Visión Artificial y Reconocimiento de Patrones

Usted está aquí

Créditos
4.5
Tipos
Optativa
Requisitos
Esta asignatura no tiene requisitos
Departamento
URV;CS
This course aims at studying the fundamental techniques for image processing and advanced issues on machine vision related to the problems of automatic analysis and recognition of complex images. Practical applications will be developed on well-known machine vision software.

Profesores

Responsable

  • Domenec Savi Puig Valls ( )

Horas semanales

Teoría
1.7
Problemas
0
Laboratorio
1
Aprendizaje dirigido
0
Aprendizaje autónomo
4.8

Competencias

Competencias Técnicas Genéricas

Genéricas

  • CG1 - Capacidad para proyectar, diseñar e implantar productos, procesos, servicios e instalaciones en todos los ámbitos de la Inteligencia Artificial.

Competencias Técnicas de cada especialidad

Académicas

  • CEA6 - Capacidad de comprender los principios básicos de funcionamiento de las técnicas de Visión Computacional, y saber utilizarlas en el entorno de un sistema o servicio inteligente.
  • CEA14 - Capacidad de comprender las técnicas avanzadas de Visión, Percepción y Robótica, y saber diseñar, implementar y aplicar estas técnicas en el desarrollo de aplicaciones, servicios o sistemas inteligentes.

Profesionales

  • CEP1 - Capacidad de resolver las necesidades de analisis de la informacion de las diferentes organizaciones, identificando las fuentes de incertidumbre y variabilidad.
  • CEP5 - Capacidad de diseñar nuevas herramientas informáticas y nuevas técnicas de Inteligencia Artificial en el ejercicio profesional.
  • CEP6 - Capacidad de asimilar e integrar los cambios del entorno economico, social y tecnologico a los objetivos y procedimientos del trabajo informatico en sistemas inteligentes.

Competencias Transversales

Actitud frente al trabajo

  • CT5 - Estar motivado para el desarrollo profesional, para afrontar nuevos retos y para la mejora continua. Tener capacidad de trabajo en situaciones de falta de informacion.

Básicas

  • CB7 - Que los estudiantes sean capaces de integrar conocimientos y enfrentarse a la complejidad de formular juicios a partir de una información que, siendo incompleta o limitada, incluya reflexiones sobre las responsabilidades sociales y éticas vinculadas a la aplicación de sus conocimientos y juicios

Objetivos

  1. To learn and practise the main algorithms and methods for image feature extaction.
    Competencias relacionadas: CEA6, CEA14,
  2. To learn and understand the main concepts of image processing.
    Competencias relacionadas: CEA6,
  3. To learn and practise the principal color and texture analysis methods.
    Competencias relacionadas: CEA14, CEP5, CB7,
  4. To learn and practise the main image segmetation and classification techniques.
    Competencias relacionadas: CEA14, CEP1, CEP5, CB7,
  5. To know some basics about stereoscopic vision and 3D models.
    Competencias relacionadas: CEA14, CEP1, CEP5,
  6. To be able to analyze a real computer vision problem, and propose effective solutions.
    Competencias relacionadas: CG1, CEP5, CEP6, CT5, CB7,

Contenidos

  1. Chapter 1. Image Processing.
    Filtering and smoothing operations. Morphological techniques.
  2. Chapter 2. Feature Extraction.
    Lines and corners detection. Identification of basic geometrical structures.
  3. Chapter 3. Color and texture analysis.
    Color models, kinds of texture, texture feature extraction, geometrical methods.
  4. Chapter 4. Image Segmentation and Image Classification.
    Unsupervised segmentation based on regions and edges. Supervised classification, theoretical decision methods, statistical methods, neural networks.
  5. Chapter 5. Stereoscopic Vision.
    Camera calibration and camera systems, epipolar geometry, image rectification, search for correspondences, triangulation.
  6. Chapter 6. Perception and 3D Modeling.
    Range images generation, extraction of geometric elements, automatic scene generation, scene recognition, geometrical hashing.

Actividades

Actividad Acto evaluativo


Master class

Theoretical and practical explanation of the main concepts of this course
Objetivos: 2 3 5 1 4 6
Teoría
30h
Problemas
0h
Laboratorio
0h
Aprendizaje dirigido
0h
Aprendizaje autónomo
40h

Lab

Implementation of practical cases
Objetivos: 2 3 1 4 6
Teoría
0h
Problemas
0h
Laboratorio
15h
Aprendizaje dirigido
0h
Aprendizaje autónomo
28h

Metodología docente

Introductory activities: Introduction to the course: motivation, objectives, contents, teaching methods, bibliography and evaluation.
IT-based practicals in computer rooms: Practical use of simulators related to course content and developing new functionalities.
Presentations / oral communications: Students perform oral presentation of their work going in depth into specific topics of the subject. Assessment by the teacher.
Lecture: Explanation of theoretical contents by the teacher.
Problem solving, exercises in the classroom: Students perform in groups of 2 people some analyses and research tasks related to the main themes of the course. Preparation of a report. Final evaluation by the teacher.
Personal attention: Personal attention to each student by the teacher during the teacher's office hours.

Método de evaluación

IT-based practicals in computer rooms:
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. 40%

Presentations / oral communications:
Students perform in groups of 2 people some analyses and research tasks related to the main themes of the course. Preparation of a report. Oral presentation. Final evaluation by the teacher. 20%

Extended-answer tests:
Extended-answer tests. 20%

Short-answer objective tests:
Objective short-answer tests. 20%

Bibliografía

Básica:

Adenda

Contenidos

There are no changes to the information published in the Academic Guide.

Metodología docente

Due to COVID19, the course will start fully online. This methodology could last till the end of the first term. Only if the clinical and social situation stabilizes in a save condition and classes can turn back to face-to-face, the registered students will be asked to decide if they prefer to continue with online classes or move to in-room classes. No decision will be taken unilaterally by the professor, but as a result of an agreement between all the students. Face-to-face laboratories will start as virtual classes. Only if room classes are recovered because COVID19 situation allows it, the on-site laboratories will be reactivated in agreement with the students.

Método de evaluación

There are no changes to the information published in the Academic Guide.

Plan de contingencia

There are no changes to the information published in the Academic Guide.