| Code |
14476
|
| Year |
1
|
| Semester |
S2
|
| ECTS Credits |
6
|
| Workload |
PL(30H)/T(30H)
|
| Scientific area |
Informatics
|
|
Entry requirements |
Notions of structured programming. Block, iterative and conditional blocks. Notions of artificial intelligence. Elementary notions of: linear algebra, probability and statistics, geometry.
|
|
Mode of delivery |
Face-to-face.
|
|
Work placements |
(Not applicable)
|
|
Learning outcomes |
Study of mechanisms of biological vision and its relationship to computational vision systems. Understanding of the main concepts about vision systems. Dynamics of the acquired information and noise handling. Understanding of the main techniques for detection, segmentation and classification of objects in images.
By the end of this course, students should be able to identify the requisites for computer vision systems. Identify techniques for image processing and vision, most suitable for specific problems.
Planning and implement solutions for computer vision systems.
|
|
Syllabus |
Introduction. Computer Vision (CV). What is it? Applications of CV. Biologic Perspective Vision. Cameras and Images. Optics. Digital Images. Sampling. Calibration. Filtering. Convolution, Correlation. Spatial and Frequency Domains. Fourier Transform. Noise Sources. Image Representation: features. Data Descriptors: Color, intensity, texture and shape. Detection, Segmentation and Recognition
|
|
Main Bibliography |
Main
David A. Forsyth and Jean Ponce; Computer Vision: A Modern Approach, Prentice-Hall, 2002.
Dana Ballard and Chris Brown; Computer Vision, Online.
J. R. Parker; Algorithms for Image Processing and Computer Vision, Wiley, 1995.
Complementary
Torras, C.; Computer Vision, Theory and Industrial Applications, New York, Springer, 1992.
Davies, E.R.; Machine Vision: Theory, Algorithms, Practicalities, Third Edition, Morgan Kaufmann, 2005.
On-line resources: http://homepages.inf.ed.ac.uk/rbf/CVonline/books.htm#online
|
|
Teaching Methodologies and Assessment Criteria |
Assidui
A aprovação à disciplina está condicionada a níveis mínimos de assiduidade de 80% nas aulas.
Trabalho Prático (P)
Os trabalhos práticos da disciplina contribuem em 10 valores para a classificação final.
A aprovação à disciplina requer a nota mínima de 5 valores no trabalho prático.
Parte 1: OCR Dataset (2 valores): 18 de Março de 2021, 23:59, via email.
Parte 2: GTSRB Dataset Classification (2 valores): 8 de Abril de 2021, 23:59, via email.
Parte 3: GTSRB Dataset Detection (3 valores): 6 de Maio de 2021, 23:59, via email.
Parte 4: Reinforcement Learning (3 valores): 31 de Maio de 2021, 23:59, via email.
A obtenção de classificação nos trabalhos práticos está condicionada à apresentação/discussão individual de cada aluno com o docente.
Frequência
Prova (F1) - 5ª feira, 20 de maio de 2021, 14:00-16:00, Sala 6.18
Classificação Ensino/Aprendizagem (C)
C=P*10/20+F*10/20
Admissão a Exame
Consideram-se admitidos a Exame os alunos que obtiverem classificação mínima de 6 valor
|
|
Language |
Portuguese. Tutorial support is available in English.
|