Fondazione Bruno Kessler - Technologies of Vision

contains material from
Template Matching Techniques in Computer Vision: Theory and Practice
Roberto Brunelli 2009 John Wiley & Sons, Ltd


1 Introduction
 1.1 The software environment
 1.2 Basic template matching
2 The Imaging Process
 2.1 Image distortions
 2.2 Diffraction Effects
 2.3 Noise
 2.4 Digital imaging artifacts
  2.4.1 Demosaicing
  2.4.2 Interlacing
 2.5 Image resampling
 2.6 Log-polar imaging
3 Template Matching as Testing
 3.1 The ROC curve
 3.2 The normalized correlation coefficient
 3.3 Stein estimation
4 Robust Similarity Estimators
 4.1 Validity of distributional hypotheses
 4.2 Tanh estimators
 4.3 L1 similarity measures
5 Ordinal Matching Measures
 5.1 Histogram equalization
 5.2 Ordinal Correlation Measures
 5.3 Bhat-Nayar correlation
 5.4 Non Parametric Local Transforms
6 Matching Variable Patterns
 6.1 Maximizing SNR over class samples
 6.2 Multi-class Synthetic Discriminant Functions
7 Matching Linear Structure: the Hough Transform
 7.1 Edge detection
 7.2 The Hough Transform
8 Low Dimensionality Representations and Matching
 8.1 Principal component analysis
 8.2 James-Stein estimation
9 Deformable Templates
10 Computational Aspects of Template Matching
 10.1 Hierarchical matching
11 Matching Points Sets: the Hausdorff distance
 11.1 Hausdorff matching
12 Support Vector Machines And Friends
13 Feature Templates
14 Building a Multi-biometric System
A AnImAl: a Software Environment for Fast Prototyping
 A.1 The AnImAl environment
B Synthetic Oracles for Algorithm Development
 B.1 Thematic maps
 B.2 Color rendering
C On Evaluation
D Template Matching Literature