Computer Vision

Code:

M.EEC034

Acronym:

VCOMP

Keywords
Classification	Keyword
OFICIAL	Other Technical Areas

Instance: 2023/2024 - 2S

Active?	Yes
Responsible unit:	Department of Electrical and Computer Engineering
Course/CS Responsible:	Master in Electrical and Computer Engineering

Cycles of Study/Courses

Acronym	No. of Students	Study Plan	Curricular Years	Credits UCN	Credits ECTS	Contact hours	Total Time
M.EEC	36	Syllabus	1	-	6	39

Teaching language

Suitable for English-speaking students

Objectives

This course is an introduction to basic concepts and methods in computer vision. Emphasis will be put both on the essential theory and on practical examples and projects. Each exercise will be carefully chosen to reinforce concepts explained in the lectures or to develop and generalize them in significant ways.

Learning outcomes and competences

Upon the successful conclusion of the course, the student should:
- understand and be able to explain the basic concepts of computer vision and the fundamental algorithms for manipulation of images;
- have knowledge of existing methods for visual data analysis and be able to apply them in practical situations;
- acquire skills to use a library implementing some of the analyzed algorithms;
- be able to analyze and understand selected scientific papers in and computer vision.
- be able to develop simple computer vision systems according to existing needs and apply the most appropriate technological tools.

Working method

Presencial

Pre-requirements (prior knowledge) and co-requirements (common knowledge)

Knowledge of MatLab programming.

Program

1. Introduction (presentation of the concept of computer vision and relation with related scientific areas) (Week 1)
2. Human visual system; Acquisition and formation of digital, monochromatic and polychromatic, images; breif introduction to digital topology (Week 2)
3. Digital image processing: intensity transformations, linear and nonlinear filtering; Filtering in the frequency domain (Weeks 3 to 5).
4. Image segmentation (clustering-based, region-based, model-based) (weeks 6 and 7)
5. Detection and matching of points and regions of interest (edges, corners, points and regions) (Weeks 8 and 97)
6. Image analysis (digital topology, dimensional, morphological and intensity characteristics) (week 10 and 11)
7. Image recognition (weeks 12 and 13)

Mandatory literature

Rafael C. Gonzalez; Digital image processing. ISBN: 978-0-13-335672-4
Rafael C. Gonzalez; Digital image processing using Matlab. ISBN: 0-13-008519-7
Richard Szeliski; Computer vision. ISBN: 978-1-84882-935-0

Complementary Bibliography

E. R. Davies; Computer vision. ISBN: 978-0-12-809284-2
Reinhard Klette; Concise Computer Vision: An Introduction into Theory and Algorithms, Springer-Verlag, 2014

Teaching methods and learning activities

Lectures in auditorium or online; practical classes in computer labs; learning based on the resolution of practical cases and projects, autonomous work and independent study by students, group work and cooperative learning.Distributed assessment with a final exam, including a project work.

Software

MatLab

Evaluation Type

Distributed evaluation with final exam

Assessment Components

Designation	Weight (%)
Exame	60,00
Trabalho prático ou de projeto	40,00
Total:	100,00

Amount of time allocated to each course unit

Designation	Time (hours)
Elaboração de projeto	50,00
Estudo autónomo	65,00
Frequência das aulas	39,00
Trabalho escrito	6,00
Apresentação/discussão de um trabalho científico	2,00
Total:	162,00

Eligibility for exams

The components for obtaining course frequency are:
- project carried out in a group and its written report;
- oral presentation of the project.

Obtaining frequency presupposes the successful completion of the group work, including the preparation of the report and oral presentation, in addition to the legal conditions that apply.

The frequecy grade is the classification of the project, considering the aspects of execution, result achieved, division of tasks in the group, quality of the written report and of the public presentation.

Students who have not obtained a frequency grade may not take any exams in the current academic year.

Calculation formula of final grade

The frequency grade (FC) of each student is the grade obtained in the group work.

The final grade (FN) is calculated by




where Ex is the exam grade and F=min(CF, Ex+4).

Classification improvement

The frequency grade cannot be improved in the same academic year.

The improvement of the classification obtained in the first examination is carried out in the appeal examination, which focuses on the entire subject taught. The attendance grade will also be taken into account in the grade improvement period.