Educational guide
IDENTIFYING DATA 2023_24
Subject COMPUTER VISION AND LEARNING Code 00715007
Study programme
0715 - MASTER UNIV. INGENIERIA INFORMATICA
Descriptors Credit. Type Year Period
4.5 Compulsory First Second
Language
Ingles
Prerequisites
Department ING.ELECTR.DE SIST. Y AUTOMATI
Coordinador
FIDALGO FERNANDEZ , EDUARDO
E-mail efidf@unileon.es
ralar@unileon.es
ealeg@unileon.es
vgonc@unileon.es
Lecturers
ALAIZ RODRÍGUEZ , ROCÍO
ALEGRE GUTIÉRREZ , ENRIQUE
GONZÁLEZ CASTRO , VICTOR
FIDALGO FERNANDEZ , EDUARDO
Web http://agora.unileon.es/
General description This course covers fundamental topics in artificial vision with a focus on object recognition. During the course, the main ideas related with color, segmentation, image features, shape, texture and object recognition will be explained. During labs sessions some of the methods viewed in class will be programmed using MATLAB. A Final Project will be carried out allowing to students to explore in depth a chosen topic.
Tribunales de Revisión
Tribunal titular
Cargo Departamento Profesor
Presidente ING.MECANICA,INFORMAT.AEROESP. MATELLAN OLIVERA , VICENTE
Secretario ING.ELECTR.DE SIST. Y AUTOMATI FOCES MORAN , JOSE MARIA
Vocal ING.ELECTR.DE SIST. Y AUTOMATI GARCIA RODRIGUEZ , ISAIAS
Tribunal suplente
Cargo Departamento Profesor
Presidente ING.MECANICA,INFORMAT.AEROESP. FERNANDEZ LLAMAS , CAMINO
Secretario ING.MECANICA,INFORMAT.AEROESP. RODRIGUEZ DE SOTO , ADOLFO
Vocal ING.ELECTR.DE SIST. Y AUTOMATI RODRIGUEZ SEDANO , FRANCISCO JESUS

Competencies
Type A Code Competences Specific
  A13233
  A13249
  A13260
  A13261
Type B Code Competences Transversal
  B3064
  B3065
  B3066
  B3068
Type C Code Competences Nuclear
  C1
  C3

Learning aims
Competences
Understand the main concepts related to computer vision and machine learning. Understand and know how to program basic and also applied computer vision, text processing and machine learning methods. Learn to use Python to program simple computer vision and machine learning applications. Be able to use computer vision techniques and machine learning to solve new problems. A13233
A13249
A13260
A13261
 B3064
B3065
B3066
B3068
 C1
C3

Contents
Topic Sub-topic
Block I: THEORY Lesson 1: BASIC CONCEPTS OF COMPUTER VISION AND MACHINE LEARNING
Artificial Intelligence. Basic Concepts of Machine Learning, Computer Vision and NLP.

Lesson 2. MACHINE LEARNING
Supervised Classification (parametric and non-parametric). Classification committees (ensemble learning). Classifier evaluation: metrics and techniques. Unsupervised learning.

Lesson 3. TEXT CLASSIFICATION
Introduction. Text classification Pipeline. Preprocessing. Description. Classification. Text Classification with Deep Learning

Lesson 4. Deep LEARNING
What is deep learning. Neural Networks and their parts. Activation function. Optimization. Loss Function. Regularization. Underfitting and Overfitting. Steps to solve a problem in Machine Learning.

Lesson 5. IMAGE CLASSIFICATION
Introduction. Description. Machine Learning methods for Image Classification. Image Classification based on Deep Learning
Block II: LABS During the practical training, which will be carried out in the laboratory F3, we will use Python 3.X. It will be available in the lab, although it is highly recommended that each student installs it also in her/his own computer.
The practical sessions will be oriented to the learning of Python basics and, then, several Vision and Learning libraries will be used in the application to image description and classification.

Planning
Methodologies  ::  Tests
  Class hours Hours outside the classroom Total hours
Problem solving, classroom exercises 12 0 12
 
Laboratory practicals 40.5 0 40.5
Assignments 25 0 25
 
Lecture 31 0 31
 
Extended-answer tests 4 0 4
 
(*)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 Exercises done on the blackboard and through slides and examples Also, exercises could be left in Agora, with solutions, most of the time also with examples solved in Excel.
Laboratory practicals Guided labs based on programming, used to evaluate and to learn more in deep some methods and techniques discussed in class. 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 it in Agora.
Assignments A specific subject will be studied by each student. A general explanation of the chosen subject will be carried out and a specific study, mainly based in a research paper and its implementation, will be performed.
Lecture Theoretical sessions in the classroom using slides. Presentations or documents corresponding to the materials of each lesson will be left in Agora and a forum for doubts will be set up. Some lessons will be accompanied by videos related to the concepts presented, some recorded by the teachers and others from internet resources that the teachers consider especially appropriate. Some lessons could be accompanied by a questionnaire with questions, which can be both theoretical and practical, whose deliveries will be evaluable. Datacamp platform courses, or similar ones, could be used to reinforce some of the lessons taught, with some courses being optional and others being mandatory.

