Objectives and competences
The goal of the course is for the students to understand the basics of deep networks in the field of computer vision and be able to apply them in practice.
Content (Syllabus outline)
• Introduction: definition of basic concepts
• Color and geometric transformations: color spaces and basic geometric transformations
• Convolution and linear operators: edge detectors, examples of edge detectors
• Image segmentation
• Deep neural networks and computer vision: layers, learning algorithms, transfer learning
• Training data preparation: data preprocessing and improvement (augmentation), noise removal
• Interpretation of deep models: underfitting and overfitting, evaluation of deep network models.
• Examples of applications of deep networks: classification, detection, segmentation.
Learning and teaching methods
Lectures,
Lab work.
Intended learning outcomes - knowledge and understanding
Learning outcome: identify computer vision problems, and select and use appropriate deep network models
Learning outcome: Understand the fundamental building blocks and the architecture of deep neural network models
Learning outcome: Apply deep neural network models to solve computer vision problems
Learning outcome: Reuse trained deep neural network models to solve new computer vision problems
Learning outcome: Analyze and compare solutions for computer vision problems
Readings
F. Chollet, Deep Learning with Python, druga izdaja, Manning, 2021.
E. R. Davies, Computer Vision: Principles, Algorithms, Applications, Learning, peta izdaja, Academic Press, 2017.
R. Shanmugamani, Deep Learning for Computer Vision, Packt Publishing, 2018.
Literatura v slovenskem jeziku za tematiko, ki pokriva celoten predmet ne obstaja.
