Introduction
Importance of Vision
Adaptive Image Processing
Three Main Image Feature Classes
Difficulties in Adaptive Image-Processing System Design
Computational Intelligence Techniques
Scope of the Book
Contributions of the Current Work
Overview of This Book
Fundamentals of CI-Inspired Adaptive Image Restoration
Image Distortions
Image Restoration
Constrained Least Square Error
Neural Network Restoration
Neural Network Restoration Algorithms in the Literature
An Improved Algorithm
Analysis
Implementation Considerations
Numerical Study of the Algorithms
Summary
Spatially Adaptive Image Restoration
Dealing with Spatially Variant Distortion
Adaptive Constraint Extension of the Penalty Function Model
Correcting Spatially Variant Distortion Using Adaptive Constraints
Semiblind Restoration Using Adaptive Constraints
Implementation Considerations
More Numerical Examples
Numerical Examples
Local Variance Extension of the Lagrange Model
Summary
Acknowledgments
Regional Training Set Definition
Determination of the Image Partition
Edge-Texture Characterization Measure
ETC Fuzzy HMBNN for Adaptive Regularization
Theory of Fuzzy Sets
Edge-Texture Fuzzy Model Based on ETC Measure
Architecture of the Fuzzy HMBNN
Estimation of the Desired Network Output
Fuzzy Prediction of Desired Gray-Level Value
Experimental Results
Summary
Adaptive Regularization Using Evolutionary Computation
Introduction to Evolutionary Computation
ETC-pdf Image Model
Adaptive Regularization Using Evolutionary Programming
Experimental Results
Other Evolutionary Approaches for Image Restoration
Summary
Blind Image Deconvolution
Computational Reinforced Learning
Soft-Decision Method
Simulation Examples
Conclusions
Edge Detection Using Model-Based Neural Networks
MBNN Model for Edge Characterization
Network Architecture
Training Stage
Recognition Stage
Experimental Results
Summary
Image Analysis and Retrieval via Self-Organization
Self-Organizing Map (SOM)
Self-Organizing Tree Map (SOTM)
SOTM in Impulse Noise Removal
SOTM in Content-Based Retrieval
Genetic Optimization of Feature Representation for Compressed-Domain Image Categorization
Compressed-Domain Representation
Problem Formulation
Multiple-Classifier Approach
Experimental Results
Conclusion
Content-Based Image Retrieval Using Computational Intelligence Techniques
Problem Description and Formulation
Soft Relevance Feedback in CBIR
Predictive-Label Fuzzy Support Vector Machine for Small Sample Problem
Conclusion