文档介绍：Knowledge-Based Intelligent Techniques in Character Recognition:Table of Contents
Preface
Chapter 1—An Introduction to Handwritten Character and Word Recognition
1 Introduction
2 Knowledge-Based Intelligent Techniques
3 Off-Line Handwriting Recognition
Preprocessing
Segmentation
Recognition
Analytical Methods
Holistic Methods
Recognition-Based Methods
Character Recognition
4 On-Line Handwriting Recognition
5 Some Considerations about Performance Evaluation
6 Summary
Chapter 2—Recognition of Handwritten Digits in the Real World by a
Neocognitron
1. Introduction
2. Neocognitron
S-cell Layer
C-cell Layer
work Architecture of Lower Stages
3. Unsupervised Learning of Feature-Extracting Cells
4. Threshold of S-cells
Mathematical Notation of an S-cell
Relationship Between Threshold and Selectivity of an S-cell
Calculation of Inhibitory Variable Connection
with High Thresholds for S-cells
with a Lower Threshold
5. Different Thresholds in Learning and Recognition
Threshold in Learning Phase
Upper Bound of the Threshold
6. The Highest Stage; Classification Layer
7. Results
Optimization of Thresholds and Recognition Rate
file:///F|/htdocs/ICE/temp/20030703/knowledge-based-intelligent-techniques-in-character-recognition/ (1 of 5)2003-11-8 10:36:17
Knowledge-Based Intelligent Techniques in Character Recognition:Table of Contents
8. Summary
Chapter 3—Recognition of Rotated Patterns Using a Neocognitron
1 Introduction
2 Rotation-Invariant Neocognitron
Short Review of Neocognitron
Structure of Rotation-Invariant Neocognitron
Unsupervised Learning and Detection of Rotated Patterns
Robustness for Rotations
3 Simulation
4 Summary
Chapter 4—A puting Approach to Handwritten Numeral Recognition
1. Introduction
2. Description of Data an