Checking date: 25/05/2022


Course: 2022/2023

Artificial vision
(19492)
Bachelor in Computer Science and Engineering (Plan: 489 - Estudio: 218)


Coordinating teacher: DIAZ DE MARIA, FERNANDO

Department assigned to the subject: Signal and Communications Theory Department

Type: Electives
ECTS Credits: 3.0 ECTS

Course:
Semester:




Objectives
- To know how images and video are digitally represented. - To know basic concepts of image processing with special emphasis on the operation of spatial filtering. - To know basic concepts of machine learning in the framework of neural networks: loss functions, regularization, hyperparameters, data augmentation. - To understand deep neural networks and to know the algorithms used for their training: gradient descent and back-propagation algorithms. - Understand Convolutional Neural Networks (CNN) and their most common building blocks. - Understand, design and train CNN architectures for image classification. - Understand, design and train advanced CNN-based architectures to solve other visual recognition tasks: object detection, image segmentation, image synthesis.
Skills and learning outcomes
Link to document

Description of contents: programme
1. Digital Images and Video 2. Basic concepts in image and video processing 3. Basic concepts in deep learning 4. Convolutional Neural Networks (CNNs) for image classification 5. Deep networks for other image-related tasks a. Networks for image segmentation b. Networks for object detection c. Networks for image matching d. Networks for image synthesis
Learning activities and methodology
Seminars and lectures supported by computer and audiovisual aids. Practical learning based on cases and problems, and exercise resolution. Individual and group or cooperative work with the option of oral or written presentation. Individual and group tutorials to resolve doubts and queries about the subject. Internships and directed laboratory activities.
Assessment System
  • % end-of-term-examination 0
  • % of continuous assessment (assigments, laboratory, practicals...) 100
Calendar of Continuous assessment
Basic Bibliography
  • Francois Chollet . Deep Learning with Python, Second Edition. Manning. 2021
  • Ian Goodfellow, Yoshoua Bengio, and Aaron Courville. Deep Learning. The MIT Press. 2016
  • Mohamed Elgendy. Deep Learning for Vision Systems. Manning. 2020
Additional Bibliography
  • Rafael C. González and Richard E. Woods. Digital Image Processing. Fourth Edition. Pearson. 2018
  • Wilhelm Burger and Mark J. Burge. Principles of Digital Image Processing: Fundamental Techniques. Springer-Verlag. 2009
  • Wilhelm Burger and Mark J. Burge. Principles of Digital Image Processing: Core Techniques. Springer-Verlag. 2009

The course syllabus may change due academic events or other reasons.