UMH - COMPUTER VISION

Contents

Navigation tree of "Faculty"

COMPUTER VISION

Course

Code: 1782

Degree: Bachelor's in Electronic Engineering and Industrial Automation

School of Engineering of Elche

Year: Year 4 of Bachelor's in Electronic Engineering and Industrial Automation

Semester: Spring

Type: Elective

Language: Spanish

ECTS credits: 6

Lecture: 3

Laboratory: 3

Hours: 150

Directed: 60

Shared: 24

Autonomous: 66

Subject matter: Program Electives

Module: Transversal and Professional Competencies

Degree website

Department: Systems Engineering and Automation

Area: AUTOMATION AND SYSTEMS ENGINEERING

Course instructors are responsible for the course content descriptions in English.

Description

Sensory integration. Machine vision systems. Image acquisition. Digital image processing.

Faculty

Name	Coordinator	Lecture	Laboratory
JIMENEZ GARCÍA, LUIS MIGUEL	■	■	■

Professional interest

Knowledge of Computer Vision provides students with specific skills for their future professional activity, enabling it to solve real problems of automated industrial inspection, by designing and implementing algorithms for extracting information, description and recognition from digital images

Competencies and learning outcomes

General competencies

Capacity for drafting, signing, and developing projects within the field of industrial electronics engineering aimed at construction, remodeling, repair, maintenance, demolition, manufacturing, installation, assembly and/or the operation of structures, mechanical equipment, energy installations, electrical and electronic installations, industrial installations and plants, and manufacturing and automation processes.
Ability to manage the kinds of engineering projects described in the preceding competency.
Knowledge about basic and technological material that enable learning new methods and theories, providing versatility for adapting to new situations.
Capacity to resolve problems with initiative, decision making, creativity, critical reasoning, and to communicate and transmit knowledge, abilities, and skills within the field of industrial electronics engineering.
Capacity to analyze and assess the social and environmental impact from technical solutions.
Ability to apply quality principles and methods.
Ability to work within a multilingual and multidisciplinary environment.

Specific competencies

Knowledge about and capacity for modeling and simulating systems.
Knowledge about the principles and applications of robotic systems.

Objectives (Learning outcomes)

01Studying the phenomena involved in capturing images on a computer vision system.
02Knowing the basic characteristics of a digital image.
03Understanding the transformations in digital images in both spatial and frequency domain
04Implement algorithms for noise reduction in digital images.
05Learning the techniques for extracting information from the image (edges, corners, regions).
06Study segmentation algorithms and description of regions in digital images
07Introduce students to the problem of classification in the context of computer vision.
08Modeling the process of forming an image in a camera calibration.
09Knowing the 3D vision techniques using stereo systems
010Know how to calibrate the projective model of a stereo pair.
011Calculate 3D information from one or more cameras using computer vision techniques.
012Implement practice the concepts in theory to real digital image analysis.
013Understand the use of applications and image processing libraries to implement computer vision systems.

Teaching units

Association between objectives and units

Objective/Unit	U1	U2	U3	U4
01
02
03
04
05
06
07
08
09
010
011
012
013

Schedule

Week	Teaching units	Directed hours	Shared hours	Autonomous hours	Total hours
1	U1	4	0	0	4
2	U1	4	0	0	4
3	U2	4	0	0	4
4	U2	4	0	4	8
5	U2	4	0	4	8
6	U2	4	0	4	8
7	U2	4	0	6	10
8	U2	4	0	6	10
9	U3	4	2	6	12
10	U3	4	2	6	12
11	U3	4	4	6	14
12	U3	4	4	6	14
13	U4	4	4	6	14
14	U4	4	4	6	14
15	U4	4	4	6	14

Basic bibliography

Complementary bibliography

Enrieue Alegra, Gonzalo Pajares, Arturo de la Escalera. "Conceptos y Métodos en Visión por Computador". CEA Grupo de Visión.
Bishop, Christopher M. "Pattern recognition and machine learning". New York Springer 2006.
Mitchell, Tom M. "Machine Learning". New York McGraw-Hill cop 1997.
Hartley, Richard. Zisserman, Andrew. "Multiple view geometry in computer vision ". Cambridge, UK New York Cambridge University Press 2003.
Trucco, Emanuele. Verri, Alessandro. "Introductory techniques for 3-D computer vision". Upper Saddle River, NJ Prentice Hall c1998.
Faugeras, Olivier 1949-. "The geometry of multiple images". Cambrigde The Mit Press 2001.
Forsyth, David A. Ponce, Jean. "Computer vision a modern approach". Upper Saddle River [New Jersey] Prentice Hall cop. 2003.

Software

MATLAB 2015A
Weka
titere

Methodology and grading

Methodology

Cooperative learning: Develop active learning through cooperative working strategies among students and promote shared responsibility to reach group goals.
Lecture: Pass on knowledge and activate cognitive processes in students, encouraging their participation.
Problem-based learning: Develop active learning strategies through problem solving that promote thinking, experimentation, and decision making in the student.
Project-based learning: Realization of a project to solve a problem, applying acquired learning and promoting abilities related to planning, design, performing activities, and reaching conclusions.
Solving exercises and problems: Exercise, test, and apply previous knowledge through routine repetition.

Grading

The final grade will be based on the following parts:

- Group works made during the course (20%)

- Practical sessions (10%)

- Final exam (70%). It will consist of two parts:
* Part 1 (50%) Test: Each wrong answer subtracts 1/4 of the value of each question.
* Part 2 (50%) Theoretical questions: The punctuation of each question is outlined in the exam.

Assessment test characteristics

no aplica

Correction criteria

- Final exam It will consist of two parts:
* Part 1 (50%) Test: Each wrong answer subtracts 1/4 of the value of each question.
* Part 2 (50%) Theoretical questions: The punctuation of each question is outlined in the exam.

Additional requirements

Identification, Pen, Pencil, Pencil, Non-programmable Calculator

Note: Mobile devices and programmable calculators are not allowed.

Faculty: COMPUTER VISION