 Foundations of Image Segmentation
			1.2.1 Pixel-Based Image Segmentation
			1.2.2 Contour-Based Image Segmentation
			1.2.3 Region-Based Image Segmentation
			1.2.4 Neural Network–Based Image Segmentation
		1.3 Examples: Image Segmentation
			1.3.1 Automatic Drive
			1.3.2 Medical Image Analysis
			1.3.3 Remote Sensing
			1.3.4 Industrial Inspection
		1.4 Assessment of Image Segmentation
		1.5 Discussion and Summary
		References
	Chapter 2 Clustering
		2.1 Introduction
		2.2 K-Means
		2.3 Fuzzy C-means Clustering
		2.4 Hierarchical Clustering
		2.5 Spectral Clustering
		2.6 Gaussian Mixed Model
		2.7 Discussion and Summary
		References
	Chapter 3 Mathematical Morphology
		3.1 Introduction
		3.2 Morphological Filtering
			3.2.1 Erosion and Dilation
			3.2.2 Opening and Closing
			3.2.3 Basic Morphological Operation for Grayscale Images
			3.2.4 Composed Morphological Filters
		3.3 Morphological Reconstruction
			3.3.1 Geodesic Dilation and Erosion
			3.3.2 Reconstruction of Opening Operations and Closing Operations
		3.4 Watershed Transform
			3.4.1 Basic Concepts
			3.4.2 Watershed Segmentation Algorithms
		3.5 Multivariate Mathematical Morphology
			3.5.1 Related Concepts
			3.5.2 Duality of Grayscale Mathematical Morphology
			3.5.3 Ordering Relations
			3.5.4 Multivariate Dual Morphological Operators
		3.6 Discussion and Summary
		References
	Chapter 4 Neural Networks
		4.1 Artificial Neural Networks
			4.1.1 Overview
			4.1.2 Neuron Model
			4.1.3 Single-Layer Perceptron and Linear Network
				4.1.3.1 Single Layer Perceptron
				4.1.3.2 Perceptron Learning Algorithm
				4.1.3.3 Linear Neural Network
		4.2 Convolutional Neural Network
			4.2.1 Convolution and its Application in Images
				4.2.1.1 Definition
				4.2.1.2 One-Dimensional Convolution in Discrete Domain
				4.2.1.3 Two-Dimensional Convolution in Discrete Domain
				4.2.1.4 Extended Convolution Operation
			4.2.2 Convolutional Network Architecture and Parameter Learning
				4.2.2.1 Convolutional Network Architecture
				4.2.2.2 Convolution Layer
				4.2.2.3 Pooling Layer
				4.2.2.4 Full Connection Layer
				4.2.2.5 Parameter Learning
				4.2.2.6 Back-Propagation Algorithm
		4.3 Graph Convolutional Network
			4.3.1 Overview
			4.3.2 Convolutional Network over Spectral Domains
			4.3.3 Chebyshev Network
			4.3.4 Graph Convolutional Network
		4.4 Discussion and Summary
		References
Part II Methods
	Chapter 5 Fast and Robust Image Segmentation Using Clustering
		5.1 Introduction
		5.2 Related Work
			5.2.1 Objective Function of FCM Based on Neighborhood Information
			5.2.2 Membership Correction Based on Local Distance
		5.3 Local Spatial Information Integration to FCM
			5.3.1 Fast and Robust FCM Based on Histogram
			5.3.2 Morphological Reconstruction
		5.4 Membership Filtering for FCM
		5.5 Discussion and Summary
			5.5.1 Results on Synthetic Images
			5.5.2 Results on Real Images
			5.5.3 Results on Color Images
			5.5.4 Running Time
			5.5.5 Summary
		References
	Chapter 6 Fast Image Segmentation Using Watershed Transform
		6.1 Introduction
		6.2 Related Work
			6.2.1 Morphological Opening and Closing Reconstructions
			6.2.2 Multiscale and Adaptive Mathematical Morphology
			6.2.3 Seeded Segmentation
			6.2.4 Spectral Segmentation
		6.3 Adaptive Morphological Reconstruction (AMR)
			6.3.1 The Presented AMR
			6.3.2 The Monotonic Increasing-ness Property of AMR
			6.3.3 The Convergence Property of AMR
			6.3.4 The Algorithm of AMR
		6.4 AMR for Seeded Image Segmentation
			6.4.1 Seeded Image Segmentation
			6.4.2 Seed-Based Spectral Segmentation
		6.5 Discussion and Summary
			6.5.1 Discussion
			6.5.2 Summary
		References
	Chapter 7 Superpixel-Based Fast Image Segmentation
		7.1 Introduction
		7.2 Related Work
			7.2.1 Fuzzy Clustering with Adaptive Local Information
			7.2.2 FCM Based on Histogram of Gray Images
