book

Optimisation in Signal and Image Processing

Name: Optimisation in Signal and Image Processing
Author: Patrick Siarry
ISBN: 9781848210448

by Patrick Siarry

October 2009

Intermediate to advanced

352 pages

10h 7m

English

Wiley

Read now

Unlock full access

Coverpage
Titlepage
Copyright
Table of Contents
Introduction
Chapter 1. Modeling and Optimization in Image Analysis
1.1. Modeling at the source of image analysis and synthesis1.2. From image synthesis to analysis1.3. Scene geometric modeling and image synthesis1.4. Direct model inversion and the Hough transform1.4.1. The deterministic Hough transform1.4.2. Stochastic exploration of parameters: evolutionary Hough1.4.3. Examples of generalization1.5. Optimization and physical modeling1.5.1. Photometric modeling1.5.2. Motion modeling1.6. Conclusion1.7. Acknowledgements1.8. Bibliography
Chapter 2. Artificial Evolution and the Parisian Approach. Applications in the Processing of Signals and Images
2.1. Introduction2.2. The Parisian approach for evolutionary algorithms2.3. Applying the Parisian approach to inverse IFS problems2.3.1. Choosing individuals for the evaluation process2.3.2. Retribution of individuals2.4. Results obtained on the inverse problems of IFS2.5. Conclusion on the usage of the Parisian approach for inverse IFS problems2.6. Collective representation: the Parisian approach and the Fly algorithm2.6.1. The principles2.6.2. Results on real images2.6.3. Application to robotics: fly-based robot planning2.6.4. Sensor fusion2.6.5. Artificial evolution and real time2.6.6. Conclusion about the fly algorithm2.7. Conclusion2.8. Acknowledgements2.9. Bibliography
Chapter 3. Wavelets and Fractals for Signal and Image Analysis
3.1. Introduction3.2. Some general points on fractals3.2.1. Fractals and paradox3.2.2. Fractal sets and self-similarity3.2.3. Fractal dimension3.3. Multifractal analysis of signals3.3.1. Regularity3.3.2. Multifractal spectrum3.4. Distribution of singularities based on wavelets3.4.1. Qualitative approach3.4.2. A rough guide to the world of wavelet3.4.3. Wavelet Transform Modulus Maxima (WTMM) method3.4.4. Spectrum of singularities and wavelets3.4.5. WTMM and some didactic signals3.5. Experiments3.5.1. Fractal analysis of structures in images: applications in microbiology3.5.2. Using WTMM for the classification of textures – application in the field of medical imagery3.6. Conclusion3.7. Bibliography
Chapter 4. Information Criteria: Examples of Applications in Signal and Image Processing
4.1. Introduction and context4.2. Overview of the different criteria4.3. The case of auto-regressive (AR) models4.3.1. Origin, written form and performance of different criteria on simulated examples4.3.2. AR and the segmentation of images: a first approach4.3.3. Extension to 2D AR and application to the modeling of textures4.3.4. AR and the segmentation of images: second approach using 2D AR4.4. Applying the process to unsupervised clustering4.5. Law approximation with the help of histograms4.5.1. Theoretical aspects4.5.2. Two applications used for encoding images4.6. Other applications4.6.1. Estimation of the order of Markov models4.6.2. Data fusion4.7. Conclusion 4.8. Appendix4.8.1. Kullback (-Leibler) information4.8.2. Nishii’s convergence criteria4.9. Bibliography
Chapter 5. Quadratic Programming and Machine Learning – Large Scale Problems and Sparsity
5.1. Introduction5.2. Learning processes and optimization5.2.1. General framework5.2.2. Functional framework5.2.3. Cost and regularization5.2.4. The aims of realistic learning processes5.3. From learning methods to quadratic programming5.3.1. Primal and dual forms5.4. Methods and resolution5.4.1. Properties to be used: sparsity5.4.2. Tools to be used5.4.3. Structures of resolution algorithms5.4.4. Decomposition methods5.4.5. Solving quadratic problems5.4.6. Online and non-optimized methods5.4.7. Comparisons5.5. Experiments5.5.1. Comparison of empirical complexity 5.5.2. Very large databases5.6. Conclusion5.7. Bibliography

