Course syllabus

Course description

SSY098 Image analysis lp4 VT26 (7.5 hp)
Course is offered by the department of Electrical Engineering

Contact details

Examiner
Jennifer Alvén, alven@chalmers.se, office: EDIT building room 7312

Teachers
Victor Wåhlstrand, victor.wahlstrand@chalmers.se 
Josef Bengtson, bjosef@chalmers.se 
Vilgot Jansson, vilgot.jansson@chalmers.se  
Sofie Allgöwer, allgower@chalmers.se 

Course representatives
Found here

Course purpose

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.

Schedule

Course schedule: Course schedule
Course schedule on TimeEdit: TimeEdit

Course literature

The necessary course material will be provided during the course. This includes lab slides, lab pm's, lecture slides, lecture notes, project slides, project pm's.

The following three resources (available online for free) complement and extend the course material and serve as additional (optional) reading:

Course design

In this course, you will learn fundamental concepts in image analysis, computer vision, and deep learning. You will apply the theoretical knowledge from lectures through lab assignments and a project. The project involves implementing an image analysis tool and will require incorporating techniques beyond those covered directly in lectures, though closely related. Lab assignments and the project will also include optional theoretical exercises.

You can work on the labs and project at home or in the scheduled lab sessions. Attendance at lectures and labs is not mandatory. An anonymous discussion forum will be available for peer and teacher support. Teachers will also have office hours where you can ask questions. Course announcements will be posted on Canvas (some may also be mentioned in lectures, but all will be on Canvas).

All practical assignments and projects will be implemented in Python. The first lab serves as an introduction to using Python for image analysis, and does not require submission. For details on lab and project submissions, revisions, and grading, see Examination below.

Changes made since the last occasion

  • New TA: Vilgot.
  • New rules regarding LLM usage, see Examination below.
  • New rules for late submission of labs and projects, see Examination below.
  • New lectures on (i) multi-modality & vision-language models, and (ii) explainability & uncertainty.

Additionally, all lectures, labs, and projects have been updated based on feedback from previous years and the rapid development of the research field. Some tasks and techniques are now emphasized more, while others are de-emphasized.

Learning objectives and syllabus

Learning objectives

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.

Link to the syllabus on Studieportalen.

Examination

This course does not have a written exam. Instead, your grade will be based on lab assignments and a project.

Passing the course (Grade 3)
To pass the course with a grade of 3, you must:

  • Complete and pass all four labs
    • Each lab requires submitting a completed Jupyter notebook including code.
    • Labs are done in groups of 1–2 students.
    • Before starting each lab, sign up for a lab group on the People page. You need to sign up for a new lab group for each lab, even though you choose to work with the same partner.
    • More detailed instructions for the labs (what to do and what to submit) can be found in each lab's assignment page.
  • Complete the basic part of a project
    • The project requires submitting a short report and your code.
    • The project is done individually (not in groups).
    • You will choose one out of five project options. Before starting the project, sign up for the chosen project on the People page. There will be a limit on the number of students who can choose each project.
    • More detailed instructions for the projects (what to do and what to submit) will appear in May.

Higher Grades (4 & 5)
To achieve a higher grade:

  • Grade 4:
    • Either complete the advanced part of the project, extending your basic implementation.
    • Or answer a set of theoretical questions related to your project.
  • Grade 5:
    • Complete both the advanced part of the project and the theoretical questions.
  • Bonus points:
    • Each lab includes one set of theoretical questions, worth 2 points each (total of 8 points for all 4 labs).
    • If you achieve 6 or more points, your grade will automatically increase by one step, provided you have passed the course without it.
    • The theoretical questions must be answered individually and cannot be revised.

Submission and revision guidelines

  • All labs, projects, and theoretical questions must be submitted electronically through Canvas.
  • The deadlines for the project and the labs are given in the course schedule and in each assignment respectively.
    • Late lab bonus questions submissions (after the deadline) will not be marked.
    • Late project advanced part or theoretical questions submissions (after the deadline) will not be marked.
    • Any lab or project submitted after the deadline will count as one revision attempt.
  • You will be given the opportunity to revise the labs and projects based on our comments.
    • You will have one revision opportunity for each lab during the course (deadline for submitting revisions are given in the course schedule) .
    • You will have one revision opportunity for each lab after the course.
    • You will have one revision opportunity for the project after the course. The advanced part and the theoretical questions cannot be revised.
    • Lab and project revisions submitted after the course will be graded when the teachers' schedules permit.

Examination rules

  • You are not allowed to copy solutions (text or code) from fellow students or the internet (e.g. github accounts).
  • You are allowed to use AI tools, but you are responsible for doing so in a responsible and scientific manner:
    • You are responsible for your own learning.
    • You must fully understand everything you submit and be able to explain it if asked.
    • You must document your use of AI tools by providing a clear and detailed explanation of how you used them to solve the task. Be prepared to submit your prompts if requested. Even if you have not used AI tools, you must include a statement confirming this. Any submission without AI usage statements will not be marked. 
    • If we suspect that you have used LLMs irresponsibly (e.g., suspected lack of understanding or misleading AI usage statement), the examiner or TAs will ask you to take an oral test or fail the particular task.