Optimisation in Signal and Image Processing

Informationen zum Autor Patrick Siarry is a Professor of Automatics and Informatics at the University of Paris-Est Créteil, where he leads the Image and Signal Processing team in the Laboratoire Images, Signaux et Systèmes Intelligents - LiSSi. Klappentext "First published in France in 2007 by Hermes Science/Lavoisier entitled: Optimisation en traitement du signal et de l'image"--T.p. verso. Zusammenfassung Describes the optimization methods commonly encountered in signal and image processing: artificial evolution and Parisian approach; wavelets and fractals; information criteria; training and quadratic programming; Bayesian formalism; probabilistic modeling; Markovian approach; hidden Markov models; and! metaheuristics. Inhaltsverzeichnis 8267197

List of contents

Introduction xiii Chapter 1. Modeling and Optimization in Image Analysis 1
Jean Louchet
1.1. Modeling at the source of image analysis and synthesis 1
1.2. From image synthesis to analysis 2
1.3. Scene geometric modeling and image synthesis 3
1.4. Direct model inversion and the Hough transform 4
1.5. Optimization and physical modeling 9
1.6. Conclusion 12
1.7. Acknowledgements 13
1.8. Bibliography 13
Chapter 2. Artificial Evolution and the Parisian Approach. Applications in the Processing of Signals and Images 15
Pierre Collet and Jean Louchet
2.1. Introduction 15
2.2. The Parisian approach for evolutionary algorithms 15
2.3. Applying the Parisian approach to inverse IFS problems 17
2.4. Results obtained on the inverse problems of IFS 20
2.5. Conclusion on the usage of the Parisian approach for inverse IFS problems 22
2.6. Collective representation: the Parisian approach and the Fly algorithm 23
2.7. Conclusion 40
2.8. Acknowledgements 41
2.9.Bibliography 41
Chapter 3. Wavelets and Fractals for Signal and Image Analysis 45
Abdeldjalil Ouahabi and Djedjiga Ait Aouit
3.1. Introduction 45
3.2. Some general points on fractals 46
3.3. Multifractal analysis of signals 54
3.4. Distribution of singularities based on wavelets 60
3.5. Experiments 70
3.6. Conclusion 76
3.7. Bibliography 76
Chapter 4. Information Criteria: Examples of Applications in Signal and Image Processing 79
Christian Oliver and Olivier Alata
4.1. Introduction and context 79
4.2. Overview of the different criteria 81
4.3. The case of auto-regressive (AR) models 83
4.4. Applying the process to unsupervised clustering 95
4.5. Law approximation with the help of histograms 98
4.6. Other applications 103
4.7. Conclusion 106
4.8. Appendix 106
4.9. Bibliography 107
Chapter 5. Quadratic Programming and Machine Learning - Large Scale Problems and Sparsity 111
Gaé›”le Looslil, Sté–œhane Canu
5.1. Introduction 111
5.2. Learning processes and optimization 112
5.3. From learning methods to quadratic programming 117
5.4. Methods and resolution 119
5.5. Experiments 128
5.6. Conclusion 132
5.7. Bibliography 133
Chapter 6. Probabilistic Modeling of Policies and Application to Optimal Sensor Management 137
Fr閐閞ic Dambreville, Francis Celeste and C閏ile Simonin
6.1. Continuum, a path toward oblivion 137
6.2. The cross-entropy (CE) method 138
6.3. Examples of implementation of CE for surveillance 146
6.4. Example of implementation of CE for exploration 153
6.5. Optimal control under partial observation 158
6.6. Conclusion 166
6.7. Bibliography 166
Chapter 7. Optimizing Emissions for Tracking and Pursuit of Mobile Targets 169
Jean-Pierre Le Cadre
7.1. Introduction 169
7.2. Elementary modeling of the problem (deterministic case) 170
