ITF31719 Image Processing (Spring 2025)

The course is connected to the following study programs

Compulsory course in

• Bachelor in Computer Science - Machine Learning

Elective course in other study programmes.

Recommended requirements

This course requires prerequisite knowledge in:

• mathematics equivalent to the course in Mathematics for Computer Science / Discrete Mathematics

• mathematics equivalent to the course in Mathematics 1 / Calculus

• programming equivalent to the course in Object-oriented Programming / Programming 2

Lecture Semester

6th semester (Spring).

The student's learning outcomes after completing the course

Knowledge

The student

• understands digital images and their properties

• is familiar with representation methods for digital images, including image coding and compression

• understands how images can be filtered/processed for better quality

• understands the principles and methods in basic pattern recognition

Skills

The student can

• use standard filters to filter noise

• use standard filters to enhance the details in an image

• use standard techniques to detect edges, corners and objects in an image

• write programs for basic image processing and pattern recognition

• get a computer and/or computer system to recognize objects in an image

Content

Representation methods for digital images, filtering, noise reduction, use of filters, detail enhancement, edge detection, image transformations, handcrafted feature extraction techniques. Basics of Artificial Neural Networks, Support Vector Machines, Principle Component Analysis and Deep Learning. 

Forms of teaching and learning

Lectures, exercises and lab assignments/projects.

If students from international partners attend courses, the lectures will be conducted in English.

Workload

Approx. 250 hours.

4 hours of lectures per week, in addition to study groups and project work.

Examination

Individual portfolio assignment

2 assignments and 1 portfolio project  must be submitted by given deadlines and in accordance with specifications given by the course instructor.

An individual grade will be awarded on the basis of assessment of the two assignments (in total 50%) and the  portfolio project (50%) as a whole. 

Grading scale from A to F are used.

Examiners

One external and one internal examiner, or two internal examiners will be involved in the assessment.

Conditions for resit/rescheduled exams

In the event of a resit or rescheduled examination, all parts of the portfolio must be re-submitted.

New and postponed exams are conducted simultaneously with the next regular exam. The department management may decide to arrange a postponed exam in the following semester for students with valid absence from the regular exam.

Course evaluation

This course is evaluated by a

• End-of-term evaluation (compulsory)

The responsible for the course compiles a report based on the feedback from the students and his/her own experience with the course. The report is discussed by the study quality committee of the faculty of Computer Sciences.

Literature

The current reading list for 2024 Spring can be found in Leganto