Vision and Image Processing (VIP)

Course content

Vision and Image Processing (VIP) gives an overview of modern vision techniques used in man and machine.  Focus is both on conceptual understanding of the models and methods, and on practical experience. The course covers state of the art methods for image analysis including how to solve visual processing tasks such as object recognition and content-based image search and retrieval.


The course is not focused on providing a deep mathematical understanding of the techniques but will include the mathematical background necessary to understand vision and image processing.


Through a number of mandatory programming exercises, the students will develop simple programs and obtain solutions to non-trivial vision tasks.  After the course, the students will be able to understand the models and principles of vision technologies used in new products and applications.

 

This course is mandatory for students enrolled in the IT and Cognition MSc study programme and is an elective course for students enrolled in the MSc programme in Computer Science. The course content does not overlap with Signal and Image Processing (MSc in Computer Science).

Education

MSc Programme in IT and Cognition

Learning outcome

Knowledge of

  • Theoretical and practical knowledge of the current research within computer vision and image analysis
  • Common application areas


Skills to

  • Read and apply the knowledge obtained by reading scientific papers
  • Convert a theoretical algorithmic description into a concrete program implementation
  • Compare computer vision and image analysis algorithms and assess their ability to solve a specific task


Competences in

  • Understanding and analyzing the main challenges in vision and image processing today
  • Describing common applications of importance to society
  • Describing and applying feature extraction methods and modelling techniques in image and vision processing
  • Analyzing the main challenges in vision and image processing today.
  • Implementation of selected methods

 

Mix of lectures and exercises

See Absalon for a list of course literature.

Basic programming and linear algebra as obtained on Scientific Programming (IT and Cognition) or as required by the BSc or MSc programme in Computer Science.

Academic qualifications equivalent to a BSc degree is recommended.

Written
Oral
Continuous feedback during the course of the semester
ECTS
7,5 ECTS
Type of assessment
Continuous assessment
Type of assessment details
Continuous assessment based on 4-6 written group- and individual assignments throughout the course, where all assignments must be passed.
Aid
All aids allowed

The use of Large Language Models (LLM)/Large Multimodal Models (LMM) – such as ChatGPT and GPT-4 – is permitted.

Marking scale
passed/not passed
Censorship form
No external censorship
Several internal examiners
Re-exam

The re-exam consists of two parts:

1. Resubmission of all assignments no later than 3 weeks before the re-exam week

2. A 20 minutes oral examination (including grading) without preparation in the re-exam week

Criteria for exam assessment

See "Learning outcome".

Single subject courses (day)

  • Category
  • Hours
  • Lectures
  • 32
  • Preparation
  • 75
  • Practical exercises
  • 16
  • Exam
  • 83
  • English
  • 206

Kursusinformation

Language
English
Course number
NDAK12002U
ECTS
7,5 ECTS
Programme level
Full Degree Master
Duration

1 block

Placement
Block 2
Schedulegroup
C
Capacity
No limitation – unless you register in the late-registration period (BSc and MSc) or as a credit or single subject student.
Studyboard
Study Board of Mathematics and Computer Science
Contracting department
  • Department of Computer Science
Contracting faculty
  • Faculty of Science
Course Coordinators
  • Serge Belongie   (10-773266697073726b6d6944686d326f7932686f)
  • Hang Yin   (4-777088784f73783d7a843d737a)
Saved on the 14-02-2024

Er du BA- eller KA-studerende?

Er du bachelor- eller kandidat-studerende, så find dette kursus i kursusbasen for studerende:

Kursusinformation for indskrevne studerende