ASCI course a8:
Front-End Vision and Multi-Scale Image Analysis

Autumn 2011


[Image of Scale-Space Cube]

An introduction to modern multi-scale image analysis
based on inspiration of biological vision.

A PhD course given at the Department of Biomedical Engineering (Eindhoven University of Technology and University of Maastricht).

NB: This course is also open for TU/e BME MSc students as course 8D010, as "ASCI PhD course a8", and as course for the PhD Research School "ImagO".

Tutors: Prof. Bart M. ter Haar Romeny, PhD, Eindhoven University of Technology / Maastricht University
Prof. Nicolai Petkov, PhD, University of Groningen
Dates: 2 fulltime weeks, with one 'recovery' week in between without lectures.
Lectures in the morning from (09:45-12:30) Monday 3 October 2011 till Friday 7 October 2011, and from Monday 17 October 2011 till Friday 21 October 2011.
Computer laboratories in the afternoon (13:45-16:30), using Mathematica 8 to exercise the course material and tasks.
In the week 10-15 October 2011 there is no course.

Registration:

Register through the ASCI website: here.

 
Registration for course and exam is free for TU/e, ASCI, ImagO students, and employees of industries officially collaborating with TU/e BME.
For registration as 'contractant' with TU/e to do an official exam for 3 ECTS as non-TU/e student: see STU registration form.
Costs: € 250 per course. Registration is free when no exam is done.
Costs for industrial participants: € 1200 (invoice will be sent by ASCI after registration).

Evaluation: Form, to be sent to ASCI.

Total duration: 27 oral lectures of 45 minutes each, and 27 hours hands-on training.

Code ASCI: a8 (4 ECTS study points)
Code TUE-BME: 8D010 (3 ECTS study points).
The lectures will be made available as streaming video.

Goal:

Image analysis is the extraction of useful information from images. In this course we give a modern mathematical (and physics based) approach to multi-scale image analysis as a branch of computer vision. We give an intuitive introduction to multi-scale image analysis, trying to keep the analogy with stages in the human visual system as close as possible. The human visual system also widely exploits a diversity of multi-scale filters in its processing layers.

Among the topics covered are: filters to sample and analyze images, the use of filters in detecting edges and corners in images, multi-scale analysis of 2D and 3D shape and motion from image sequences, depth from stereo, orientation analysis, and the use of contemporary, well-understood mathematical tools in this field such as differential geometry and tensor analysis.

The majority of the examples discussed are from 2D, 3D and 4D (3D-time) medical imaging. We devote some time to the efficient numerical implementation of the different techniques. Hands-on experience is acquired in a computer lab, where experiments in Mathematica 8 illustrate the theory and applications in practice.

Topics discussed:

Computer vision plays an increasing role in the detection and recognition of structures, quantitative analysis, segmentation and visualization. 

A modern development is computer-aided diagnosis (CAD), where the computer assists in finding possible pathology in images, particularly for screening applications.
We discuss several examples in detail:

Detailed program and content:

Times:
Day Time Content Lecture material Room
(to be announced)
Monday
3 October 2011
13:45-14:30 Course Introduction   Introduction
  Introduction (zipfile with all movies, 146 MB)
GEM-Z 3A10
14:45-15:30 Course Notion of scale Powers of 10 GEM-Z 3A10
15:45-16:30 Course Axiomatics of multi-scale operators   Scale-space from entropy GEM-Z 3A10
Tuesday
4 October 2011
09:45-11:30 Computer lab Introduction to Mathematica 8
Screencast: 20 minute introduction to Mathematica 8

More screencasts


Tutorial Mathematica notebooks 8ZZ16:

Course part 1 of 3 (English)
Course part 2 of 3 (English)

Course part 3 of 3 (English)
 


BMIA MMA 8 course

GEM-Z 3A06
11:45-12:30 Computer lab Exercises with Mathematica 8 Download the FEV book

MathVisionTools:  www.mathvisiontools.net

(Run the command:
$AddOnsDirectory
in Mathematica, and store in this directory)

Images of the book & test images
(Data.zip, 31 MB, extract in MathVisionTools\Data directory)

shortnotation.nb

Exercises I

Some testimages to play with.

GEM-Z 3A06

 
Exercises with Mathematica 8 Study material:
Eindhoven Tips
Dictionary manipulations
Often used commands

FrondEnd Interactivity
Demo active shape
PackageNotebook.nb
Wolfram Inc.
Eduroam (network access through SurfNet)

GEM-Z 3A06
Tuesday
4 October 2011
13:45-14:30 Course The Gaussian kernel Gaussian kernel Note:
Change of room!

