Roberto Brunelli, Senior Researcher, ITC-irst, Italy
Roberto Brunelli is currently working for ITC-irst for the Technologies of Vision Research Line of Interactive Sensory Systems Division. He has held this post since 1987 after gaining his degree in Physics from the University of Trento (Italy). His research activities and interests are in the areas of computer vision tools, analysis of aerial images, the development of algorithms for the compressed description of binary images, optimization, neural networks, face analysis, video analysis and image retrieval. Dr Brunelli's research projects have been implemented in several EU funded projects, and he has also undertaken teaching assignments at the International Doctorate School of the University of Trento. He has written over 30 published journal and conference papers, several of which deal with computational face perception. The paper 'Template Matching: Matched Spatial Filters and Beyond' received a Pattern Recognition Society Award in 1998. He has acted as a referee for some of the major journals on image processing and related techniques, for example Computer Vision and Image Understanding and IEEE Transactions on Image Processing, and has also been on the Technical Committee for several conferences, including Audio- and Video-Based Biometric Person Authentication, IEEE Conference on Computer Vision and Pattern Recognition and European Conference on Computer Vision.

The detection and recognition of objects in images is a key research topic in the computer vision community. Within this area, face recognition and interpretation has attracted increasing attention owing to the possibility of unveiling human perception mechanisms, and for the development of practical biometric systems. This book and the accompanying website, focus on template matching, a subset of object recognition techniques of wide applicability, which has proved to be particularly effective for face recognition applications. Using examples from face processing tasks throughout the book to illustrate more general object recognition approaches, Roberto Brunelli:
* examines the basics of digital image formation, highlighting points critical to the task of template matching;
* presents basic and advanced template matching techniques, targeting grey-level images, shapes and point sets;
* discusses recent pattern classification paradigms from a template matching perspective;
* illustrates the development of a real face recognition system;
* explores the use of advanced computer graphics techniques in the development of computer vision algorithms.
Template Matching Techniques in Computer Vision is primarily aimed at practitioners working on the development of systems for effective object recognition such as biometrics, robot navigation, multimedia retrieval and landmark detection. It is also of interest to graduate students undertaking studies in these areas.

Preface.
1 Introduction.
1.1 Template Matching and Computer Vision.
1.2 The Book.
1.3 Bibliographical Remarks.
References.
2 The Imaging Process.
2.1 Image Creation.
2.1.1 Light.
2.1.2 Gathering Light.
2.1.3 Diffraction-limited Systems.
2.1.4 Quantum Noise.
2.2 Biological Eyes.
2.2.1 The Human Eye.
2.2.2 Alternative Designs.
2.3 Digital Eyes.
2.4 Digital Image Representations.
2.4.1 TheSampling Theorem.
2.4.2 Image Resampling.
2.4.3 Log-polar Mapping.
2.5 Bibliographical Remarks.
References.
3 Template Matching as Testing.
3.1 Detectionand Estimation.
3.2 Hypothesis Testing.
3.2.1 The Bayes RiskCriterion.
3.2.2 The Neyman-Pearson Criterion.
3.3 An Important Example.
3.4 A Signal Processing Perspective: Matched Filters.
3.5 Pattern Variability and the Normalized Correlation Coefficient.
3.6 Estimation.
3.6.1 Maximum Likelihood Estimation.
3.6.2 Bayes Estimation.
3.6.3 James-Stein Estimation.
3.7 Bibliographical Remarks.
References.
4 Robust Similarity Estimators.
4.1 Robustness Measures.
4.2 M-estimators.
4.3 L1 Similarity Measures.
4.4 Robust Estimation of Covariance Matrices.
4.5 Bibliographical Remarks.
References.
5 Ordinal Matching Measures.
5.1 Ordinal Correlation Measures.
5.1.1 Spearman Rank Correlation.
5.1.2 Kendall Correlation.
5.1.3 Bhat-Nayar Correlation.
5.2 Non-parametric Local Transforms.
5.2.1 The Census and Rank Transforms.
5.2.2 Incremental Sign Correlation.
5.3 Bibliographical Remarks.
References.
6 Matching Variable Patterns.
6.1 Multiclass Synthetic Discriminant Functions.
6.2 Advanced Synthetic Discriminant Functions.
6.3 Non-orthogonal Image Expansion.
6.4 Bibliographical Remarks.
References.
7 Matching Linear Structure: The Hough Transform.
7.1 Getting Shapes: Edge Detection.
7.2 The Radon Transform.
7.3 The Hough Transform: Line and Circle Detection.
7.4 The Generalized Hough Transform.
7.5 Bibliographical Remarks.
References.
8 Low-dimensionality Representations and Matching.
8.1 Principal Components.
8.1.1 Probabilistic PCA.
8.1.2 How Many Components?
8.2 ANonlinear Approach: Kernel PCA.
8.3 Independent Components.
8.4 Linear Discriminant Analysis.
8.4.1 Bayesian Dual Spaces.
8.5 A Sample Application: Photographic-quality Facial Composites.
8.6 Bibliographical Remarks.
References.
9 Deformable Templates.
9.1 A Dynamic Perspective on the Hough Transform.
9.2 Deformable Templates.
9.3 Active Shape Models.
9.4 DiffeomorphicMatching.
9.5 Bibliographical Remarks.
References.
10 Computational Aspects of Template Matching.
10.1 Speed.
10.1.1 Early Jump-out.
10.1.2 TheUse of SumTables.
10.1.3 Hierarchical Template Matching.
10.1.4 Metric Inequalities.
10.1.5 The FFT Advantage.
10.1.6 PCA-basedSpeed-up.
10.1.7 A Combined Approach.
10.2 Precision.
10.2.1 A Perturbative Approach.
10.2.2 Phase Correlation.
10.3 Bibliographical Remarks.
References.
11 Matching Point Sets: The Hausdorff Distance.
11.1 Metric Pattern Spaces.
11.2 Hausdorff Matching.
11.3 Efficient Computation of the Hausdorff Distance.
11.4 Partial Hausdorff Matching.
11.5 Robustness Aspects.
11.6 A Probabilistic Perspective.
11.7 Invariant Moments.
11.8 Bibliographical Remarks.
References.
12 Support Vector Machines and Regularization Networks.
12.1 Learning and Regularization.
12.2 RBF Networks.
12.2.1 RBF Networks for Gender Recognition.
12.3 Support Vector Machines.
12.3.1 Improving Efficiency.
12.3.2 Multiclass SVMs.
12.3.3 Best Practice.
12.4 Bibliographical Remarks.
References.
13 Feature Templates.
13.1 Detecting Templates by Features.
13.2 Parametric FeatureManifolds.
13.3 Multiclass Pattern Rejection.
13.4 Template Features.
13.5 Bibliographical Remarks.
References.
14 Building a Multibiometric System.
14.1 Systems.
14.2 The Electronic Librarian.
14.3 Score Integration.
14.4 Rejection.
14.5 Bibliographical Remarks.
References.
Appendices.
A AnImAl: A Software Environment for Fast Prototyping.
A.1 AnImAl: An Image Algebra.
A.2 Image Representationand Processing Abstractions.
A.3 The AnImAl Environment.
A.4 Bibliographical Remarks.
References.
B Synthetic Oracles for Algorithm Development.
B.1 Computer Graphics.
B.2 Describing Reality: Flexible Rendering Languages.
B.3 Bibliographical Remarks.
References.
C On Evaluation.
C.1 A Note on Performance Evaluation.
C.2 Traininga Classifier.
C.3 Analyzing the Performance of a Classifier.
C.4 Evaluating a Technology.
C.5 Bibliographical Remarks.
References.
Index.