Logo

Mathematical Sciences Research Institute

Home » Introductory Workshop in Mathematical, Computational and Statistical Aspects of Image Analysis

Workshop

Introductory Workshop in Mathematical, Computational and Statistical Aspects of Image Analysis January 24, 2005 - January 28, 2005
Registration Deadline: January 28, 2005 almost 10 years ago
To apply for Funding you must register by: October 24, 2004 about 10 years ago
Parent Program: Mathematical, Computational and Statistical Aspects of Image Analysis
Organizers David Donoho, Olivier Faugeras, David B Mumford
Speaker(s)

Show List of Speakers

Description

The introductory workshop will be a week long and concentrate on problems in what is typically described as ``early vision'' or ``low-level vision''. By this, people mean whatever you can understand about an image as a function or a signal without introducing explicitly the origin of the image on the basis of the physics and the specific objects present in the world. We have in mind the following themes, each of which will be introduced in a series of tutorial lectures, intended at a level that could be understood by mathematicians, physical scientists or engineers with no previous background in vision and image analysis. 1. Harmonic analysis applied to images. The last few years have seen a great deal interest in the computational harmonic analysis community on developing approximations and expansions specifically oriented to problems in dealing with images, for example edges and textures in images. The resulting multiscale processing tools start with wavelets and go considerably beyond (bandelets, curvelets, ridgelets, brushlets, etc.). There are numerous applications to compression, denoising etc. (Candes, Mallat, Meyer, Saito, Donoho) 2. Statistics of natural images at the signal as well as morphological levels. Because of its data intensive nature, a deep study of the statistics of images lagged some 20 years behind the statistical study of speech. However, many groups are now working out many types of statistics and constructing stochastic models for various aspects of natural images. (Malik, Grenander, Ruderman, Simoncelli, Olshausen, Gousseau, Lee, van Hateren, Freeman, Mumford) 3. Contours, textures, and perceptual organization. The gestalt school of psychophysics, from the 20.s through the 60.s, systematized in a qualitative way the rules by which the elements of images are grouped into larger structures. Vision scientists are now beginning to formalize these rules quantitatively. (Malik, Zhu, Morel, Moisan, Desolneux, Geman, Williams). 4. Variational approaches, partial differential equations for image analysis. These techniques date from the 80.s (Mumford-Shah/Blake-Zisserman functional, the .snakes. of Terzopoulos, Perona-Malik non-linear diffusion) and have been one of the main mathematical approaches to image processing, esp. in the schools of Osher and Morel. (Osher, Chan, Shah, Tannenbaum, Morel, Guichard, Faugeras, Mumford, Sethian). Lectures Tutorial/Introductory/Survey David Donoho (Stanford) 1. Natural Image Statistics and Bayesian Statistics, Information Theory vs. Computer Vision Perspectives 2. Image Manifolds and Image Complexes 3. Harmonic Analysis Analogies to Early Vision. Olivier Faugeras (INRIA) 1. Fundamental PDE's of Computer Vision 2. Approaches to Image Warping and Matching 3. Shape Topologies and Applications to Segmentation David Mumford (Brown) 1. Pattern theory: Grenander's ideas and examples. 2. Modeling shape: comparing metrics, L^1, L^2 and L^\infty techniques, the solid, liquid and conformal approaches. Research/Advanced 1. Image representation: Eero Simoncelli (NYU) 2. Biological vision: Bruno Olshausen (Davis/RNI) 3. Seeing as Statistical Inference: Song Chun Zhu (UCLA) 4. Statistics of Grouping and Figure/Ground in Natural images: J.Malik 5. Modern Classifier design: Trevor Hastie (Stanford) 6. Towards Unsupervised Learning of Categories: Pietro Perona (Caltech) 7. Strategies for visual recognition: Donald Geman (JHU/ENS Cachan) 8. Ecological optics: Jan Koenderink 9. Energy minimization and "u+v" models: Luminita Vese (UCLA) Schedule of Talks


Funding & Logistics Show All Collapse

Show Funding

To apply for funding, you must register by the funding application deadline displayed above.

