
Résumé
Kulkarni starts by reviewing the fundamentals of computer vision, and the stages of a computer vision system. He shows how these stages have traditionally been implemented via statistical techniques; then introduces approaches that incorporate neural networks, fuzzy inference systems, and fuzzy-neural network models. Kulkarni introduces pre-processing techniques such as radiometric or geometric corrections; feature extraction; supervised and unsupervised classification; associative memories; and other key techniques for improving the accuracy and performance of computer vision systems. Finally, the book includes thorough coverage of key computer vision applications, including remote sensing, medical image processing, data compression, data mining, character recognition, and stereovision. The accompanying CD-ROM contains an extensive library of MATLAB command files, test images from Kodak and Space Imaging, and more.
For engineers, scientists, programmers, and other professionals working in computer vision, remote sensing, character recognition, data compression, medical and law enforcement applications, and related fields.
Features:
- CD-ROM-Includes some test images from Kodak and
Space Imaging, MATLAB command files for some illustrative
examples, and a display program.
- Makes the text suitable for hands-on experience and self-study.
- Detailed tutorials, hands-on exercises, real-world
examples, and proven algorithms.
- Makes this book the first complete guide to applying fuzzy-neural systems in computer vision.
- New computer vision techniques-Based on neural
networks, fuzzy inference systems, and fuzzy-neural network
models.
- Goes beyond traditional implementation of computer vision via statistical techniques.
- Preface
- 1: Introduction
- Introduction
- Computer Vision
- Neural Network Models
- Fuzzy Logic Techniques
- Fuzzy Neural Systems
- Summary
- Outline
- References
- Exercises
- 2: Computer Vision Fundamentals
- Introduction
- Human Vision System
- Perception
- Input-Output Devices
- Camera Models
- Sampling And Quantization
- Preprocessing Techniques
- Image Transforms
- Feature Extraction And Recognition
- Summary
- References
- Exercises
- 3: Fuzzy Logic Fundamentals
- Introduction
- Fuzzy Sets And Membership Functions
- Logical Operations And If-Then Rules
- Fuzzy Inference System
- Defuzzification
- Fuzzy Set Representation With A Cube
- Hedges
- Fuzzy Systems As Function Approximators
- Extraction Of Rules From Sample Data Points
- Fuzzy Basis Functions
- Design And Implementation Of A Fuzzy Inference System
- Summary
- References
- Exercises
- 4: Neural Network Fundamentals
- Introduction
- Neuron Representation
- Perception
- Linear Networks
- Single-Layer Networks With Nonlinear Transfer Functions
- Backpropagation
- Kohonen Feature Maps
- Competitive Learning
- Hopfield Networks
- Counterpropagation Network
- Summary
- References
- Exercises
- 5: Preprocessing
- Introduction
- Gray-Level Histogram
- Point Operations
- Filtering Techniques
- Noise Removal Techniques
- Mathematical Morphology
- Edge Detection Techniques
- Neural Network Models For Brightness Perception And Boundary Detection
- Image Restoration
- Geometric Corrections And Registration
- Interpolation
- Summary
- References
- Exercises
- 6: Feature Extraction
- Introduction
- Segmentation And Shape Descriptors
- Moment Invariants
- Feature Extraction Using Orthogonal Transforms
- Neural Network Models For Ft Domain Feature Extraction
- Neural Network Model For Wht Domain Feature Extraction
- Invariant Feature Extraction Using Adaline
- Texture Features
- Neural Network Models For Texture Analysis
- Summary
- References
- Exercises
- 7: Supervised Classifiers
- Introduction
- Discriminant Functions
- Minimum Distance Classifiers
- Bayes Classifier
- Tree Classifiers
- Neural Network Models For Classification
- Fuzzy Neural Network Models
- Summary
- References
- Exercises
- 8: Unsupervised Classifiers
- Introduction
- Conventional Clustering Techniques
- Self-Organizing Networks
- Fuzzy C-Means Clustering
- Fuzzy Neural Network Models For Clustering
- Summary
- References
- Exercises
- 9: Associative Memories
- Introduction
- Discrete Autocorrelator
- Discrete Bidirectional Associative Memory
- Bidirectional Associative Memories With Multiple Input-Output Patterns
- Optimal Associative Memory
- Selective Reflex Memory
- Temporal Associative Memory
- Counterpropagation Networks As Associative Memory
- Fuzzy Associative Memory
- Computer Vision Applications
- Summary
- References
- Exercises
- 10: Applications
- Introduction
- Remote Sensing
- Medical Image Processing
- Image Data Compression
- Data Mining And Computer Vision
- Biometric Applications
- Character Recognition
- Knowledge-Based Pattern Recognition
- Stereo Vision
- Summary
- References
- Exercises
- Index
- About The Author
- About The CD-ROM
Caractéristiques techniques
PAPIER | |
Éditeur(s) | Prentice Hall |
Auteur(s) | Arun D. Kulkarni |
Parution | 01/06/2001 |
Nb. de pages | 509 |
Format | 18 x 24 |
Couverture | Relié |
Poids | 1012g |
Intérieur | Noir et Blanc |
EAN13 | 9780135705995 |
Avantages Eyrolles.com
Consultez aussi
- Les meilleures ventes en Graphisme & Photo
- Les meilleures ventes en Informatique
- Les meilleures ventes en Construction
- Les meilleures ventes en Entreprise & Droit
- Les meilleures ventes en Sciences
- Les meilleures ventes en Littérature
- Les meilleures ventes en Arts & Loisirs
- Les meilleures ventes en Vie pratique
- Les meilleures ventes en Voyage et Tourisme
- Les meilleures ventes en BD et Jeunesse