2023-2024 / ELEN0016-2

Computer vision

Duration

30h Th, 10h Pr, 50h Proj.

Number of credits

 Master of Science (MSc) in Biomedical Engineering5 crédits 
 Master of Science (MSc) in Data Science5 crédits 
 Master of Science (MSc) in Electrical Engineering5 crédits 
 Master of Science (MSc) in Computer Science and Engineering5 crédits 
 Master of Science (MSc) in Computer Science and Engineering (double degree programme with HEC)5 crédits 
 Master of Science (MSc) in Data Science and Engineering5 crédits 
 Master of Science (MSc) in Computer Science5 crédits 
 Master of Science (MSc) in Computer Science (joint-degree programme with HEC)5 crédits 

Lecturer

Marc Van Droogenbroeck

Language(s) of instruction

English language

Organisation and examination

Teaching in the first semester, review in January

Schedule

Schedule online

Units courses prerequisite and corequisite

Prerequisite or corequisite units are presented within each program

Learning unit contents

Contents (note that it can be adapted depending on the nature of the project): introduction, linear filtering and deconvolution, mathematical morphology, non-linear filtering, features extraction and border detection, texture, enhancement and restoration, shape analysis, image segmentation, motion detection, aspects of 3D vision, machine learning, pattern recognition, deep learning

Learning outcomes of the learning unit

This course introduces to the major techniques used in computer vision. Theoretical and practical aspects of image processing are discussed in details, with a focus on industrial applications.

At the end of the course, students will be able to:

  • master the notion of an image;
  • understand the major vision processing techniques;
  • design a complete video processing chain with a practical aim.
Exercise sessions, laboratory sessions and a large homework will help the students in developing more general skills like the capacity to evaluate tools, the conception of complete chain from the specifications to the realization, and team working.

This course contributes to the learning outcomes I.1, I.2, II.1, II.2, II.3, III.2, III.3, III.4, IV.1, IV.2, VI.1, VI.2, VII.1, VII.2, VII.3, VII.4, VII.5 of the MSc in biomedical engineering.
This course contributes to the learning outcomes I.1, I.2, I.3, II.1, II.2, II.3, III.2, III.3, III.4, IV.1, IV.2, IV.3, VI.1, VI.2, VII.1, VII.2, VII.3, VII.4, VII.5 of the MSc in data science and engineering.
This course contributes to the learning outcomes I.1, I.2, II.1, II.2, II.3, III.2, III.3, III.4, IV.1, IV.2, IV.8, VI.1, VI.2, VII.1, VII.2, VII.3, VII.4, VII.5 of the MSc in electrical engineering.
This course contributes to the learning outcomes I.1, I.2, II.1, II.2, II.3, III.2, III.3, III.4, IV.1, IV.2, VI.1, VI.2, VII.1, VII.2, VII.3, VII.4, VII.5 of the MSc in computer science and engineering.

Prerequisite knowledge and skills

  • The student shall have passed a course on advanced programming.
  • The student shall be familiar with signal processing concepts.

Planned learning activities and teaching methods

Face-to-face (no streaming, no podcasts)

  • exercise sessions
  • computer simulations
  • a large project (which is compulsory) consisting in a software implementation of computer vision techniques applied to a real situation. The project is usually divided in sub-tasks.

Mode of delivery (face to face, distance learning, hybrid learning)

Face-to-face course


Additional information:

It includes a lecture on theory and training session per week. The project must be delivered by the end of the first semester.

Recommended or required readings

Slides : http://orbi.ulg.ac.be/handle/2268/184667

Exam(s) in session

Any session

- In-person

written exam ( open-ended questions )

Written work / report


Additional information:

Written exam during the exam session (compulsory).
The exam is written and includes questions of theoretical nature and on the exercises. The exam is closed-book.

Homework (compulsory).
This work must imperatively be given during the penultimate week of course of the first semester. Failure to achieve the required activities during the year will result in denying the possibility to pass the exam (1st AND 2d sessions!). There is no possibility to acheive the work during another semester than the one of the course; there is no second chance for the work!.

Important note !

If the project comprises several sub-tasks, failing to deliver the result of a sub-task means that this task AND all the following ones will be granted a note of 0 !

Final note computation weights:



  • January: project = 2/3, written exam = 1/3
  • August: project (partial note identical to that of January) = 1/2, written exam = 1/2

Work placement(s)

Organisational remarks and main changes to the course

Please note that the course is taught in english!

Contacts

Teacher : M. Van Droogenbroeck (04/366 26 93) Secretary : 04/ 366 26 91 Assistant : Renaud Vandeghen

Association of one or more MOOCs