Adaptive Image Processing,9780849302831

Adaptive Image Processing

by ;
Edition: 1st
ISBN13: 9780849302831
ISBN10: 0849302838
Format: Hardcover
Pub. Date: 2001-12-21
Publisher(s): CRC
List Price: $176.49

Rent Textbook

Select for Price
Add to Cart
There was a problem. Please try again later.

New Textbook

We're Sorry
Sold Out

Used Textbook

We're Sorry
Sold Out

eTextbook

We're Sorry
Not Available

Buy from our Marketplace starting at $13.81

How Marketplace Works:

  • This item is offered by an independent seller and not shipped from our warehouse
  • Item details like edition and cover design may differ from our description; see seller's comments before ordering.
  • Sellers much confirm and ship within two business days; otherwise, the order will be cancelled and refunded.
  • Marketplace purchases cannot be returned to eCampus.com. Contact the seller directly for inquiries; if no response within two days, contact customer service.
  • Additional shipping costs apply to Marketplace purchases. Review shipping costs at checkout.

Summary

There is not a single book that treats this problem from a viewpoint which is directly linked to human perception-until now. Gives a detailed account of computational intelligence methods and algorithms for adaptive image processing in regularization, edge detection, and early vision.

Table of Contents

Introduction
1(22)
The Importance of Vision
1(1)
Adaptive Image Processing
2(1)
The Three Main Image Feature Classes
3(2)
Difficulties in Adaptive Image Processing System Design
5(3)
Computational Intelligence Techniques
8(5)
Scope of the Book
13(6)
Image Restoration
14(4)
Edge Characterization and Detection
18(1)
Contributions of the Current Work
19(2)
Application of Neural Networks for Image Restoration
19(1)
Application of Neural Networks to Edge Characterization
20(1)
Application of Fuzzy Set Theory to Adaptive Regularization
20(1)
Application of Evolutionary Programming to Adaptive Regularization and Blind Deconvolution
21(1)
Overview of This Book
21(2)
Fundamentals of Neural Network Image Restoration
23(18)
Image Distortions
23(3)
Image Restoration
26(3)
Degradation Measure
26(1)
Neural Network Restoration
27(2)
Neural Network Restoration Algorithms in the Literature
29(3)
An Improved Algorithm
32(2)
Analysis
34(2)
Implementation Considerations
36(1)
A Numerical Study of the Algorithms
37(2)
Setup
37(1)
Efficiency
37(1)
An Application Example
38(1)
Summary
39(2)
Spatially Adaptive Image Restoration
41(44)
Introduction
41(2)
Dealing with Spatially Variant Distortion
43(3)
Adaptive Constraint Extension of the Penalty Function Model
46(20)
Motivation
46(2)
The Gradient-Based Method
48(9)
Local Statistics Analysis
57(9)
Correcting Spatially Variant Distortion Using Adaptive Constraints
66(2)
Semi-Blind Restoration Using Adaptive Constraints
68(4)
Implementation Considerations
72(1)
More Numerical Examples
73(3)
Efficiency
73(1)
An Application Example
74(2)
Adaptive Constraint Extension of the Lagrange Model
76(6)
Problem Formulation
76(1)
Problem Solution
77(3)
Conditions for KKT Theory to Hold
80(2)
Discussion
82(1)
Summary
82(3)
Perceptually Motivated Image Restoration
85(26)
Introduction
85(1)
Motivation
86(1)
A LVMSE-Based Cost Function
87(9)
The Extended Algorithm for the LVMSE-Modified Cost Function
88(4)
Analysis
92(4)
A Log LVMSE-Based Cost Function
96(6)
The Extended Algorithm for the Log LVR-Modified Cost Function
97(2)
Analysis
99(3)
Implementation Considerations
102(1)
Numerical Examples
102(7)
Color Image Restoration
102(3)
Grayscale Image Restoration
105(1)
LSMSE of Different Algorithms
105(1)
Robustness Evaluation
105(4)
Summary
109(2)
Model-Based Adaptive Image Restoration
111(44)
Model-Based Neural Network
111(2)
Weight-Parameterized Model-Based Neuron
112(1)
Hierarchical Neural Network Architecture
113(2)
Model-Based Neural Network with Hierarchical Architecture
115(1)
HMBNN for Adaptive Image Processing
115(1)
The Hopfield Neural Network Model for Image Restoration
116(1)
Adaptive Regularization: An Alternative Formulation
116(6)
Correspondence with the General HMBNN Architecture