		7.3 Superpixel Integration to FCM
			7.3.1 Superpixel Based on Local Feature
			7.3.2 Superpixel-Based Fast FCM
		7.4 Discussion and Summary
			7.4.1 Comparison with Other Algorithms
			7.4.2 Parameter Setting
			7.4.3 Results on Synthetic Image
			7.4.4 Results on Real Images
			7.4.5 Execution Time
			7.4.6 Conclusions
		References
Part III Applications
	Chapter 8 Image Segmentation for Traffic Scene Analysis
		8.1 Introduction
		8.2 Related Work
			8.2.1 Convolutional Neural Networks for Image Classification
			8.2.2 Traffic Scene Semantic Segmentation Using Convolutional Neural Networks
		8.3 Multi-Scale Feature Fusion Network for Scene Segmentation
			8.3.1 Multi-Scale Feature Fusion Using Dilated Convolution
			8.3.2 Encoder-Decoder Architecture
			8.3.3 Experiments
		8.4 Self-Attention Network for Scene Segmentation
			8.4.1 Non-local attention Module
			8.4.2 Dual Attention Module
			8.4.3 Criss-Cross Attention
			8.4.4 Multi-scale Non-local Module
			8.4.5 Experiments
		8.5 Discussion and Summary
			8.5.1 Network Architecture Search
			8.5.2 Compact Networks
			8.5.3 Vision Transformer
		References
	Chapter 9 Image Segmentation for Medical Analysis
		9.1 Introduction
		9.2 Related Work
			9.2.1 Traditional Approaches for Medical Image Segmentation
			9.2.2 Deep Learning for Medical Image Segmentation
		9.3 Lightweight Network for Liver Segmentation
			9.3.1 Network Compression
			9.3.2 3D Deep Supervision
			9.3.3 Experiment
				9.3.3.1 Data Set Preprocessing
				9.3.3.2 Training
				9.3.3.3 Evaluation and Results
		9.4 Deformable Encoder–Decoder Network for Liver and Liver-Tumor Segmentation
			9.4.1 Deformable Encoding
			9.4.2 Ladder-ASPP
			9.4.3 Loss Function
			9.4.4 Postprocessing
			9.4.5 Experiment
				9.4.5.1 Data Set and Preprocessing
				9.4.5.2 Experimental Setup and Evaluation Metrics
				9.4.5.3 Ablation Study
				9.4.5.4 Experimental Comparison on Test Data Sets
				9.4.5.5 Model-Size Comparison
		9.5 Discussion and Summary
		References
	Chapter 10 Image Segmentation for Remote Sensing Analysis
		10.1 Introduction
		10.2 Related Work
			10.2.1 Threshold Segmentation Methods
			10.2.2 Clustering Segmentation Methods
			10.2.3 Region Segmentation Methods
			10.2.4 Segmentation Methods Using Deep Learning
		10.3 Unsupervised Change Detection for Remote Sensing Images
			10.3.1 Image Segmentation Using Image Structuring Information
			10.3.2 Image Segmentation Using Gaussian Pyramid
			10.3.3 Fast Fuzzy C-Means for Change Detection
			10.3.4 Postprocessing for Change Detection
			10.3.5 The Proposed Methodology
			10.3.6 Experiments
				10.3.6.1 Data Description
				10.3.6.2 Experimental Setup
				10.3.6.3 Experimental Results
				10.3.6.4 Experimental Analysis
		10.4 End-to-End Change Detection for VHR Remote Sensing Images
			10.4.1 MMR for Image Preprocessing
			10.4.2 Pyramid Pooling
			10.4.3 The Network Structure of FCN-PP
			10.4.4 Experiments
				10.4.4.1 Data Description
				10.4.4.2 Experimental Setup
				10.4.4.3 Experimental Results
				10.4.4.4 Experimental Analysis
		10.5 Discussion and Summary
		References
	Chapter 11 Image Segmentation for Material Analysis
		11.1 Introduction
		11.2 Related Work
			11.2.1 Metal Materials
			11.2.2 Foam Materials
			11.2.3 Ceramics Materials
		11.3 Image Segmentation for Metal Material Analysis
			11.3.1 Segmentation of Porous Metal Materials
			11.3.2 Classification of Holes
			11.3.3 Experiment Analysis
		11.4 Image Segmentation for Foam Material Analysis
			11.4.1 Eigenvalue Gradient Clustering
			11.4.2 The Algorithm
			11.4.3 Experiment Analysis
		11.5 Image Segmentation for Ceramics Material Analysis
			11.5.1 Preprocessing
			11.5.2 Robust Watershed Transform
			11.5.3 Contour Optimization
			11.5.4 Experiment Analysis
		11.6 Discussion and Summary
		References
Index
EULA