IDENTIFYING DATA 2019_20
Subject (*) COMPUTERIZED VISION Code 17234217
Study programme
Bachelor's Degree in Computer engineering (2010)
 Cycle 1st
Descriptors Credits Type Year Period
6 Optional
Language
Català
Department Computer Engineering and Mathematics
Coordinator
PUIG VALLS, DOMÈNEC SAVI
 E-mail susana.alvarez@urv.cat
domenec.puig@urv.cat
mohamed.abdelnasser@urv.cat
Lecturers
ALVAREZ FERNANDEZ, SUSANA MARIA
PUIG VALLS, DOMÈNEC SAVI
ABDELNASSER MOHAMED MAHMOUD, MOHAMED
Web http://moodle.urv.cat/
General description and relevant information Realitzar una introducció al món de la Visió per Computador. S'estudiaran les necessitats i motivacions que han portat a mecanitzar alguns processos de percepció visual amb la finalitat d'aconseguir resultats semblants als de la visió humana. L'assignatura tindrà un caire descriptiu i pràctic, i només s'explicaran els models matemàtics i físics imprescindibles per a fonamentar les tècniques exposades. S'estudiaran alguns dels principals processos que permeten obtenir, caracteritzar i interpretar la informació present en les imatges capturades en el món tridimensional. La part pràctica de l'assignatura inclourà l'estudi dels components bàsics de qualsevol sistema de visió (CCD's, plaques, etc), així com la realització de petites implementacions d'algunes de les tècniques de processament d'imatges explicades a les classes teòriques. Els exemples pràctics que es proposaran estaran encaminats a estudiar la interrelació entre la visió i altres disciplines com la robòtica així com la seva aplicació al món industrial.

Competences
Type A Code Competences Specific
 CP3 Be able to evaluate the computational complexity of a problem, know algorithmic strategies that may lead to its resolution and recommend, develop and implement the one that will guarantee the best performance in accordance with the established requirements.
 CP5 Be able to acquire, obtain, formalise and represent human knowledge in a computable format to solve problems through an IT system in any field of application, particularly those related to aspects of computation, perception and action in intelligent environments and settings.
 CP7 Have knowledge of and develop computational learning techniques and design and implement applications and systems that use them, including those dedicated to the automatic extraction of information and knowledge from large volumes of data.
Type B Code Competences Transversal
 CT5 Communicate information clearly and precisely to a variety of audiences.
Type C Code Competences Nuclear

Learning outcomes
Type A Code Learning outcomes
 CP3 Be familiar with and know how to use techniques of preprocessing, segmentation and image classification.
Design applications oriented toward inspection and quality control.
 CP5 Know the stages that integrate a computer vision system.
Know the process of image formation.
 CP7 Know how to apply basic Vision methods in the resolution of specific problems.
Design applications oriented toward inspection and quality control.
Type B Code Learning outcomes
 CT5 Produce quality texts that have no grammatical or spelling errors, are properly structured and make appropriate and consistent use of formal and bibliographic conventions.
Draw up texts that are structured, clear, cohesive, rich and of the appropriate length
Draw up texts that are appropriate to the communicative situation, consistent and persuasive
Type C Code Learning outcomes

Contents
Topic Sub-topic
Tema 1.- Introduction Concept and objectives of Computer Vision. Image acquisition. Levels of image processing.
Tema 2.- Image formation. Geometric foundations: mathematical representation of an image, basic geometric transformations, perspective transformation, parallel transformation. Illumination techniques. Color. Charge-coupled device: camera model, lens focus and perception, stereoscopic vision.
Tema 3.- Preprocessing techniques. Basic relationships between pixels. Spatial domain. Frequency domain. Filtering techniques: normalization, equalization, smoothing, edge detection.
Tema 4.- Representation techniques. Segmentation: detection of borders, thresholding, region growing, split and merge. Feature Extraction.
Tema 5.- Description and recognition techniques. Description: border descriptors, region descriptors. Recognition. Interpretation.
Tema 6.- Computer vision applications. Industrial applications: inspection, quality control. Medical applications. Office applications.

Planning
Methodologies  ::  Tests
  Competences (*) Class hours
 Hours outside the classroom
 (**) Total hours
Introductory activities
CP5
 2 0 2
IT-based practicals in computer rooms
CP3
 15 30 45
Assignments
CT5
 0 13 13
Lecture
CP5
CP7
 9 33 42
Problem solving, exercises in the classroom
CP5
 15 29 44
Personal attention
2 0 2
 
Multiple-choice objective tests
CP3
CP5
CP7
 2 0 2
 
(*) On e-learning, hours of virtual attendance of the teacher.
(**) The information in the planning table is for guidance only and does not take into account the heterogeneity of the students.

Methodologies
Methodologies
  Description
Introductory activities Comprehensive description of the course: contents, assessment, etc.
IT-based practicals in computer rooms Practical exercises related to the theoretical concepts in lectures using standard computer vision software.
Assignments Performing work related to theoretical concepts in lectures: the work will be theoretical or practical.
Lecture Explanation by the teacher of Computer Vision concepts, techniques, methodologies, etc., related to the course content.
Problem solving, exercises in the classroom Solving exercises under the supervision of the teacher.
Personal attention Personal attention by teachers of the subject. Includes personalized attention devoted to the evaluation of some projects and exercises.

Personalized attention
Description
Personal attention by teachers of the subject. Includes personalized attention devoted to the evaluation of some projects and exercises.

Assessment
Methodologies Competences Description Weight        
IT-based practicals in computer rooms
CP3
 Practical exercises related to the theoretical concepts in lectures using standard computer vision software. 50%
Assignments
CT5
 Performing work related to theoretical concepts in lectures: the work will be theoretical or practical. 25%
Problem solving, exercises in the classroom
CP5
 Solving exercises under the supervision of the teacher. 15%
Multiple-choice objective tests
CP3
CP5
CP7
 Solve tests related to the theoretical contents of the course. 10%
Others  
 
Other comments and second exam session

A la segona convocatòria s'hauran de tornar a realitzar les proves parcials d'avaluació continua que l'alumne no hagi aconseguit una nota minima.

La nota mitjana ponderada de totes les proves parcials ha de ser com a mínim de 5.

Sources of information

Basic Escalera, A. de la, Visión por Computador, Prentice Hall, 2001
Ajenjo, A.D, Tratamiento Digital de Imágenes, Anaya Multimedia, 1994
Forsyth, D.A.; Ponce, J., Computer vision a modern approach, Prentice Hall, 2011
Pajares Martinsanz, Gonzalo, Visión por computador: imágenes digitales y aplicaciones , Ra-Ma, 2007

Complementary Vitrià, J., Visió per Computador, Servei Publicacions U.A.B., 1995
Fu, K.S.; Gonzalez, R.C.; Lee, C.S.G, Robótica: Control, Detección, Visión e Inteligencia, McGraw Hill, 1990

Recommendations
(*)The teaching guide is the document in which the URV publishes the information about all its courses. It is a public document and cannot be modified. Only in exceptional cases can it be revised by the competent agent or duly revised so that it is in line with current legislation.