Educational guide
IDENTIFYING DATA 2024_25
Subject MACHINE VISION Code 00717028
Study programme
0717 - GRADO INGENIERÍA DATOS INTELIGENCIA ARTIFICIAL
Descriptors Credit. Type Year Period
6 Compulsory Third Second
Language
Castellano
Prerequisites
Department ING.ELECTR.DE SIST. Y AUTOMATI
Coordinador
FIDALGO FERNANDEZ , EDUARDO
E-mail efidf@unileon.es
ealeg@unileon.es
Lecturers
ALEGRE GUTIÉRREZ , ENRIQUE
FIDALGO FERNANDEZ , EDUARDO
Web http://agora.unileon.es
General description
Tribunales de Revisión
Tribunal titular
Cargo Departamento Profesor
Presidente ING.ELECTR.DE SIST. Y AUTOMATI ALAIZ RODRIGUEZ , ROCIO
Secretario ING.ELECTR.DE SIST. Y AUTOMATI PEREZ LOPEZ , DANIEL
Vocal ING.ELECTR.DE SIST. Y AUTOMATI DIEZ DIEZ , ANGELA
Tribunal suplente
Cargo Departamento Profesor
Presidente ING.ELECTR.DE SIST. Y AUTOMATI ALAIZ MORETON , HECTOR
Secretario ING.ELECTR.DE SIST. Y AUTOMATI FOCES MORAN , JOSE MARIA
Vocal ING.ELECTR.DE SIST. Y AUTOMATI RIESCO PELAEZ , FELIX

Competencias
Code  
A18976
B5800
B5802
B5806
B5807
B5809
C2 CMECES2 That students know how to apply their knowledge to their work or vocation in a professional manner and possess the skills that are usually demonstrated through the development and defense of arguments and the resolution of problems within their area of study.
C4 CMECES4 That students can transmit information, ideas, problems and solutions to both a specialised and non-specialised audience
C5 CMECES5 That students have developed those learning skills necessary to undertake further studies with a high degree of autonomy

Learning aims
Competences
Know and apply the concepts, methodologies and technologies of image and video processing in different formats A18976
 B5800
 C2
C4
Master the main operations of preprocessing, segmentation and description of images and objects in images A18976
 B5800
 C2
C4
Knows and knows how to apply techniques and models that allow the classification of images or videos or the recognition and recovery of objects present in images. B5802
B5806
B5807
 C2
Analyzes, synthesizes and solves problems related to Artificial Vision A18976
 B5800
B5806
B5807
 C2
C5
Correctly transmits information, ideas, problems and solutions. A18976
 B5809
 C4

Contents
Topic Sub-topic
1. Introduction to Computer Vision
2. Steps in Computer Vision.
3. Convolutional Neural Networks
4. Modelos secuenciales para Computer Vision
5. Object Detection & Recognition
6. Image segmentation
7. Unsupervised and Self-supervised learning models
8. Generative models
9. Vision and Language Models

Planning
Methodologies  ::  Tests
  Class hours Hours outside the classroom Total hours
Problem solving, classroom exercises 4 2 6
 
Presentations / expositions 4 16 20
Practicals using information and communication technologies (ICTs) in computer rooms 26 26 52
Assignments 6 18 24
0 8 8
 
Lecture 20 20 40
 
 
(*)The information in the planning table is for guidance only and does not take into account the heterogeneity of the students.

