Required in stage
First term
Second term
Both terms
This year
Next year
Alternating years
External
Prerequisites
Taught by
Language of instruction
Duration
LevelComputer Vision (B-KUL-H02A5A)
Cannot be taken as part of an examination contractAims
Computer vision or Image understanding is the 'art' of developing computerized procedures to extract relevant numerical and symbolic information from images. Not backed up by a single theory, we will try to provide the attendees a structured overview of, and guidelines for, computer vision or image understanding strategies.
Previous knowledge
Basic programming experience. Some mathematical background.
Course material
Articles and literature
Slides, transparencies, courseware
Toledo / e-platform
Is also included in other courses
- Master in de toegepaste informatica (Multimedia) 60 ects.
-
Master in de toegepaste economische wetenschappen: handelsingenieur in de beleidsinformatica
120 ects.
-
Master in de ingenieurswetenschappen: wiskundige ingenieurstechnieken
120 ects.
-
Master in de ingenieurswetenschappen: biomedische technologie
120 ects.
-
Master of Artificial Intelligence
60 ects.
- Master in de informatica (uitdovend, enkel 2e fase) (Specialisation: Artificial Intelligence) 120 ects.
- Master in de informatica (uitdovend, enkel 2e fase) (Specialisation: Multimedia) 120 ects.
- Master in de ingenieurswetenschappen: computerwetenschappen (Specialisation: Artificial Intelligence) 120 ects.
- Master in de ingenieurswetenschappen: computerwetenschappen (Specialisation: Man Machine Communication) 120 ects.
-
Master of Engineering: Biomedical Engineering
120 ects.
Activities
1.5 ects. Computer Vision: Lecture (B-KUL-H02A5a)
Content
The course is subdivided in two parts:
1.Digital image processing (prerequisites for image understanding algorithms)
- Introduction: basic concepts and applications
- Statistical operations (point operations such as histogram transformations, contrast enhancement, algebraic operations, geometric operations, ...)
- Spatial operations (filtering, edge enhancement, noise suppression, ...)
- Low-level image segmentation (region growing/merging, edge linking, ...)
2. Computational strategies for object recognition
- Introduction
- Feature vector classification (statistical pattern recognition, neural nets for object recognition)
- Fitting models to photometry
- Fitting models to symbolic structures
- Combined strategies..
Evaluation
Evaluation : Computer Vision (B-KUL-H22A5a)
Explanation
Project work: report and presentation, including additional questions related to the concepts presented in the course that might be useful as alternative strategies for solving the object recognition project work.