Chapter 6. Probabilistic Modeling of Policies and Application to Optimal Sensor Management
6.1. Continuum, a path toward oblivion6.2. The cross-entropy (CE) method6.2.1. Probability of rare events6.2.2. CE applied to optimization6.3. Examples of implementation of CE for surveillance6.3.1. Introducing the problem6.3.2. Optimizing the distribution of resources6.3.3. Allocating sensors to zones6.3.4. Implementation6.4. Example of implementation of CE for exploration6.4.1. Definition of the problem6.4.2. Applying the CE6.4.3. Analyzing a simple example6.5. Optimal control under partial observation6.5.1. Decision-making in partially observed environments6.5.2. Implementing CE6.5.3. Example6.6. Conclusion6.7. Bibliography
Chapter 7. Optimizing Emissions for Tracking and Pursuit of Mobile Targets
7.1. Introduction7.2. Elementary modeling of the problem (deterministic case)7.2.1. Estimability measurement of the problem7.2.2. Framework for computing exterior products7.3. Application to the optimization of emissions (deterministic case)7.3.1. The case of a maneuvering target7.4. The case of a target with a Markov trajectory7.5. Conclusion7.6. Appendix: monotonous functional matrices7.7. Bibliography
Chapter 8. Bayesian Inference and Markov Models
8.1. Introduction and application framework8.2. Detection, segmentation and classification8.3. General modeling8.3.1. Markov modeling8.3.2. Bayesian inference8.4. Segmentation using the causal-in-scale Markov model8.5. Segmentation into three classes8.6. The classification of objects8.7. The classification of seabeds8.8. Conclusion and perspectives8.9. Bibliography
Chapter 9. The Use of Hidden Markov Models for Image Recognition: Learning with Artificial Ants, Genetic Algorithms and Particle Swarm Optimization
9.1. Introduction9.2. Hidden Markov models (HMMs)9.2.1. Definition9.2.2. The criteria used in programming hidden Markov models9.3. Using metaheuristics to learn HMMs9.3.1. The different types of solution spaces used for the training of HMMs9.3.2. The metaheuristics used for the training of the HMMs9.4. Description, parameter setting and evaluation of the six approaches that are used to train HMMs9.4.1. Genetic algorithms9.4.2. The API algorithm9.4.3. Particle swarm optimization9.4.4. A behavioral comparison of the metaheuristics9.4.5. Parameter setting of the algorithms9.4.6. Comparing the algorithms’ performances9.5. Conclusion9.6. Bibliography
Chapter 10. Biological Metaheuristics for Road Sign Detection
10.1. Introduction10.2. Relationship to existing works10.3. Template and deformations10.4. Estimation problem10.4.1. A priori energy10.4.2. Image energy10.5. Three biological metaheuristics 10.5.1. Evolution strategies10.5.2. Clonal selection (CS)10.5.3. Particle swarm optimization10.6. Experimental results10.6.1. Preliminaries10.6.2. Evaluation on the CD3 sequence10.7. Conclusion10.8. Bibliography
Chapter 11. Metaheuristics for Continuous Variables. The Registration of Retinal Angiogram Images
11.1. Introduction11.2. Metaheuristics for difficult optimization problems11.2.1. Difficult optimization11.2.2. Optimization algorithms11.3. Image registration of retinal angiograms11.3.1. Existing methods11.3.2. A possible optimization method for image registration11.4. Optimizing the image registration process11.4.1. The objective function11.4.2. The Nelder-Mead algorithm11.4.3. The hybrid continuous interacting ant colony (HCIAC)11.4.4. The continuous hybrid estimation of distribution algorithm11.4.5. Algorithm settings11.5. Results11.5.1. Preliminary tests11.5.2. Accuracy11.5.3. Typical cases11.5.4. Additional problems11.6. Analysis of the results11.7. Conclusion11.8. Acknowledgements11.9. Bibliography
Chapter 12. Joint Estimation of the Dynamics and Shape of Physiological Signals through Genetic Algorithms
12.1. Introduction12.2. Brainstem Auditory Evoked Potentials12.2.1. BAEP generation and their acquisition12.3. Processing BAEPs12.4. Genetic algorithms12.5. BAEP dynamics12.5.1. Validation of the simulated signal approach12.5.2. Validating the approach on real signals12.5.3. Acceleration of the GA’s convergence time12.6. The non-stationarity of the shape of the BAEPs12.7. Conclusion12.8. Bibliography
Chapter 13. Using Interactive Evolutionary Algorithms to Help Fit Cochlear Implants
13.1. Introduction13.1.1. Finding good parameters for the processor13.1.2. Interacting with the patient13.2. Choosing an optimization algorithm13.3. Adapting an evolutionary algorithm to the interactive fitting of cochlear implants13.3.1. Population size and the number of children per generation13.3.2. Initialization13.3.3. Parent selection13.3.4. Crossover13.3.5. Mutation13.3.6. Replacement13.4. Evaluation13.5. Experiments13.5.1. The first experiment with patient A13.5.2. Analyzing the results13.5.3. Second set of experiments: verifying the hypotheses13.5.4. Third set of experiments with other patients13.6. Medical issues which were raised during the experiments13.7. Algorithmic conclusions for patient A13.8. Conclusion13.9. Bibliography
List of Authors
Index

