Adaptive Image Processing: A Computational Intelligence Perspective, Second Edition

Note: Supplemental materials are not guaranteed with Rental or Used book purchases.

ISBN: 9781420084351 | 1420084356
Cover: Hardcover
Copyright: 12/23/2009

Rent

(Recommended)

$154.12

Term

Due

Price

Semester

Dec 12

$162.23

Quarter

Aug 13

$154.12

Short Term

Jul 20

$146.00

*This item is part of an exclusive publisher rental program and requires an additional convenience fee. This fee will be reflected in the shopping bag.
Buy New

Usually Ships in 3-5 Business Days

$207.69
eBook

Available Instantly

Online: 180 Days

Downloadable: 180 Days

*To support the delivery of the digital material to you, a digital delivery fee of $3.99 will be charged on each digital item.

$158.40*

Illustrating essential aspects of adaptive image processing from a computational intelligence viewpoint, the second edition of Adaptive Image Processing: A Computational Intelligence Perspective provides an authoritative and detailed account of computational intelligence (CI) methods and algorithms for adaptive image processing in regularization, edge detection, and early vision.With three new chapters and updated information throughout, the new edition of this popular reference includes substantial new material that focuses on applications of advanced CI techniques in image processing applications. It introduces new concepts and frameworks that demonstrate how neural networks, support vector machines, fuzzy logic, and evolutionary algorithms can be used to address new challenges in image processing, including low-level image processing, visual content analysis, feature extraction, and pattern recognition.New to the Second Edition:A new chapter on a family of unsupervised algorithms with a basis in self-organization yet somewhat free from many of the constraints typical of other well-known self-organizing architecturesNew material on recent challenges in image content analysis and classification, including small sample problems and fuzzy user perceptionA new technique in visual query processing and visualization in 2D spaceNew experiments and updates on perceptual error-based restorationEmphasizing developments in state-of-the-art CI techniques, such as content-based image retrieval, this book continues to provide educators, students, researchers, engineers, and technical managers in visual information processing with the up-to-date understanding required to address contemporary challenges in image content processing and analysis.

