Teaching language: English
Application code: 10118
Open for exchange students: Yes
Block schedule:
C
Module 

Credit distribution 

Examination dates 
Sp1 
Sp2 
Sp3 
Sp4 
Summer course 
No Sp 
0119 
Project 
3,5c 
Grading: TH 



3,5c






0219 
Laboratory 
4,0c 
Grading: TH 



4,0c






In programs
MPDSC DATA SCIENCE AND AI, MSC PROGR, Year 1 (compulsory elective)
MPBME BIOMEDICAL ENGINEERING, MSC PROGR, Year 1 (compulsory)
MPCOM COMMUNICATION ENGINEERING, MSC PROGR, Year 1 (compulsory elective)
MPSYS SYSTEMS, CONTROL AND MECHATRONICS, MSC PROGR, Year 1 (elective)
Examiner:
Torsten Sattler
Go to Course Homepage
Replaces
ESS060
Image analysis SSY095
Image analysis SSY096
Image analysis SSY097
Image analysis
Eligibility:
In order to be eligible for a second cycle course the applicant needs to fulfil the general and specific entry requirements of the programme that owns the course. (If the second cycle course is owned by a first cycle programme, second cycle entry requirements apply.)
Exemption from the eligibility requirement:
Applicants enrolled in a programme at Chalmers where the course is included in the study programme are exempted from fulfilling these requirements.
Course specific prerequisites
A basic course in Signals and Systems (or the equivalent) including the Fourier Transform, linear filter theory (impulse response, transfer function, convolution, sampling theorem). Working knowledge of probability theory.
Aim
The main aim of the course is to give a basic introduction to the algorithms and mathematical methods used in image analysis, to an extent that will allow the student to handle industrial image analysis problems. In addition the aim is to help the student develop his or her ability in problem solving, both with or without a computer.
Learning outcomes (after completion of the course the student should be able to)
Knowledge and understanding
For a passing grade the student must
 be able to explain clearly, and to independently use, basic mathematical concepts in image analysis.
 be able to describe and give an informal explanation of the mathematical theory behind some central image analysis algorithms (both deterministic and stochastic).
 have an understanding of the statistical principles used in machine learning.
Competences and skills
For a passing grade the student must
 in an engineering manner be able to use computer packages to solve problems in image analysis.
 show good capability to independently identify problems which can be solved with methods from image analysis, and be able to choose an appropriate method.
 be able to independently apply basic methods in image analysis to problems which are relevant in industrial applications or research.
 with proper terminology, in a well structured way and with clear logic be able to explain the solution to a problem in image analysis.
Content
Basic image analysis tools: Filtering and scale space representations.
Extraction of image features: Blob, edge and corner detection.
Image similarity: Correlation, mutual information and the SIFT descriptor.
Image registration: Robust model fitting and RANSAC.
Basics of computer vision: camera geometry, epipolar geometry and motion estimation
Machine learningbased methods for classification and segmentation: Nearest neighbour and convolutional nets.
Applications: Computeraided diagnostics (segmentation, alignment, classification), robotic vision (motion estimation, object/scene recognition) and image search.
Organisation
The course consists of a number of lectures (including guest lectures given by industry and / or academic researchers showcasing practical applications of image analysis). In addition there are a number of exercise sessions, four laboratory sessions and one project. The laboratory sessions may be carried out individually or in groups, but the project needs to be carried out individually. The project involves the submission of a written report explaining the image analysis problem at hand, a motivation of the chosen theory and algorithms, results and conclusions.
Literature
Optional: Szeliski, R.: Computer Vision, Algorithms and Applications. Springer, 2010, ISBN: 9781848829343.
optional: Goodfellow, I. and Bengio, Y. and Courville, Deep Learning. MIT Press, 2016, ISBN: 9780262035613.
It is possible to pass the course without owning the books, using material available through the course page. Both books are available online for free (as preprints).
Examination including compulsory elements
There is no written exam in this course. Students will be graded based on the project and will need to pass the laboratory sessions. Optional exercises in the laboratory will count towards higher grades (only if the passing grade is reached).