Image Segmentation
Principles, Techniques, and Applications
1st Edition
Published on 26. September 2022
336 pages
978-1-119-85903-1 (ISBN)
Description
Image Segmentation
Summarizes 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.
Summarizes 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.
More details
Other editions
Additional editions
T Lei
Image Segmentation - Principles, Techniques, and Applications
Principles, Techniques, and Applications
Book
10/2022
1st Edition
Wiley-Blackwell
€134.50
Shipment within 15-20 days
Software
09/2022
Wiley
€145.94
No shipping information available
Persons
Tao Lei, Professor, School of Electronic Information and Artificial Intelligence, Shaanxi University of Science and Technology, China. His research interests include image processing, pattern recognition, and machine learning and he has authored and co-authored more than 100 research papers.
Asoke K. Nandi, Professor, Department of Electronic and Electrical Engineering, Brunel University London, UK. He is also Distinguished Visiting Professor, Xi'an Jiaotong University, China. Professor Nandi has authored over 600 technical publications, including 280 journal papers as well as five books.
Content
Preface
About the Authors
List of Abbreviations
Part One: Principle
1 Introduction to Image Segmentation
2 Principles of Clustering
3 Principles of Mathematical Morphology
4 Principles of Neural Network
Part Two: Methods
5 Fast and Robust Image Segmentation Using Clustering
6 Fast Image Segmentation Using Watershed Transform
7 Superpixel-based Fast Image Segmentation
Part Three: Application
8 Image Segmentation for Traffic Scene Analysis
9 Image Segmentation for Medical Analysis
10 Image Segmentation for Remote Sensing Analysis
11 Image Segmentation for Material Analysis
List of Symbols and Abbreviations
Chapter 1
Symbols and Abbreviations p ii The number of pixels of i-th class predicted as belonging to i-th class p ij The number of pixels of i-th class predicted as belonging to j-th class MPA Mean pixel accuracy TP The true positive fraction FP The false positive fraction FN The false negative fraction F1-Score The harmonic mean of precision and recall S(A) The set of surface voxels of A
Chapter 2
Symbols and Abbreviations c The number of clusters N The number of samples ? The number of iterations u ik The strength of the i-th sample xi relative to the k-th cluster center vk ||xi - vk|| The Euclidean distance between sample xi and cluster center vk ? The convergence threshold B The maximum number of iterations V (0) The initialize cluster center v k The cluster center ? j The Lagrange multiplier U (0) The initialized membership matrix U The anti fuzzy membership matrix S A A similarity matrix s The scale parameters of Gaussian kernel function D A degree matrix F e The feature vector N(X │ vk, Sk) The k-th Gaussian density function Sk The covariance matrix p k The Prior Probability
Chapter 3
Symbols and Abbreviations A A set E A structuring element f An image d The dilation operation e The erosion operation C l A complete lattice G A complete lattice ? Opening operator ? Closing operator ? Idempotent s f The filter of size Geodesic dilation g A masker image The geodesic erosion x A pixel in an image t max The maximum value f c The complement of a grayscale image f ? * The dual operator of ? P 1 The function of the variant r P 2 The function of the variant g P 3 The function of the variant b
Chapter 4
Symbols and Abbreviations w i The weight b The bias term z A hyperplane f a An activation function a r An activated result x i An input s(·) A sigmoid function ß A learnable parameter or a fixed hyperparameter M The maximum number of iterations * The convolution operation F The convolution kernel space size K The number of convolution kernels S c The convolution kernel sliding step P The filling size of input tensors N The number of categories of classification tasks l The number of convolutional layers ? The cross-correlation operation err The error term p Feature maps The derivative of the activation function The wide convolution rot180 (·) The 180° of rotation F{f} The corresponding spectral domain signal L A laplace matrix x A graph signal g A filter ? Hadamard Product g ? A diagonal matrix X A feature Matrix The i-th column of matrix T k The chebyshev polynomial Ø A parameter matrix Z The output after graph convolution H l The node vector of the l-th layer W l The parameters of the corresponding layer M A An adjacency matrix
Chapter 5
Symbols and Abbreviations g = {x1, x2, ?, xN} A grayscale image x i The gray value of the i-th pixel pv k The prototype value of the k-th cluster v ki The fuzzy membership value U = [uki]c × N The membership partition matrix N The total number of pixels c The number of clusters m The weighting exponent G ki The fuzzy factor x r The neighbor of xi N i The set of neighbors within a window around xi d ir The spatial Euclidean distance A mean value or median value u kl The fuzzy membership ? l The gray level t The number of the gray levels R C The morphological closing reconstruction f o The original image ? ...