118(4)
Regional Training Set Definition
122(2)
Determination of the Image Partition
124(2)
The Edge-Texture Characterization Measure
126(4)
The ETC Fuzzy HMBNN for Adaptive Regularization
130(1)
Theory of Fuzzy Sets
131(2)
Edge-Texture Fuzzy Model Based on ETC Measure
133(2)
Architecture of the Fuzzy HMBNN
135(2)
Correspondence with the General HMBNN Architecture
137(1)
Estimation of the Desired Network Output
137(1)
Fuzzy Prediction of Desired Gray Level Value
138(7)
Definition of the Fuzzy Estimator Membership Function
139(1)
Fuzzy Inference Procedure for Predicted Gray Level Value
140(1)
Defuzzification of the Fuzzy Set G
141(1)
Regularization Parameter Update
142(2)
Update of the Estimator Fuzzy Set Width Parameters
144(1)
Experimental Results
145(9)
Summary
154(1)
Adaptive Regularization Using Evolutionary Computation
155(28)
Introduction
155(1)
Introduction to Evolutionary Computation
156(4)
Genetic Algorithm
156(1)
Evolutionary Strategy
157(1)
Evolutionary Programming
158(2)
The ETC-pdf Image Model
160(4)
Adaptive Regularization Using Evolutionary Programming
164(8)
Competition under Approximate Fitness Criterion
168(1)
Choice of Optimal Regularization Strategy
169(3)
Experimental Results
172(7)
Other Evolutionary Approaches for Image Restoration
179(1)
Hierarchical Cluster Model
179(1)
Image Segmentation and Cluster Formation
180(1)
Evolutionary Strategy Optimization
180(1)
Summary
180(3)
Blind Image Deconvolution
183(46)
Introduction
183(3)
Computational Reinforced Learning
185(1)
Blur Identification by Recursive Soft Decision
185(1)
Computational Reinforced Learning
186(17)
Formulation of Blind Image Deconvolution as an Evolutionary Strategy
186(7)
Knowledge-Based Reinforced Mutation
193(4)
Perception-Based Image Restoration
197(2)
Recombination Based on Niche-Space Residency
199(2)
Performance Evaluation and Selection
201(2)
Soft-Decision Method
203(13)
Recursive Subspace Optimization
203(1)
Hierarchical Neural Network for Image Restoration
204(6)
Soft Parametric Blur Estimator
210(1)
Blur Identification by Conjugate Gradient Optimization
211(3)
Blur Compensation
214(2)
Simulation Examples
216(9)
Identification of 2D Gaussian Blur
217(2)
Identification of 2D Gaussian Blur from Degraded Image with Additive Noise
219(1)
Identification of 2D Uniform Blur by CRL
220(5)
Identification of Non-standard Blur by RSD
225(1)
Conclusions
225(4)
Edge Detection Using Model-Based Neural Networks
229(24)
Introduction
229(1)
MBNN Model for Edge Characterization
230(4)
Input-Parameterized Model-Based Neuron
230(2)
Determination of Sub-Network Output
232(1)
Edge Characterization and Detection
232(2)
Network Architecture
234(6)
Characterization of Edge Information
236(1)
Sub-Network Ur
236(1)
Neuron Vrs in Sub-Network Ur
236(1)
Dynamic Tracking Neuron Vd
237(1)
Binary Edge Configuration
238(1)
Correspondence with the General HMBNN Architecture
239(1)
Training Stage
240(1)
Determination of pr* for Sub-Network Ur*
240(1)
Determination of wr*s&ast for Neuron Vr&asts&ast
241(1)
Acquisition of Valid Edge Configurations
241(1)
Recognition Stage
241(2)
Identification of Primary Edge Points
242(1)
Identification of Secondary Edge Points
242(1)
Experimental Results
243(4)
Summary
247(6)
References 253(12)
Index 265

An electronic version of this book is available through VitalSource.

This book is viewable on PC, Mac, iPhone, iPad, iPod Touch, and most smartphones.

By purchasing, you will be able to view this book online, as well as download it, for the chosen number of days.

Digital License

You are licensing a digital product for a set duration. Durations are set forth in the product description, with "Lifetime" typically meaning five (5) years of online access and permanent download to a supported device. All licenses are non-transferable.

More details can be found here.

A downloadable version of this book is available through the eCampus Reader or compatible Adobe readers.

Applications are available on iOS, Android, PC, Mac, and Windows Mobile platforms.

Please view the compatibility matrix prior to purchase.