ECTS credits ECTS credits: 3
ECTS Hours Rules/Memories Hours of tutorials: 1 Expository Class: 10 Interactive Classroom: 11 Total: 22
Use languages English
Type: Ordinary subject Master’s Degree RD 1393/2007 - 822/2021
Departments: Electronics and Computing
Areas: Computer Science and Artificial Intelligence, Languages and Computer Systems
Center Higher Technical Engineering School
Call: First Semester
Teaching: With teaching
Enrolment: Enrollable | 1st year (Yes)
The main objective of this compulsory subject is to set the bases that the different processes for the interpretation of images entail (image formation, preprocessing, segmentation and feature detection) so that students have the minimum knowledge necessary for the application of different techniques of AI in computer vision. In addition to the study and application of fundamental techniques, practical applications of these techniques to solve real problems will be studied. This subject provides the necessary tools to apply the algorithms used in practical cases, as well as the bases to develop new algorithms and continue with the study of more advanced methods.
Topic 1. Introduction to Computer Vision: Electromagnetic radiation, visible spectrum and vision. Short history of an interdisciplinary field.
Topic 2. Digital images: Color Space. Image sampling and quantization. Image histogram. Camera models. Geometric transformations.
Topic 3. Image Processing: Pixel-level transformations. Local transformations. Image pyramids.
Topic 4. Edge detection: First derivative and image gradients. Canny edge detector. Second derivative operator. Marr-Hildreth edge detector. Hough transform.
Topic 5. Image segmentation: histogram-based segmentation, clustering, region growing and merging. Tagging. Morphological transformations.
Topic 6. Feature descriptors. Invariant measures. SIFT (Scale Invariant Feature Transform).
Topic 7. Image matching: corner detector, blob detector, matching algorithms.
Basic bibliography:
-Richard Szeliski. Computer Vision: Algorithms and Applications. ISBN: 978-3030343712.
Complementary bibliography:
-Gonzalez & Woods. Digital image processing. ISBN: 0-20-118075-8.
-D.A. Forsyth y J. Ponce. Computer Vision. ISBN 0-13-085198-1.
-Steger & Wiedemann. Machine Vision Algorithms and Applicacions. ISBN 978-3-527-4073.
-Basic:
CB6 - Possess and understand knowledge that provides a basis or opportunity to be original in the development and/or application of ideas, often in a research context.
CB7 - That the students know how to apply the knowledge acquired and their ability to solve problems in new or little-known environments within broader (or multidisciplinary) contexts related to their area of study.
CB10 - That the students have the learning skills that allow them to continue studying in a way that will be largely self-directed or autonomous.
-General:
CG1 - Maintain and extend grounded theoretical approaches to allow the introduction and exploitation of new and advanced technologies in the field of Artificial Intelligence.
CG3 - Search and select the useful information necessary to solve complex problems, handling the bibliographic sources of the field with ease.
CG5 - Work in a team, especially of a multidisciplinary nature, and be skillful in managing time, people and decision-making.
-Transversal:
CT3 - Use the basic tools of information and communication technologies (ICT) necessary for the exercise of their profession and for lifelong learning.
CT4 - Develop oneself for the exercise of a respectful citizenship with the democratic culture, human rights and the gender perspective.
CT8 - Assess the importance of research, innovation and technological development in the socioeconomic and cultural progress of society.
-Specific:
CE23.- Understanding and command of the basic concepts and techniques of digital image processing.
CE24.- Ability to apply different techniques to computer vision problems.
CE25.- Knowledge and skills to design systems for detection, classification and tracking of objects in images and video.
CE26.- Understanding and command of the forms of representation of signals and images based on their data, as well as their fundamental characteristics and their forms of representation.
-Master class: the teacher presents a topic to the students with the aim of providing a set of information with a specific scope.
-Laboratory practices: the teaching staff of the subject poses to the students a problem or problems of a practical nature whose resolution requires the understanding and application of the theoretical-practical contents included in the contents of the subject.