STC 0.02

(Helix building = Chemistry), near the eleveators, to the right.

14:45-15:30 Course Gaussian derivatives Gaussian derivatives STC 0.02 (Helix)
15:45-16:30 Course Deblurring

 

 

 

Numeric implementation of
Gaussian derivatives

 

 

 

Limits on observations

Deblurring
Deblurring

Convolution01
Convolution02
Convolution03
  Convolution animations
Implementation

Limits
Limits

STC 0.02 (Helix)
Wednesday
5 October 2011
09:45-10:30 Course Speed of Gaussian convolutions

Regularization

Regularization STC 0.02 (Helix)
10:45-11:30 Course Gauge coordinates Differential structure STC 0.02 (Helix)
11:45-12:30 Course Differential structure I   STC 0.02 (Helix)
13:45-16:30 Computer Lab Exercising FEV lectures Tasks 02 GEM-Z 3A06
Thursday
6 October 2011
09:45-12:30 Computer Lab Exercising FEV lectures   GEM-Z 3A06
13:45-14:30 Course Second order differential structure Vesselness

Original paper: A. Frangi, W. Niessen, K. Vincken and M. Viergever, Multiscale vessel enhancement filtering. In: Proceedings of the MICCAI’98Lecture Notes in Computer Science vol. 1496, Springer-Verlag, Berlin (1998), pp. 130–137. 

GEM-Z 3A08
14:45-15:30 Course Applications second order differential structure Applications second order structure GEM-Z 3A08
15:45-16:30 Course Third order differential structure   GEM-Z 3A08
Friday
7 October 2011
09:45-12:30 Computer Lab Exercising FEV lectures Tasks 03 GEM-Z 3A06
13:45-14:30 Course Front-end visual system I Front-End Visual System AUD 07
14:45-15:30 Course Front-end visual system II Youtube: Hubel & Wiesel - Cortical neuron V1

Youtube: Hubel's research

AUD 07
15:45-16:30 Course Front-end visual system III Visual illusions
Spiral illusion
AUD 07
Note: No lectures from 10 October 2011 till 15 October 2011.  
Monday
17 October 2011
09:45-12:30 Computer Lab Exercising FEV lectures Tasks 03 (with some solutions)

Tasks 07 (with some solutions)

GEM-Z 3A06
13:45-14:30 Course Gabor functions and filters (as models of cortical areas V1/V2) Prof. Nicolai Petkov STC 0.02 (Helix)
14:45-15:30 Course Surround suppression (or non-classical receptive field inhibition in areas V1/V2)

References:
Contour and boundary detection improved by surround suppression of texture edges (pdf)

Contour detection based on nonclassical receptive field inhibition (pdf)

Suppression of contour perception by band-limited noise and its relation to non-classical receptive field inhibition (pdf)

Prof. Nicolai Petkov

Lecture slides 01 (Gabor)

Lecture slides 02 (surround suppression)

STC 0.02 (Helix)
15:45-16:30 Course What comes after V2? Computational model of shape selective neurons in area V4, with application to the detection of blood vessel bifurcations in retinal funds images. Dr. George Azzopardi
(g.azzopardi@rug.nl,
www.cs.rug.nl/~george)

Lecture slides

STC 0.02 (Helix)
Tuesday
18 October 2011
09:30-12:30 Computer Lab Exercising FEV lectures Tasks - visual system GEM-Z 3A06
13:45-14:30 Course Geometry-driven diffusion I Geometry-Driven Diffusion
Geometry-Driven Diffusion
STC 0.02 (Helix)
14:45-15:30 Course Geometry-driven diffusion II PDF: Original paper:
P. Perona, J. Malik, "Scale-space and edge detection using anisotropic diffusion", PAMI 12(7), pp. 629-639, 1990. 
STC 0.02 (Helix)
15:45-16:30 Course Scale-time: differential structure of time sequences Scale-time
Scale-time
STC 0.02 (Helix)
Wednesday
19 October 2011
09:45-10:30 Course Color Differential Structure Color differential structure
Color differential structure

Color Invariants

STC 0.02 (Helix)
10:45-11:30 Course Deep structure I:
Edge focusing, watershed segmentation,
ScaleSpaceViz demo
Edge focusing, follicles

