Image SegmentationSummarizes and improves new theory, methods, and applications of current image segmentation approaches, written by leaders in the field
The process of image segmentation divides an image into different regions based on the characteristics of pixels, resulting in a simplified image that can be more efficiently analyzed. Image segmentation has wide applications in numerous fields ranging from industry detection and bio-medicine to intelligent transportation and architecture.
Image Segmentation: Principles, Techniques, and Applications is an up-to-date collection of recent techniques and methods devoted to the field of computer vision. Covering fundamental concepts, new theories and approaches, and a variety of practical applications including medical imaging, remote sensing, fuzzy clustering, and watershed transform. In-depth chapters present innovative methods developed by the authors--such as convolutional neural networks, graph convolutional networks, deformable convolution, and model compression--to assist graduate students and researchers apply and improve image segmentation in their work.
Describes basic principles of image segmentation and related mathematical methods such as clustering, neural networks, and mathematical morphology. Introduces new methods for achieving rapid and accurate image segmentation based on classic image processing and machine learning theory. Presents techniques for improved convolutional neural networks for scene segmentation, object recognition, and change detection, etc. Highlights the effect of image segmentation in various application scenarios such as traffic image analysis, medical image analysis, remote sensing applications, and material analysis, etc.
Image Segmentation: Principles, Techniques, and Applications is an essential resource for undergraduate and graduate courses such as image and video processing, computer vision, and digital signal processing, as well as researchers working in computer vision and image analysis looking to improve their techniques and methods.
Author(s): Tao Lei, Asoke K. Nandi
Publisher: Wiley
Year: 2022
Language: English
Pages: 331
City: Hoboken
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