7.3. Application to the optimization of emissions (deterministic case) 175
7.4. The case of a target with a Markov trajectory 181
7.5. Conclusion 189
7.6. Appendix: monotonous functional matrices 189
7.7. Bibliography 192
Chapter 8. Bayesian Inference and Markov Models 195
Christophe Collet
8.1. Introduction and application framework�5
8.2. Detection, segmentation and classification�6
8.3. General modeling�9
8.4. Segmentation using the causal-in-scale Markov model�1
8.5. Segmentation into three classes�3
8.6. The classification of objects�6
8.7. The classification of seabeds�2
8.8. Conclusion and perspectives�4
8.9. Bibliography�5
Chapter 9. The Use of Hidden Markov Models for Image Recognition: Learning with Artificial Ants, Genetic Algorithms and Particle Swarm Optimization�9
S閎astien Aupetit, Nicolas Monmarch� and Mohamed Slimane
9.1. Introduction�9
9.2. Hidden Markov models (HMMs)�0
9.3. Using metaheuristics to learn HMMs�3
9.4. Description, parameter setting and evaluation of the six approaches that are used to train HMMs�6
9.5. Conclusion�0
9.6. Bibliography�0
Chapter 10. Biological Metaheuristics for Road Sign Detection�5
Guillaume Dutilleux and Pierre Charbonnier
10.1. Introduction�5
10.2. Relationship to existing works�6
10.3. Template and deformations�8
10.4. Estimation problem�8
10.5. Three biological metaheuristics�2
10.6. Experimental results�9
10.7. Conclusion�5
10.8. Bibliography�6
Chapter 11. Metaheuristics for Continuous Variables. The Registration of Retinal Angiogram Images�9
Johann Dré‘Ÿ, Jean-Claude Nunes and Patrick Siarry
11.1. Introduction�9
11.2. Metaheuristics for difficult optimization problems�0
11.3. Image registration of retinal angiograms�5
11.4. Optimizing the image registration process�9
11.5. Results�8
11.6. Analysis of the results�5
11.7. Conclusion�6
11.8. Acknowledgements�6
11.9. Bibliography�6
Chapter 12. Joint Estimation of the Dynamics and Shape of Physiological Signals through Genetic Algorithms�1
Amine Na飔-Ali and Patrick Siarry
12.1. Introduction�1
12.2. Brainstem Auditory Evoked Potentials (BAEPs)�2
12.3. Processing BAEPs�3
12.4. Genetic algorithms�5
12.5. BAEP dynamics�7
12.6. The non-stationarity of the shape of the BAEPs�4
12.7. Conclusion�7
12.8. Bibliography�7
Chapter 13. Using Interactive Evolutionary Algorithms to Help Fit Cochlear Implants�9
Pierre Collet, Pierrick Legrand, Claire Bourgeois-Ré–œublique, Vincent P閍n and Bruno Frachet
13.1. Introduction�9
13.2. Choosing an optimization algorithm�3
13.3. Adapting an evolutionary algorithm to the interactive fitting of cochlear implants�5
13.4. Evaluation�8
13.5. Experiments�9
13.6. Medical issues which were raised during the experiments�0
13.7. Algorithmic conclusions for patient A�2
13.8. Conclusion�4
13.9. Bibliography�4
List of Authors�7
Index�9

About the author

Patrick Siarry is a Professor of Automatics and Informatics at the University of Paris-Est Créteil, where he leads the Image and Signal Processing team in the Laboratoire Images, Signaux et Systèmes Intelligents - LiSSi.

Product details

• Authors: SIARRY, P Siarry, Patrick Siarry, Patrick (EDT) Siarry
• Assisted by: Patrick Siarry (Editor)
• Publisher: Wiley, John and Sons Ltd
• Languages: English
• Product format: Hardback
• Released: 18.05.2009
• EAN: 9781848210448
• ISBN: 978-1-84821-044-8
• No. of pages: 361
• Dimensions: 159 mm x 241 mm x 25 mm
• Series: ISTE
• Subject: Natural sciences, medicine, IT, technology > Technology > Electronics, electrical engineering, communications engineering