Introductory course on Computer Vision (CV) to provide the theoretical and practical foundations of this discipline, with a particular focus on the use of neural networks and convolutional architectures (CNN).
CONTENT
Introduction to Computer Vision:
• Neural Networks.
• Loss function and training.
Computer Vision:
• CV tasks.
• Feature extraction.
Convolutional Neural Networks:
• Architecture.
• Convolutional layers.
• Activation function and hyperparameters.
Exercises:
• Object recognition with YOLO.
• Training with custom datasets.
OBJECTIVES
The aim of the course is to provide a solid introductory knowledge of Computer Vision, enabling students to understand the principles governing neural networks and CNNs.
LEARNING OUTCOMES
Students will be able to describe the main tasks of Computer Vision (classification, object detection, segmentation, etc.), understand the functioning of neural networks, the training process, and the backpropagation algorithm. Finally, they will acquire the skills to use modern tools for object recognition and will be able to apply these tools in solving practical problems, integrating theory and practice.
PREREQUISITES
Experience in Python programming.