Go to:
Logótipo
You are here: Start > PRODEF037

Image Analysis and Recognition

Code: PRODEF037     Acronym: RAI

Keywords
Classification Keyword
OFICIAL Electrical and Computer Engineering

Instance: 2022/2023 - 1S

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

Cycles of Study/Courses

Acronym No. of Students Study Plan Curricular Years Credits UCN Credits ECTS Contact hours Total Time
PRODEF 3 Syllabus since 2009/2010 1 - 6 28 162

Teaching language

Portuguese and english

Objectives

This curricular unit aims to give the students the ability to understand and apply some of the most recent advances in this rapid evolving field of Image Analysis and Recognition. This CU is based on a recommended textbook along with a list of selected original research papers in order to allow the students to follow the advances in the addressed topics. The main topics covered will allow the students to develop abilities and skills in: image segmentation, tracking, image registration, and object and pattern recognition and matching. The CU focuses on the use of the methods and techniques with potential for applications, such as visual inspection, document processing, biometrics and biomedical images.

 

Learning outcomes and competences

Skills to acquire: develop abilities and skills in image segmentation, tracking, image registration, and object and pattern recognition and matching.

Working method

Presencial

Program

1. Image Enhancement
2. From color to edges and textures
3. Segmentation
a. Clustering methods. Embedding local constrains. Mean Shift
b. Graphtheoretic clustering. Affinity measures. Graph Cuts. 4. Motion analysis
a. Background subtraction
b. Optical flow
c. Tracking using linear and nonlinear dynamical models.
5. Image Registration
a. Multi view geometry.
b. Strategies for image registration of rigid and nonrigid

objects.
c. Local invariant features and similarity measures.
6. Image Recognition a. Machine learning tools
b. Feature extraction and selection: i. Principal Component analysis. ii. Object and shape representation using invariant features.
c. Object modeling i. Active appearance models. ii. Constellation model and the Implicit Shape Model. iii. Bag of

visual term models.
d. Recognition examples

Mandatory literature

David A. Forsyth, Jean Ponce; Computer Vision: A Modern Approach. ISBN: 978-0136085928

Teaching methods and learning activities

This curricular unit is organized in lectures, which include oral presentations and computer vision labs under supervised tutoring.

Distributed evaluation with final examination. (Formula for calculating the final grade: Grading and evaluation is based on the following scheme: Practical assignments: 60% (15% for each one of the 4 assignments).

Presentation of a selected research paper: (10%), Final examination: 30%. Grading will be from 0 to 20. A final passing grade in the CU corresponds to a minimum of 10.

Evaluation Type

Distributed evaluation with final exam

Assessment Components

Designation Weight (%)
Apresentação/discussão de um trabalho científico 10,00
Exame 30,00
Trabalho prático ou de projeto 60,00
Total: 100,00

Amount of time allocated to each course unit

Designation Time (hours)
Apresentação/discussão de um trabalho científico 16,00
Estudo autónomo 32,00
Trabalho escrito 97,00
Frequência das aulas 17,00
Total: 162,00

Eligibility for exams

Does not apply

Calculation formula of final grade

Grading and evaluation is based on the following scheme: Practical assignments: 60% (15% for each one of the 4 assignments).

Presentation of a selected research paper: (10%)

Final examination: 30%

Grading will be from 0 to 20. A final passing grade in the CU corresponds to a minimum of 10.
Recommend this page Top
Copyright 1996-2024 © Faculdade de Engenharia da Universidade do Porto  I Terms and Conditions  I Accessibility  I Index A-Z  I Guest Book
Page generated on: 2024-07-27 at 13:34:51 | Acceptable Use Policy | Data Protection Policy | Complaint Portal