Advanced image processing and analysis

Code:

MVCOMP08

Acronym:

PAIA

Keywords
Classification	Keyword
CNAEF	Informatics Sciences

Instance: 2023/2024 - 2S

Active?	Yes
Responsible unit:	Department of Informatics Engineering
Course/CS Responsible:	Master in Computer Vision

Cycles of Study/Courses

Acronym	No. of Students	Study Plan	Curricular Years	Credits UCN	Credits ECTS	Contact hours	Total Time
MVCOMP	10	Syllabus	1	-	6	42	162

Teaching language

English

Objectives

• Study and application of advanced digital image processing techniques.


• Study and application of advanced techniques of digital image analysis.


• Analysis of real problems and design and development of solutions based on advanced image processing and analysis technologies.


• Evaluation of the adequacy of the methodologies applied to specific problems.

Learning outcomes and competences

Working method

Presencial

Program

- Advanced image processing techniques. Advanced denoising. Total variation.
Advanced edge detection (e.g. bilateral filter, anisotropic diffusion, phase congruence).
- Advanced segmentation (deformable models, level-set methods, Markov Random Fields, graph cuts, dynamic programming, etc.).
Learning-based segmentation (active shape/appearance models).
- Salience and attention models.
- Selected topics on advanced image processing and analysis (detection, semantic segmentation, multi-view enhancement, superresolution, inpainting, colouring, photo stitching, background removal, etc.).
- Advanced applications of image processing and analysis.

Mandatory literature

Richard Szeliski; Computer vision. ISBN: 978-1-84882-935-0

Complementary Bibliography

Adrian Kaehler; Learning OpenCV 3. ISBN: 978-1-491-93799-0
David A. Forsyth; Computer vision. ISBN: 0-13-085198-1

Teaching methods and learning activities

The teaching-learning process will be based on a theoretical-practical. There will be a presentation and discussion of the course topics and resolution of exercises using learning based on the analysis and resolution of practical cases. Additionally, individual projects will be developed where the studied computer vision methods will be applied.

Evaluation Type

Distributed evaluation without final exam

Assessment Components

Designation	Weight (%)
Teste	20,00
Trabalho prático ou de projeto	80,00
Total:	100,00

Amount of time allocated to each course unit

Designation	Time (hours)
Elaboração de projeto	50,00
Estudo autónomo	70,00
Frequência das aulas	42,00
Total:	162,00

Eligibility for exams

Obtain a minimum of 50% in the distributed evaluation classification

Calculation formula of final grade

Final Classification = PR * 0.8 + T * 0.2

PR - projects
T - written tests