| Code |
15644
|
| 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 |
The course aims to introduce the fundamental concepts of Computer Vision, from digital image representation to modern architectures based on deep neural networks and generative models. By the end of the course, students should be able to:
a. Understand the fundamentals of digital signals and image formation.
b. Apply feature extraction techniques and object recognition.
c. Implement convolutional neural networks and modern architectures (CNN, Vision Transformer).
d. Understand generative methods (GANs) and vision-language models (CLIP).
e. Experimentally validate Computer Vision methods.
|
|
Syllabus |
A. Digital Signals: Basic concepts of digital images; image types; analog-to-digital conversion; spatial vs frequency domain; Fourier Transform.
B. Image formation principles and camera calibration.
C. Low-level Features: Spatial and frequency filtering; Canny algorithm; corner detection (Harris), interest points (SIFT); local and global descriptors.
D. Convolutional Neural Networks: Convolutional, pooling, linear layers; activation functions; architectures (AlexNet, VGG, ResNet, MobileNet).
E. Object Detection and Object Recognition.
F. Vision Transformer: Patch encoding; Transformer encoder; classification layer.
G. Generative Adversarial Networks: GAN architecture; cost function; transposed convolutions.
H. Vision-Language Models: CLIP; architecture; learning process; zero-shot classification.
I. Modern Architectures: Foundation Models; fusion strategies; cost functions.
J. Experimental Validation: Performance evaluation and metrics.
|
|
Main Bibliography |
Gonzalez, R. C., & Woods, R. E. (2018). Digital Image Processing (4th ed.). Pearson.
Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press.
E. R. Davies. Computer Vision: Principles, Algorithms, Applications, Learning. Academic Press, 2018
Szeliski, R. (2022). Computer Vision: Algorithms and Applications
Russell, B. & Torralba, A. (2021). Computer Vision: Foundations and Applications.
|
|
Teaching Methodologies and Assessment Criteria |
Teaching methodologies:
• Theoretical classes;
• Practical laboratory classes;
• Individual projects;
• Tutoring to clarify doubts and accompany students in the development of their projects.
Assessment methods and criteria:
The theoretical and practical components are assessed using two main elements:
- a written test (T) to assess knowledge, accounting for 70% of the final grade;
- an individual practical assignment with a report on its execution and presentation, accounting for 30% of the final grade.
Teaching-Learning Classification (CEA) = 0.7T + 0.3TP
Admission to the final exam: CEA >= 6 points (UBI regulations).
|
|
Language |
Portuguese. Tutorial support is available in English.
|