-Project-based learning: students are presented with practical projects whose scope requires that an important part of the total dedication of the student be devoted to the subject. In addition, due to the scope of the work to be carried out, it is required not only that the students apply management skills but also technical skills.
-Autonomous work: the teacher proposes to the students a job whose scope and objectives require that it be worked by the students autonomously, although with the tutelage of the teaching staff of the subject. In general, it is applied to jobs with a time scope and greater effort than laboratory practices.
-Tutorials: the teaching staff will assist the students in individualized tutorial sessions dedicated to orientation in the study and the resolution of doubts about the contents and work of the subject.
Competences CE23, CE24, CE25 and CE26 have associated specific theoretical and practical contents, which will be evaluated explicitly throughout the course.
The work of the competences CG1, CG3, CG5, CB6, CB7 and CB10 is carried out mainly through the analysis and the group discussion of the works of the state of the art.
Competences CT3, CT4, CT8 are worked on especially in group projects.
The evaluation of the students will serve to evaluate the effectiveness of the teaching methodologies developed in fulfillment of the objectives of the subject.
The assessment of the subject consists of two parts:
· 40%: The part related to the presentation of the master sessions will be evaluated through written tests which will evaluate the adequacy of the proposed solutions to the problems, the quality of the results obtained, and the understanding of the techniques used.
· 60%: Continuous evaluation of laboratory practices and/or resolution of practical cases. The adequacy of the proposed solutions to the problems, the quality of the results obtained, and the understanding of the techniques used will be evaluated.
All assignment and test marks in first chance will be kept until the second chance. Then the students could repeat all or part of the assessment activities. The final grade will be the computed based on the maxima of marks between the corresponding activities in both opportunities.
A student will receive the grade of Absent if they do not hand in any assessment exercise, nor take any exam of the two opportunities.
For cases of fraudulent performance of exercises or tests, the provisions of the Regulations for the evaluation of students' academic performance and the review of qualifications will apply.
In application of the ETSE Regulation on plagiarism (approved by the ETSE Board on 12/19/2019) the total or partial copy of any exercise of practice or theory will suppose a fail in both occasions of the course, with a qualification of 0,0 in both cases.
This subject has 3 ECTS, adding up to a total workload of 75 hours, distributed as follows:.
FACE-TO-FACE WORK IN THE CLASSROOM:
* Master classes: 10 hours
* Laboratory practices: 7 hours
* Case studies and project: 4 hours
Total hours of classroom work: 21 hours
STUDENT PERSONAL WORK:
* Autonomous study: 10 hours
* Laboratory practices: 21 hours
Total hours of personal work: 54 hours
Daily work is recommended for the study of theory, practical work and problem-solving. We also consider important to make use of mentoring for discussion of practical problems and as a means of immediate resolution of doubts.
Classes will be conducted in English and we will do an intensive use of the virtual classroom.
Maria Jose Carreira Nouche
- Department
- Electronics and Computing
- Area
- Computer Science and Artificial Intelligence
- Phone
- 881816431
- mariajose.carreira [at] usc.es
- Category
- Professor: University Lecturer
Xosé Manuel Pardo López
Coordinador/a- Department
- Electronics and Computing
- Area
- Languages and Computer Systems
- Phone
- 881816438
- xose.pardo [at] usc.es
- Category
- Professor: University Lecturer
Marta Nuñez Garcia
- Department
- Electronics and Computing
- Area
- Computer Science and Artificial Intelligence
- martanunez.garcia [at] usc.es
- Category
- Investigador/a Distinguido/a
| Tuesday | |||
|---|---|---|---|
| 15:30-17:00 | Grupo /CLE_01 | English | IA.02 |
| Wednesday | |||
| 15:30-17:00 | Grupo /CLIL_01 | English | IA.02 |
| 01.15.2025 16:00-20:00 | Grupo /CLE_01 | IA.02 |
| 01.15.2025 16:00-20:00 | Grupo /CLIL_01 | IA.02 |
| 06.25.2025 16:00-20:00 | Grupo /CLIL_01 | IA.02 |
| 06.25.2025 16:00-20:00 | Grupo /CLE_01 | IA.02 |