TMS016/MSA300, Statistical image analysis, 2017/18

Latest news

30/5: Preliminary solutions to the exam can be found here.

2/5: The second part of the project is now available below.

13/4: The first part of the project is now available below. You can start working on this after computer exercise 4 on Monday.

9/4: The lecture and exercise plan has been updated. Since we did not have time to cover the likelihood-based approach today, this will be done on Wednesday instead, and you can then continue working on Computer Exercise 3 also on Wednesday.

9/4: You can now sign up for project groups in PINGPONG.

Welcome to the course! The schedule for the course can be found in TimeEdit.

Teachers

Course coordinator: David Bolin (david.bolin@chalmers.se)

Lab supervisor: Marco Longfils (longfils@chalmers.se)

Course literature


Most of the material covered in the course is briefly described in the Lecture notes (abbreviated LN in the schedule below) by Mats Rudemo. During the first part of the course, we will mainly use chapters from the Handbook of Spatial Statistics, which is available as an eBook through the Chalmers library. For the second part of the course, we will also use material from The Elements of Statistical Learning, which also is available as an eBook through the Chalmers library.

Program

The course has two lectures and two computer exercises each week. Details for these are given in the schedule below, which will be updated during the course. For the lectures, the chapters covered in the books are listed, where LN denotes the lecture nodes and HS denotes the Handbook of spatial statistics and EL The Elements of Statistical Learning.
The lectures will always be in room MVF26, and the computer exercises in room MVF25.
TimeLectureComputer exercise
Week 1/12 Monday
10:00-11:45
L1 Introduction
LN pages 1-16.
 
  Monday
13:15-15:00
E1   Basic image processing
chalmersplatsen.jpg
  Wednesday
10:00-11:45
L2 Random fields
HS 2.1-2.7
 
  Wednesday
13:15-15:00
E2   Gaussian fields
Matlab files (zip)
Week 2/15 Monday
10:00-11:45
L3 Estimation and kriging
HS 2.8, 3
 
  Monday
13:15-15:00
E3   Estimation and kriging
Matlab files (zip)
  Wednesday
10:00-11:45
L4 Likelihood-based parameter estimation
HS 4.1-4.3
 
  Wednesday
13:15-15:00
E4   Continue working on exercise 3
Week 3/16 Monday
10:00-11:45
L5 Gaussian Markov random fields
HS 12.1.1-12.1.4, parts of 12.1.7, and 13.1-13.2
 
  Monday
13:15-15:00
E5   Image reconstruction using GMRFs
Matlab files
  Wednesday
10:00-11:45
L6 Image segmentation and mixture models
LN 1.3, 2.1-2.3,2.8
 
  Wednesday
13:15-15:00
E6   Image segmentation using mixture models
Matlab files (zip)
Week 4/17 Monday
10:00-11:45
L7 Feature selection and filtering
LN 1.2,1.4-1.6
 
  Monday
13:15-15:00
E7   Image filtering
  Wednesday
10:00-11:45
L8 Discrete Markov random fields
HS 12.1.5, 12.1.8, 12.1.9
 
  Wednesday
13:15-15:00
E8   Simulation of MRFs
Matlab files
Week 5/18 Wednesday
10:00-11:45
L9 Segmentation using Markov random fields
LN 4
 
  Monday
13:15-15:00
E9   Classification using Markov random fields
Matlab files (zip)
Week 6/19 Monday
10:00-11:45
L10 Classification and machine learning
LN 2.4-2.7, 3.2, EL 2, 12
 
  Monday
13:15-15:00
E10   Image classification
Matlab files (zip)
  Wednesday
10:00-11:45
L11 Neural nets
LN 3.1, EL 11
 
  Wednesday
13:15-15:00
E8   Work on projects
Week 7/20 Monday
10:00-11:45
L12 Point processes
LN 6,7
 
  Monday
13:15-15:00
E12   Work on projects
  Wednesday
10:00-11:45
L13 Repetition and exam questions
Mock exam
 
  Wednesday
13:15-15:00
E13   Work on projects
Week 8/21 Monday
10:00-11:45
L14 Project seminars  
  Monday
13:15-15:00
E14   Work on projects
  Wednesday
10:00-11:45
L15 Project seminars  
  Wednesday
13:15-15:00
E8   Work on projects

Computer exercises

The exercises will be done in Matlab, and some knowledge of Matlab is assumed. If you need an introduction, see Learning MATLAB, Tobin A. Driscoll ISBN: 978-0-898716-83-2 (The book is published by SIAM).

Most computer exercises will use functions written specifically for this course. These will be linked in the schedule before each exercise.

Course requirements and representatives

The learning goals of the course can be found in the course plan.

The student representatives for the course are Erik Larsson (erlarsso@student.chalmers.se), Vincent Szolnoky (szolnoky@student.chalmers.se), and Elijah Ferreira (elijahf@student.chalmers.se).

Examination

The examination consists of two parts: One written exam at the end of the course and one project assignment. These two parts are weighted equally for the final grade. The written exam is individual whereas the project work can be done in groups of 1-3 students.

The project consists of three parts:

For the third part, a list of project suggestions is available here. Send by mail to me and Marco a planning report for your project, no later than April 25 but it could very well be sent much sooner. It should contain name of project, your project group number, purpose of project, data description including source of data, if suitable also a sketch of methodology and a few literature references.

Regarding the project report:
Deadlines for the project:

Examination procedures

In Chalmers Student Portal you can read about when exams are given and what rules apply on exams at Chalmers. In addition to that, there is a schedule when exams are given for courses at University of Gothenburg.

Before the exam, it is important that you sign up for the examination. If you study at Chalmers, you will do this by the Chalmers Student Portal, and if you study at University of Gothenburg, you sign up via GU's Student Portal.

At the exam, you should be able to show valid identification.

After the exam has been graded, you can see your results in Ladok by logging on to your Student portal.

At the annual (regular) examination:
When it is practical, a separate review is arranged. The date of the review will be announced here on the course homepage. Anyone who can not participate in the review may thereafter retrieve and review their exam at the Mathematical Sciences Student office. Check that you have the right grades and score. Any complaints about the marking must be submitted in writing at the office, where there is a form to fill out.

At re-examination:
Exams are reviewed and retrieved at the Mathematical Sciences Student office. Check that you have the right grades and score. Any complaints about the marking must be submitted in writing at the office, where there is a form to fill out.