IDENTIFYING DATA 2019_20
Subject (*) ARTIFICIAL VISION AND PATTERN RECOGNITION Code 17685105
Study programme
Computer Security Engineering and Artificial Intelligence (2016)
 Cycle 2nd
Descriptors Credits Type Year Period
4.5 Compulsory First 1Q
Language
Anglès
Department Computer Engineering and Mathematics
Coordinator
PUIG VALLS, DOMÈNEC SAVI
 E-mail
Lecturers
Web http://consultar l'espai Moodle de l'assignatura
General description and relevant information To introduce the fundamental concepts of Computer Vision and further advanced topics related to problems of analysis and automatic recognition of complex images. Theoretical concepts and practical applications will be studied by means of well-known tools of Image Processing and Computer Vision.

Competences
Type A Code Competences Specific
 A1 Integrate the fundamental technology, applications, services and systems of Computer Security and Artificial Intelligence,in a broader, multidisciplinary context.
 A8 Design and develop computer systems, applications and services for the protection of privacy and information security in ubiquitous systems.
 A9 Apply computational, mathematical, statistical and artificial intelligence methods in order to model, design and develop applications, services, smart systems and knowledge-based systems.
 A10 Use and develop methodologies, methods, techniques, specific-use programmes, regulations and standards for graphic computing.
 A11 Conceptualise, design, develop and evaluate the person-computer interaction of computer products, systems, applications and services using advanced artificial intelligence techniques interaction.
 A12 Create and operate virtual environments, and create, manage and distribute multimedia content guaranteeing the protection of privacy and copyright by techniques of computer security and Artificial Intelligence.
 G1 Project, calculate and design products, processes and installations in the areas of Computer Security and Artificial Intelligence
 G2 Perform mathematical modelling, calculation and simulation in company technology and engineering centres, particularly in tasks of research, development and innovation in the areas of Computer Security and Artificial Intelligence
Type B Code Competences Transversal
 CT2 Forming opinions on the basis of the efficient management and use of information
 CT3 Solve complex problems critically, creatively and innovatively in multidisciplinary contexts.
 CT4 Work in multidisciplinary teams and in complex contexts.
 CT5 Communicate complex ideas effectively to all sorts of audiences
 CT7 Apply ethical principles and social responsibility as a citizen and a professional.
Type C Code Competences Nuclear

Learning outcomes
Type A Code Learning outcomes
 A1 Analyse the problems and their causes from a global focus in the medium and long term.
 A8 Develop advanced artificial vision techniques in cameras and other embedded and ubiquitous systems.
 A9 Know how to implement advanced computer vision techniques.
 A10 Use graphic computation techniques.
 A11 Use artificial systems that interact with humans by means of artificial vision.
 A12 Analyse multimedia content using pattern recognition and artificial vision techniques.
 G1 Integrate theoretical knowledge into the realities to which it may apply.
 G2 Apply the techniques learned in a specific context.
Type B Code Learning outcomes
 CT2 Manage information and knowledge by making efficient use of the information technologies.
 CT3 Recognise the situation as a problem in a multidisciplinary, research or professional environment, and take an active part in finding a solution.
 CT4 Participate in the group in a good working environment and help to solve problems.
 CT5 Produce a persuasive, consistent and precise discourse that can explain complex ideas and effectively interact with the audience.
 CT7 Apply ethical and socially responsible principles as a citizen and a professional.
Type C Code Learning outcomes

Contents
Topic Sub-topic
Chapter 1.- Image Processing. Filtering, image compensation and image enhancement, morphological operations.
Chapter 2.- Geometrical Feature Extraction. Identification of corners, lines and basic geometrical shapes.
Chapter 3.- Color and Texture Analysis. Color models, texture types, extraction of textural features, geometric methods.
Chapter 4.- Image Segmentation and Classification. Unsupervised segmentation based on contours and regions, supervised classification, methods of decision theory, probabilistic methods, neural networks.
Chapter 5.- Stereoscopic Vision. Calibration of cameras and camera systems, epipolar geometry, image rectification, matching, triangulation.
Chapter 6.- Perception and 3D-modeling. Generation of depth maps, extraction of basic geometric elements,
automatic generation of scenes, scene recognition, geometric hashing.

Planning
Methodologies  ::  Tests
  Competences (*) Class hours
 Hours outside the classroom
 (**) Total hours
Introductory activities
A1
 1 1.5 2.5
Presentations / oral communications
CT5
 1 1.5 2.5
Assignments
A1
A8
A10
A11
A12
G1
CT2
CT3
CT4
CT7
 13 19.5 32.5
Reading written documents and graphs
A1
A8
A9
A10
A11
G1
 26 38.5 64.5
Forums of debate
CT2
CT5
CT7
 1 1.5 2.5
Personal attention
CT2
CT3
CT7
 1 0 1
 
Multiple-choice objective tests
A9
G2
 2 5 7
 
(*) 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 Introduction to the course: motivation, objectives, contents, teaching methods, bibliography and evaluation.
Presentations / oral communications Students perform oral presentation of their work going in depth into specific topics of the subject. Assessment by the teacher.
Assignments Students perform in groups of 2 people some analyses and research tasks related to the main themes of the course. Practical use of simulators. Preparation of a report. Final evaluation by the teacher.
Reading written documents and graphs The students have to prepare the units of the course.
Forums of debate Share questions with the teacher and their mates in the Forum. The teacher or any student can reply the questions.
The collaboration between them is part of the learning process
Personal attention Personal attention to each student by the teacher.

Personalized attention
Description
Enquiries /Tutorials: Resolution of theoretical and practical questions. Correction of practices. Exams review.

Assessment
Methodologies Competences Description Weight        
Presentations / oral communications
CT5
Oral presentation. Final evaluation by the teacher.
 30
Assignments
A1
A8
A10
A11
A12
G1
CT2
CT3
CT4
CT7
 Elaboration by the students of practical work related to the main topics of the course using the tools of computer vision explained in the practical classes. Elaboration of a report. 50
Multiple-choice objective tests
A9
G2
 Realització de proves tipus test. 20
Others  
 
Other comments and second exam session

The student has to go to second call with all the assessments tests not past on the first call.

Sources of information

Basic E. Trucco, A. Verri, Introductory Techniques for 3-D Computer Vision, Prentice Hall, 1998
L. Shapiro, G. Stockman, Computer Vision, Prentice Hall, 2001
D.A. Forsyth, Computer Vision: A Modern Approach, Pearson Education, 2012
N.J. Hackensack, Handbook of pattern recognition and computer vision, Imperial College Press, 2010
R. Szeliski, Computer vision: algorithms and applications, Springer, 2011

Complementary O. Faugeras, Three-Dimensional Computer Vision, MIT Press, 1993
E.R. Davies, Machine Vision: Theory, Algorithms, Practicalities, Academic Press, 1997

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.