Preface	p. xiii
Introduction	p. 1
Importance of Vision	p. 1
Adaptive Image Processing	p. 2
Three Main Image Feature Classes	p. 3
Smooth Regions	p. 3
Edges	p. 4
Textures	p. 4
Difficulties in Adaptive Image-Processing System Design	p. 5
Segmentation	p. 7
Characterization	p. 7
Optimization	p. 7
Computational Intelligence Techniques	p. 8
Neural Networks	p. 10
Fuzzy Logic	p. 11
Evolutionary Computation	p. 12
Scope of the Book	p. 13
Image Restoration	p. 13
Edge Characterization and Detection	p. 15
Self-Organizing Tree Map for Knowledge Discovery	p. 16
Content-Based Image Categorization and Retrieval	p. 18
Contributions of the Current Work	p. 19
Application of Neural Networks for Image Restoration	p. 19
Application of Neural Networks to Edge Characterization	p. 20
Application of Fuzzy Set Theory to Adaptive Regularization	p. 20
Application of Evolutionary Programming to Adaptive Regularization and Blind Deconvolution	p. 21
Application of Self-Organization to Image Analysis and Retrieval	p. 21
Application of Evolutionary Computation to Image Categorization	p. 22
Application of Computational Intelligence to Content-Based Image Retrieval	p. 22
Overview of This Book	p. 23
Fundamentals of CI-Inspired Adaptive Image Restoration	p. 25
Neural Networks as a CI Architecture	p. 25
Image Distortions	p. 25
Image Restoration	p. 29
Constrained Least Square Error	p. 29
A Bayesian Perspective	p. 30
A Lagrangian Perspective	p. 32
Neural Network Restoration	p. 35
Neural Network Restoration Algorithms in the Literature	p. 37
An Improved Algorithm	p. 40
Analysis	p. 43
Implementation Considerations	p. 45
Numerical Study of the Algorithms	p. 45
Setup	p. 45
Efficiency	p. 46
Summary	p. 46
Spatially Adaptive Image Restoration	p. 49
Introduction	p. 49
Dealing with Spatially Variant Distortion	p. 51
Adaptive Constraint Extension of the Penalty Function Model	p. 53
Motivation	p. 54
Gradient-Based Method	p. 56
Local Statistics Analysis	p. 64
Correcting Spatially Variant Distortion Using Adaptive Constraints	p. 69
Semiblind Restoration Using Adaptive Constraints	p. 74
Implementation Considerations	p. 78
More Numerical Examples	p. 79
Efficiency	p. 79
Application Example	p. 80
Adaptive Constraint Extension of the Lagrange Model	p. 80
Problem Formulation	p. 80
Problem Solution	p. 83
Conditions for KKT Theory to Hold	p. 85
Discussion	p. 87
Summary	p. 88
Perceptually Motivated Image Restoration	p. 89
Introduction	p. 89
Motivation	p. 90
LVMSE-Based Cost Function	p. 91
Extended Algorithm for the LVMSE-Modified Cost Function	p. 92
Analysis	p. 96
Log LVMSE-Based Cost Function	p. 100
Extended Algorithm for the Log LVR-Modified Cost Function	p. 101
Analysis	p. 103
Implementation Considerations	p. 105
Numerical Examples	p. 106
Color Image Restoration	p. 106
Grayscale Image Restoration	p. 109
LSMSE of Different Algorithms	p. 109
Robustness Evaluation	p. 111
Subjective Survey	p. 113
Local Variance Extension of the Lagrange Model	p. 114
Problem Formulation	p. 114
Computing Local Variance	p. 116
Problem Solution	p. 117
Conditions for KKT Theory to Hold	p. 118
Implementation Considerations for the Lagrangian Approach	p. 120
Numerical Experiment	p. 121
Summary	p. 122
Acknowledgments	p. 122
Model-Based Adaptive Image Restoration	p. 123
Model-Based Neural Network	p. 123
Weight-Parameterized Model-Based Neuron	p. 124
Hierarchical Neural Network Architecture	p. 125
Model-Based Neural Network with Hierarchical Architecture	p. 125
HMBNN for Adaptive Image Processing	p. 126
Hopfield Neural Network Model for Image Restoration	p. 127
Adaptive Regularization: An Alternative Formulation	p. 128
Correspondence with the General HMBNN Architecture	p. 130
Regional Training Set Definition	p. 134
Determination of the Image Partition	p. 137
Edge-Texture Characterization Measure	p. 139
ETC Fuzzy HMBNN for Adaptive Regularization	p. 142
Theory of Fuzzy Sets	p. 143
Edge-Texture Fuzzy Model Based on ETC Measure	p. 145
Architecture of the Fuzzy HMBNN	p. 147
Correspondence with the General HMBNN Architecture	p. 148
Estimation of the Desired Network Output	p. 149
Fuzzy Prediction of Desired Gray-Level Value	p. 151
Definition of the Fuzzy Estimator Membership Function	p. 151
Fuzzy Inference Procedure for Predicted Gray-Level Value	p. 152
Defuzzification of the Fuzzy Set G	p. 153
Regularization Parameter Update	p. 155
Update of the Estimator Fuzzy Set Width Parameters	p. 156
Experimental Results	p. 158
Summary	p. 166
Adaptive Regularization Using Evolutionary Computation	p. 169
