Teaching plan for the course unit



Close imatge de maquetació




On 3 April 2020 and in agreement with the President of the Government of Catalonia, the Catalan Minister of Business and Knowledge and the rectors of the other Catalan universities, the Rector of the Universitat de Barcelona decided to suspend all second-semester face-to-face teaching activities until the end of the academic year. For this reason, our university's teaching staff may need to make certain changes to the course plans of the subjects they teach, so that they can teach subjects online. When and where such changes are made, they will be explained in a new appendix attached to the end of the original course plan.

General information


Course unit name: Computer Vision

Course unit code: 572674

Academic year: 2019-2020

Coordinator: Sergio Escalera Guerrero

Department: Department of Mathematics and Computer Science

Credits: 3

Single program: S



Estimated learning time

Total number of hours 75


Face-to-face and/or online activities



-  Lecture with practical component





-  Document study






Competences to be gained during study


CE6 - That students can apply in an effective way analytics and predictive machine learning tools


CE7 - That students can understand, develop, and update analytics and exploratory algorithms to work with data





Learning objectives


Referring to knowledge

Know the basics of image processing


Be able to extract discriminative features from images


Learn pattern recognition methods from image features


Know the state of the art methodologies to segment and recognize objects in images


Know the basics of text analysis in images


Know the basics of affective computing from a computer vision perspective


Know the basic on human behavior analysis



Teaching blocks


1. Introduction to computer vision

*  Introduction to computer vision

2. Image processing principles

*  Image processing principles

3. High level features

*  High level features

4. Object recognition

*  Object recognition

5. Multiclass and multilabel recognition

*  Multiclass and multilabel recognition

6. Image segmentation

*  Image segmentation

7. Image retrieval

*  Image retrieval

8. Text detection and analysis

*  Text detection and analysis

9. Scene understanding and captioning

*  Scene understanding and captioning

10. Face analysis and affective computing

*  Face analysis and affective computing

11. Behaviour analysis

*  Behaviour analysis



Teaching methods and general organization


Oral presentation of the content in combination with practical sesions associated to the different lectures of the course.



Official assessment of learning outcomes


50% of the final score: reports and code associated to the different practical sessions of the course

50% of the final score: final course exam


Examination-based assessment

50% of the final score: reports and code associated to the different practical sessions of the course

50% of the final score: final course exam



Reading and study resources

Consulteu la disponibilitat a CERCABIB


Goodfellow, Ian ; Bengio, Yoshua ; Courville, Aaron. Deep learning book. MIT  Enllaç

Edició electrònica d’accés lliure  Enllaç

Russ, John C. ; Brent Neal, F. The image processing handbook. Boca Raton : CRC Press, 2016.  Enllaç


Corneanu, Ciprian A. ; Oliu, Marc ; Cohn, Jeffrey F. ; Escalera, Sergio. Survey on RGB, 3D, Thermal, and Multimodal Approaches for Facial Expression Recognition: History, Trends, and Affect-related Applications. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 38, n. 82016.

Accés consorciat per als usuaris de la UB  Enllaç

Web page

Conference on Computr Vision and Pattern Recognizion (CVPR) 2016

http://cvpr2016.thecvf.com/program/main_conference  Enllaç





Because of COVID-19, some course adaptations needed to be done.

- Original course plan in terms of main content has been kept. In order to allow for this, audio-visual material of the theoretical sessions has been provided as multimedia material to the campusvirtual of the course.

- In order to perform evaluation of the student presentation tasks, this has been addressed as a multimedia task delivery work via the campusvirtual of the course.

- In order to keep the evaluation criteria for the course, in addition to the delivered presentation as a task at campusvirtual, the final exam is performed as a short questionnaire using campusvirtual features.