Personalized attention
 
Assignments
Laboratory practicals
Problem solving, classroom exercises
Lecture
Description
Inquiries may be made to the instructor in person or on-line.

The online inquieries could be carried out using a general forum, or specific forums for each activity.

Appointments with the instructor will be made using the Agora.

Assessment
  Description Qualification
Assignments The student will choose a topic proposed by the teachers, Course Project, and he/she will have to study and defend it. Material prepared and the defence conducted will be assessed.
The subject could have a practical part.

In addition, to pass the course, is necessary to submit correctly all requested deliveries related to the Course Project and to pass a validation exam.
 50
Extended-answer tests The subject will be assessed by a final exam and its corresponding validation examination.

The final examination consists in questions about the theoretical concepts and exercises viewed during the lectures and about practicals carried out in the Labs.
 25
Others The tasks presented by the students will be evaluated. The student must submit all the activities indicated as mandatory that will be graded by the teachers.
To pass the course, at least 50% of the compulsory activities must be delivered correctly.

Voluntary activities will also be assessed.		 25
 
Other comments and second call
  • Delayed deliveries will suffer a penalty in the note.
  • To pass the course, at least 50% of the compulsory activities must be delivered correctly. 
  • The student can compensate for the grade obtained in some main parts (Project, Exam, Laboratory sessions and DataCamp courses) if it is higher than 3.0. However, the global grade for passing the subject should be 5.0 out of 10.0.
  • Students who fail to pass any assignments (Laboratory sessions) or the final project (Final Project) in the continuous evaluation may deliver what they lack in the period corresponding to the first ordinary call.
  • To pass the subject in the second ordinary call, the student must submit the requested assignments (Laboratory Sessions) and the final project (Final Project) that will be subject of examination.

Sources of information
Access to Recommended Bibliography in the Catalog ULE

Basic

  • Deep Learning MIT book, https://www.deeplearningbook.org/ 
  • Francois Chollet, Deep learning with Python, Manning, 2022 
  • Andrew S. Glassner, Deep Learning: A visual Approach, No Starch Press, 2021 
  • Ian Goodfellow, Yoshua Bengio and Aaron Courville. Deep Learning (Adaptive Computation and Machine Learning series) Illustrated Edition. The MIT Press, 2016. Online version: https://www.deeplearningbook.org/
  • Combining Pattern Classifiers: Methods and Algorithms, L. Kuncheva, Wiley, Second Edition, 2014
  • Richard Szeliski. Computer Vision: Algorithms and Applications, Springer, 2011 (pdf available online: http://szeliski.org/Book/)
  • Pattern Classification (2nd Edition), by R.O. Duda, P.E. Hart, and D.G. Stork, Wiley-Interscience, 2000.
  • Alegre, E., Sánchez, L., Fernández, R.A. y Mostaza, J.C. (2003). Procesamiento Digital de Imagen: Fundamentos y Prácticas con Matlab. Secretariado de Publicaciones y Medios Audiovisuales de la Universidad de León.
  • González, R. C. y Woods, R. E. (2008). Digital Image Processing (Third Edition). Prentice Hall.
  • Introduction to Machine Learning. 2nd Edition. Ethem Alpaydin. The MIT Press, 2010.
  • Principles of Data Mining, Max Bramer, Springer-Verlag, 2007
Complementary

Pajares, G y de la Cruz, J.M. (2001). Visión por Computador. Ra-ma.
González, J. (2000). Visión por Computador. Paraninfo.
González, R. C. y Woods, R. E. (1996). Tratamiento digital de imágenes. Addison-Wesley /Diaz de Santos.

Shapiro, L. & Stockman G. (2001). Computer Vision. Prentice-Hall.

Parker, J.R. (1997). Algorithms for image processing and computer vision. John Wiley & Sons, Inc.
Trucco, E. & Verri, A. (1998). Introductory Techniques for 3-D Computer Vision. Prentice-Hall.
Maravall, D. (1993). Reconocimiento de formas y visión artificial. Ra-ma
Davies, E.R. (1996). Machine Vision: Theory, Alforithms, Practicalities. Academic Press.

Recommendations


Subjects that it is recommended to have taken before
INTRODUCTION TO INTELLIGENT SYSTEMS / 00709016
 
Other comments
The Artificial Vision course, in 8th semester, Grado en Ingeniero en Informatica, is also a recommended subject. Any course about Computer Vision or Machine Learning will help the student to follow this subject. Programming skills, better in Python, are recommended.