ScaleSpaceViz (VTK application) download

STC 0.02 (Helix)
11:45-12:30

 Course

Deep structure II:
Follicle detection
Edge focusing, follicles STC 0.02 (Helix)
13:45-16:30 Computer Lab Toppoints, image retrieval Toppoints in image matching

Toppoint detection

GEM-Z 3A06
Thursday
20 October 2011
10:00-10:45 Course Steerable kernels Steerable kernels GEM-Z 1.03
11:00-11:45 Course Multi-orientation analysis, context Multi-orientation analysis GEM-Z 1.03
13:45-16:30 Computer Lab Exercising FEV lectures, exam tasks   GEM-Z 3A10
Friday
21 October 2011
09:30-12:30 Computer Lab Exercising FEV lectures, exam tasks Preparing the exam tasks. GEM-Z 3A06
13:45-14:30 Course Rehearsal of the course, Questions & Answers, any topic of the course Canceled AUD 07
14:45-15:30 Course Rehearsal of the course, Questions & Answers, any topic of the course Canceled AUD 07
 

Place:


*Lecture rooms:

MA: Matrix building
PAV: Paviljoen building
AUD: Auditorium
GEM-Z: Gemini Zuid (Biomedical Engineering & Mechanical Engineering) building
GEM-Z 3A.06 is a room with desktop computers, available for exercising the course material with Mathematica 8.

See the campusmap of TU/e for directions.

Literature

The reader consists of the chapters of a the book: "Front-End Vision and Multi-scale Image Analysis", by Bart M. ter Haar Romeny. This book is written as a series of Mathematica notebooks. It contains a CR-ROM with all notebooks, which can be installed in the Mathematica Help-browser. The Mathematica code is the topic for the computer laboratories during the course.

ISBN: 1-4020-1507-0 (paperback), 1-4020-1503-8 (hardcover). Springer, Berlin. 
Order the book with Springer or Amazon.

NB: The book can also be downloaded with all chapters, Mathematica notebooks and example images from
here (login with your TU/e domain user/password).

Recommended reading:

Proceedings Scale-Space conferences

Other software:

Other:

Computer Laboratory:

On the Wednesday mornings computer laboratories will be organized to acquire hands-on experience with the discussed scaled differential invariant operators on a variety of 2D and 3D images. We use the program Mathematica 8 (http://www.wolfram.com/).

For TUE members: Mathematica 8.0.1 for Windows can be downloaded from the TU/e campus software website.
Mac OS x version:
 \\physstor\appl\mac-software.
Linux version:
\\wtbfiler\Software\Unix-Software.

Recommended tutorial books on Mathematica:

 Some useful notebooks:

The famous mathematics teaching files and resource online: MathWorld.


Examination:

Select any three (3) questions from this set of questions: Exam tasks 2011.

Write a Mathematica 8 notebook per question and send them within two weeks after the end of the course to B.M.terHaarRomeny@tue.nl.
Please explain the steps of your reasoning in detail, use Manipulate functions if appropriate.
Make sure the notebook can run, so include your own images (store them in the same directory as the notebook, and use SetDirectory[NotebookDirectory[]]), or Import them from a web URL.


Some examples

The detection of ridges (midlines) for an X-ray image of hands. "Ridgeness" is a second order property.

Low dose fluoroscopy image of an electro-physiology catheter in ther heart. The extra low dose is beneficial for the radiation dose, but leads to a deteriorated image quality. Robust catheter detection with oriented filters and tensor voting.

Left: histological image of a fungus cell, paramecium caudatum. Middle: edge detection with a detector optimized for yellow-blue differences. Right: edge detection with a detector optimized for red-green differences.

Noisy 2-photon microscopy image of bone tissue.

The same image enhanced with an orientation-score denoising filter.

Contact the tutors:

prof.dr.ir. Bart M. ter Haar Romeny
Department of Biomedical Engineering (BME-BMT)
Group Biomedical Imaging Analysis BMIA
Eindhoven University of Technology
Den Dolech 2 - WH2.106
NL-5612 AZ Eindhoven
Tel. 00-31-40-2475537 (secr. Margret Philips)
email: B.M.terHaarRomeny@tue.nl
prof.dr. Nicolai Petkov
Department of Computing Science
Rijks Universiteit Groningen
Blauwborgje 3
NL-9700 AV Groningen
Tel: 00-31-50-3633939 (secr.) / 3637129 / 3633931
Fax: 00-31-50-3633800
Email: N.Petkov@rug.nl 

Class of 2011.