Grant: Discovery Grants Program - Individual
École Polytechnique de Montréal
$12,000.00
Multiscale methods for signal processing and image synthesis
FY 2008-09
Summary
MULTISCALE METHODS FOR SIGNAL PROCESSING AND IMAGE SYNTHESIS: We propose a research program in two parts that share a multiscale / multipoint approach to signal and image processing: (I) Multiscale Principal Components (MPC) for signal and image processing and (II) The Patchwork Stochastic Simulation Algorithm (PSSA).
PART I (MPC): We have been developing a data-adaptive generalization of wavelets that we call multiscale principal components (MPC). MPC are multiscale orthogonal bases that can adapt to the class of signals considered. For some classes of signals, we have shown that MPC can perform much better than wavelets in data compression and noise filtering. We propose to pursue the development of our MPC. Our objectives are: to develop high-density MPC to get a better representation of localized patterns and improve performance in data compression and noise filtering experiments; to develop two-dimensional MPC.
PART II (PSSA): The availability of high-resolution images and remotely sensed data creates the need for more realistic statistical models of the spatial distribution of various quantities, e.g. oil, water or ore. Models are required that can reproduce accurately both the rich statistical and morphological properties of such spatial distributions. These models are essential for resource assessment and risk management. We have been developing a new and very promising multipoint stochastic simulation approach called the Patchwork Stochastic Simulation Approach (PSSA). The PSSA is based on reference images that are decomposed into sub-images (patches) that are assembled to create new images. The art lies in the assembly procedure. We propose to pursue the development of our PSSA to obtain an accurate control of the image multipoint statistics and to introduce conditioning to pre-existing data in the simulations.
Program
Discovery Grants Program - Individual
Recipient
Location
Quebec, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
250241-2008
Name nom
Saucier, Antoine
Department département
Mathématiques et génie industriel
Organization id
64
Institution établissement
École Polytechnique de Montréal
Province en
Québec
Province fr
Québec
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2008
Competition year année de concours
2008
Award amount
12000
Program id
RGPIN
Program nane en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
Discovery grants programs
Group fr
Programmes de subventions à la découverte
Committee code
337
Committee name en
Pure & Applied Maths - B
Committee name fr
Maths pures et appliquées - B
Area of application code
202
Area of application group en
Natural resources (economic aspects)
Area of application group fr
Ressources naturelles (aspects économiques)
Area of application en
Mineral resources ( prospecting, exploration, mining, extraction, processing)
Area of application fr
Ressources minérales (prospection, exploration, mines, extraction et préparation)
Research subject code
2514
Research subject group en
Electrical and electronic engineering
Research subject group fr
Génie électrique et électronique
Research subject en
Digital signal processing
Research subject fr
Traitement des signaux numériques
Partie
1
Nb partie
3
Application title
Multiscale methods for signal processing and image synthesis
Keyword
NA
Application summary
MULTISCALE METHODS FOR SIGNAL PROCESSING AND IMAGE SYNTHESIS: We propose a research program in two parts that share a multiscale / multipoint approach to signal and image processing: (I) Multiscale Principal Components (MPC) for signal and image processing and (II) The Patchwork Stochastic Simulation Algorithm (PSSA).
PART I (MPC): We have been developing a data-adaptive generalization of wavelets that we call multiscale principal components (MPC). MPC are multiscale orthogonal bases that can adapt to the class of signals considered. For some classes of signals, we have shown that MPC can perform much better than wavelets in data compression and noise filtering. We propose to pursue the development of our MPC. Our objectives are: to develop high-density MPC to get a better representation of localized patterns and improve performance in data compression and noise filtering experiments; to develop two-dimensional MPC.
PART II (PSSA): The availability of high-resolution images and remotely sensed data creates the need for more realistic statistical models of the spatial distribution of various quantities, e.g. oil, water or ore. Models are required that can reproduce accurately both the rich statistical and morphological properties of such spatial distributions. These models are essential for resource assessment and risk management. We have been developing a new and very promising multipoint stochastic simulation approach called the Patchwork Stochastic Simulation Approach (PSSA). The PSSA is based on reference images that are decomposed into sub-images (patches) that are assembled to create new images. The art lies in the assembly procedure. We propose to pursue the development of our PSSA to obtain an accurate control of the image multipoint statistics and to introduce conditioning to pre-existing data in the simulations.