Methodologies
Methodologies   ::  
  Description
Problem solving, classroom exercises Carrying out exercises using various media such as a tablet, blackboard or also through slides and examples using Excel. You can also leave exercises in Agora, with solutions, most of the time also with examples solved in Excel.
Presentations / expositions Los estudiantes explicarán durante las clases el proyecto realizado utilizando una presentación preparada previamente siguiendo las indicaciones proporcionadas por el profesor.
Practicals using information and communication technologies (ICTs) in computer rooms The subject practices will be carried out using Python (3.X). Available in the F3 laboratory although it is recommended that each student also install it on their personal computer. It is recommended to use Python 3.X starting with the installation of the Anaconda environment (https://www.anaconda.com/). Preferably, the Spyder IDE, included in said installation, will be used. The practices will be carried out following the scripts left in Agora. Doubts will be resolved by consulting the teacher. Your solution will be delivered in a task enabled for this in Agora.
Assignments The student will carry out a project during the course that will be based on the theoretical content explained in the classes and will be able to take advantage of some of the practices carried out in the laboratory.
The student will be proposed to take online courses, typically on MOOC platforms, of very short duration to reinforce completing the training received.
Lecture Theoretical sessions in the classroom using slides. Presentations or documents corresponding to the materials for each lesson can also be left on Agora. The lessons may be accompanied by videos related to the concepts presented, some recorded by the teachers and others coming from Internet resources that the teachers consider especially appropriate. Some lessons will be accompanied by a questionnaire with questions, which may be both theoretical and practical, whose deliveries will be evaluable. Courses from the Datacamp platform, or similar courses, will likely be used to reinforce some lessons taught, with some courses being optional and others mandatory.

Personalized attention
 
Problem solving, classroom exercises
Presentations / expositions
Practicals using information and communication technologies (ICTs) in computer rooms
Assignments
Lecture
Description
Questions to the teacher can be asked online or in person.
Online queries will be made by email, using a general doubt forum or, alternatively, the forums enabled for each specific activity.
For face-to-face tutorials, an appointment must be made by email or through the forum enabled for this purpose in Ágora.
Face-to-face tutoring hours may also be done by videoconference.

Assessment
  Description Qualification
Practicals using information and communication technologies (ICTs) in computer rooms The delivery of the practices that are indicated as mandatory, as well as the complementary activities indicated as mandatory, will be valued with 10% of the total grade. 10
Assignments The student will carry out a project during the subject that will be evaluated through the deliveries and presentations made and their corresponding written validation exams. It is mandatory to complete the project and pass its evaluation to pass the course. This project will have a value of 30% of the course grade and will be valued both through presentations and written validation exams. Of that 30%, 15% corresponds to the grade of the presentations and the other 15% to the grade of the validation exam or exams. 30
Algunas prácticas y otras actividades que se indiquen tendrán carácter voluntario y tendrán un valor del 10% de la nota del curso. Podrá superarse el curso sin entregar ninguna de las actividades voluntarias aunque no se obtendrá la nota correspondiente a la realización de las mismas. 10
Lecture Los contenidos impartidos en las clases teóricas, tanto conceptos teóricos como ejercicios, se valorarán mediante exámenes escritos suponiendo dichos exámenes el 50% de la nota del curso. 50
 
Other comments and second call

You may pass the course without submitting any of the voluntary activities, although you will not obtain the corresponding grade for completing them.

To pass the course it is necessary to obtain 50% of the maximum grade for all mandatory activities, which are all those indicated above except the activities indicated as voluntary.

The conditions to pass the course in the second call are the same as in the first call.

Sources of information
Access to Recommended Bibliography in the Catalog ULE

Basic
  • Aston Zhang, Zachary C. Lipton, Mu Li and Alexander J. Smola, (2023). Dive into Deep Learning. Cambridge University Press.
  • Mohamed Elgendy. (2020). Deep Learning for Vision Systems. Manning Publications.
  • V. Kishore Ayyadevara, Yeshwanth Reddy. (2020). Modern Computer Vision with PyTorch. Packt Publishing.
  • Chollet, F. (2022). Deep learning with Python. 2nd Edition. Manning Publications.
  • Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning (Adaptive Computation and Machine Learning series) (Illustrated Edition). MIT Press.
Complementary
  • Szeliski, R. (2010). Computer Vision: Algorithms And Applications. Springer.
  • Davies, E. R. (2012). Computer Vision: Principles, Algorithms, Applications, Learning. Springer.

Recommendations


Subjects that it is recommended to have taken before
LINEAR ALGEBRA II / 00717011
MATHEMATICAL MODELLING I / 00717013
MACHINE LEARNING / 00717014
ADVANCED MACHINE LEARNING / 00717019