Content preview from Optimisation in Signal and Image Processing

Index

A

A priori, 247-252, 260, 265

Acceleration, 17

Active sets, 112, 120, 123, 132

AIC (Akaike Information Criterion), 3-11, 15, 16, 19-21, 26, 27, 32

Ant colony, 273, 274, 281, 283, 297

API algorithm, 225-241

Autoregressive (AR) models, 2

B

Bayesian network, 161, 166

BIC (Bayesian Information Criterion), 3-20, 26

B-spline, 207, 211

C

Capacity, 111-117, 131, 132,

Chromosome, 305

Clonal selection (CS), 252, 255-258, 265, 266

Cloning, 256, 258

CMOS cameras, 37, 38

Compressible fluid, 11

Consistency, 4, 5

Contour segmentation, 3

Convergence speed, 335

Cost, 113-126,

Cramér-Rao bound, 153, 154,

Criterion, 1-27

Cross-entropy, 138, 166, 167

D

Deformable models, 246, 247, 267

Deformable prototype, 209

Detecting obstacles, 32, 34

Detecting, 246, 264-267

Diaphony, 344, 346

Distance map, 247, 262-265

E

Echo, 198, 203-206, 215

Electrodes, 329-331, 336, 337, 340, 344-354

Electroencephalography (EEG), 301-303, 307-309, 313, 320

Electromyography (EMG), 302-304

Entropy, 2, 3, 28

Estimation EM, 201

Evolutionary algorithms, 252, 266

Evolutionary strategies (ES), 252-255, 261, 262, 264, 265

F

Filter, 153,

Filtering, 153, 155, 167

Fitness, 18, 20, 24-40

function, 24-28, 34, 35, 38-40

Fly algorithm, 22-24, 29

G

Genetic algorithms, 337

Gibbs sampling, 200

Global algorithm, 247

Gradient descent, 247, 260

Ground truth, 249, 260-265

H

HÉVÉA, 330, 339

Hidden Markov models, 159, 162, 166

Hierarchical models, 159, 166

Hilbert space, 115

Histograms, 2, 20, 24, 27, 31

Hough transform, 2, 4-9, 13, 14

I

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.

Read now

Unlock full access

More than 5,000 organizations count on O’Reilly

O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.

Julian F.

Head of Cybersecurity

I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.

Addison B.

Field Engineer

I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.

Amir M.

Data Platform Tech Lead

I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.

Mark W.

Embedded Software Engineer

Multidimensional Signal and Color Image Processing Using Lattices

Publisher Resources

ISBN: 9781848210448Purchase book

Cloud Computing

Data Engineering

Data Science

AI & ML

Programming Languages

Software Architecture

IT/Ops

Security

Design

Business

Soft Skills

Optimisation in Signal and Image Processing

by Patrick Siarry

Index

A

B

C

D

E

F

G

H

I

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.