Students, recent Ph.D.'s, women, and members of underrepresented minorities are particularly encouraged to apply. Funding awards are typically made 6 weeks before the workshop begins. Requests received after the funding deadline are considered only if additional funds become available.

Show Lodging

MSRI has preferred rates at the Rose Garden Inn, depending on room availability. Reservations may be made by calling 1-800-992-9005 OR directly on their website. Click on Corporate at the bottom of the screen and when prompted enter code MATH (this code is not case sensitive). By using this code a new calendar will appear and will show the MSRI rate on all room types available.

MSRI has preferred rates at the Hotel Durant. Reservations may be made by calling 1-800-238-7268. When making reservations, guests must request the MSRI preferred rate. If you are making your reservations on line, please go to this link and enter the promo/corporate code 123MSRI. Our preferred rate is $139 per night for a Deluxe Queen/King, based on availability.

MSRI has preferred rates of $149 - $189 plus tax at the Hotel Shattuck Plaza, depending on room availability. Guests can either call the hotel's main line at 510-845-7300 and ask for the MSRI- Mathematical Science Research Inst. discount; or go to www.hotelshattuckplaza.com and click Book Now. Once on the reservation page, click “Promo/Corporate Code“ and input the code: msri.

MSRI has preferred rates of $110 - $140 at the Berkeley Lab Guest House, depending on room availability. Reservations may be made by calling 510-495-8000 or directly on their website. Select “I am an individual traveler affiliated with MSRI”.

Additional lodging options may be found on our short term housing page.

Show Directions to Venue

Show Visa/Immigration

Schedule
Show All Collapse
Jan 24, 2005
Monday
09:00 AM - 10:00 AM
  Pattern Theory: Grenander's Ideas and Examples
David Mumford (Brown University)
10:30 AM - 11:30 AM
  Modern Classifier Design
Trevor Hastie
10:30 AM - 11:30 AM
  Variational Principles and PDE's of Computer Vision
Olivier Faugeras (Institut National de Recherche en Informatique Automatique (INRIA))
Jan 25, 2005
Tuesday
09:00 AM - 10:00 AM
  An Invitation to Visual Recognition
Pietro Perona
10:30 AM - 11:30 AM
  Strategies for Visual Recognition
Donald Geman (Johns Hopkins University)
01:30 PM - 02:30 PM
  Image Statistics and Surface Perception
Edward Adelson
03:00 PM - 04:00 PM
  Multiscale Geometric Analysis for Images
Richard Baraniuk
Jan 26, 2005
Wednesday
09:00 AM - 10:00 AM
  Modeling Shape
David Mumford (Brown University)
10:30 AM - 11:30 AM
  Variational Methods for Multimodal Image Matching: Theory and Applications
Olivier Faugeras (Institut National de Recherche en Informatique Automatique (INRIA))
01:30 PM - 02:30 PM
  Appearance Manifolds 2
David Donoho (Stanford University)
03:00 PM - 04:00 PM
  Energy Minimization for Cartoon & Texture Separation :U+V Models
Luminita Vese
Jan 27, 2005
Thursday
09:00 AM - 10:00 AM
  Statistical Image Models
Eero Simoncelli
10:30 AM - 11:30 AM
  What We Know and Don't Know About Biological Vision
Bruno Olshausen (University of California, Berkeley)
01:30 PM - 02:30 PM
  Seeing as Statistical Inference
Song Chun Zhu (University of California, Los Angeles)
03:00 PM - 04:00 PM
  Ecological Statistics of Grouping and Figure-Ground Cues
Jitendra Malik (University of California, Berkeley)
Jan 28, 2005
Friday
09:00 AM - 10:00 AM
  Ecological Optics
Jan Koenderink
10:30 AM - 11:30 AM
  Variations on Image and Shape Warping, Statistics and Segmentation
Olivier Faugeras (Institut National de Recherche en Informatique Automatique (INRIA))
01:30 PM - 02:30 PM
  Learning and Image Segmentation
Joachim Buhmann
03:30 PM - 04:30 PM
  More Interactions
David Donoho (Stanford University)