Introduction	p. 169
Introduction to Evolutionary Computation	p. 170
Genetic Algorithm	p. 170
Evolutionary Strategy	p. 171
Evolutionary Programming	p. 172
ETC-pdf Image Model	p. 174
Adaptive Regularization Using Evolutionary Programming	p. 178
Competition under Approximate Fitness Criterion	p. 181
Choice of Optimal Regularization Strategy	p. 183
Experimental Results	p. 185
Other Evolutionary Approaches for Image Restoration	p. 190
Hierarchical Cluster Model	p. 192
Image Segmentation and Cluster Formation	p. 192
Evolutionary Strategy Optimization	p. 192
Summary	p. 193
Blind Image Deconvolution	p. 195
Introduction	p. 195
Computational Reinforced Learning	p. 197
Blur Identification by Recursive Soft Decision	p. 198
Computational Reinforced Learning	p. 198
Formulation of Blind Image Deconvolution as an Evolutionary Strategy	p. 198
Knowledge-Based Reinforced Mutation	p. 205
Perception-Based Image Restoration	p. 210
Recombination Based on Niche-Space Residency	p. 212
Performance Evaluation and Selection	p. 213
Soft-Decision Method	p. 215
Recursive Subspace Optimization	p. 215
Hierarchical Neural Network for Image Restoration	p. 217
Soft Parametric Blur Estimator	p. 222
Blur Identification by Conjugate Gradient Optimization	p. 223
Blur Compensation	p. 226
Simulation Examples	p. 229
Identification of 2-D Gaussian Blur	p. 230
Identification of 2-D Gaussian Blur from Degraded Image with Additive Noise	p. 231
Identification of 2-D Uniform Blur by CRL	p. 232
Identification of Nonstandard Blur by RSD	p. 235
Conclusions	p. 238
Edge Detection Using Model-Based Neural Networks	p. 239
Introduction	p. 239
MBNN Model for Edge Characterization	p. 240
Input-Parameterized Model-Based Neuron	p. 240
Determination of Subnetwork Output	p. 242
Edge Characterization and-Defection	p. 242
Network Architecture	p. 244
Characterization of Edge Information	p. 245
Subnetwork U_r	p. 245
Neuron V_rs in Subnetwork U_r	p. 246
Dynamic Tracking Neuron V_d	p. 246
Binary Edge Configuration	p. 247
Correspondence with the General HMBNN Architecture	p. 248
Training Stage	p. 249
Determination of p_r* for Subnetwork U_r*	p. 249
Determination of W_rs for Neuron V_rs	p. 250
Acquisition of Valid Edge Configurations	p. 250
Recognition Stage	p. 251
Identification of Primary Edge Points	p. 251
Identification of Secondary Edge Points	p. 251
Experimental Results	p. 252
Summary	p. 260
Image Analysis and Retrieval via Self-Organization	p. 261
Introduction	p. 261
Self-Organizing Map (SOM)	p. 261
Self-Organizing Tree Map (SOTM)	p. 263
SOTM Model: Architecture	p. 263
Competitive Learning Algorithm	p. 264
Dynamic Topology and Classification Capability of the SOTM	p. 267
Summary	p. 268
SOTM in Impulse Noise Removal	p. 269
Introduction	p. 269
Models of Impulse Noise	p. 272
Noise-Exclusive Adaptive Filtering	p. 274
Experimental Results	p. 279
SOTM in Content-Based Retrieval	p. 286
Architecture of the AI-CBR System with Compressed Domain Processing	p. 287
Automatic Interaction by the SOTM	p. 289
Features Extraction for Retrieval	p. 291
Features for Relevance Classification	p. 292
Retrieval of Texture Images in Compressed Domain	p. 292
Genetic Optimization of Feature Representation for Compressed-Domain Image Categorization	p. 299
Introduction	p. 299
Compressed-Domain Representation	p. 301
Problem Formulation	p. 302
Multiple-Classifier Approach	p. 305
Experimental Results	p. 307
Conclusion	p. 312
Content-Based Image Retrieval Using Computational Intelligence Techniques	p. 313
Introduction	p. 313
Problem Description and Formulation	p. 315
Soft Relevance Feedback in CBIR	p. 317
Overview and Structure of RFRBFN	p. 317
Network Training	p. 320
Experimental Results	p. 324
Predictive-Label Fuzzy Support Vector Machine for Small Sample Problem	p. 329
Overview of PLFSVM	p. 330
Training of PLFSVM	p. 331
Experimental Results	p. 335
Conclusion	p. 338
References	p. 339
Index	p. 353
Table of Contents provided by Ingram. All Rights Reserved.

Please wait while the item is added to your bag...

FREE SHIPPING

Rent More, Save More! Use code: BBRENTAL

5% off 1 book, 7% off 2 books, 10% off 3+ books

Adaptive Image Processing: A Computational Intelligence Perspective, Second Edition

Summary

Table of Contents

Supplemental Materials

FREE SHIPPING

Rent More, Save More! Use code: BBRENTAL

5% off 1 book, 7% off 2 books, 10% off 3+ books

Adaptive Image Processing: A Computational Intelligence Perspective, Second Edition

Summary

Table of Contents

Supplemental Materials

Digital License