We may earn an affiliate commission when you visit our partners.
Course image
Ernest Valveny, Jordi Gonzàlez Sabaté, and Ramon Baldrich Caselles

¿Te interesa la visión por computador? ¿Te gustaría saber cómo se puede reconocer el contenido visual de las imágenes y clasificarlas a partir de su contenido?

Read more

¿Te interesa la visión por computador? ¿Te gustaría saber cómo se puede reconocer el contenido visual de las imágenes y clasificarlas a partir de su contenido?

En este curso aprenderás diferentes métodos de representación y clasificación de imágenes. El temario del curso te permitirá conocer el esquema básico de clasificación de imágenes conocido como Bag of Visual Words. A partir de este esquema básico aprenderás cómo utilizar varios descriptores locales de la imagen así como los métodos de clasificación más habituales. También describiremos diferentes extensiones del esquema básico que permiten combinar distintos descriptores, incluir información espacial o mejorar la representación final de la imagen.

Finalizar el curso te permitirá:

• Diseñar soluciones adaptadas para diferentes problemas de clasificación y reconocimiento de imágenes

• Conocer las principales técnicas usadas para la descripción y clasificación de una imagen

• Acceder a las herramientas que permiten el desarrollo de aplicaciones reales de clasificación de imágenes

El curso está orientado tanto a estudiantes universitarios de algún grado relacionado con la informática, la ingeniería o las matemáticas, como a otros estudiantes con conocimientos de programación, interesados en aprender cómo utilizar técnicas de visión por computador para extraer información de las imágenes.

Enroll now

Two deals to help you save

We found two deals and offers that may be relevant to this course.
Save money when you learn. All coupon codes, vouchers, and discounts are applied automatically unless otherwise noted.

What's inside

Syllabus

Introducción a la clasificación de imágenes
En esta primera semana explicaremos los fundamentos de la clasificación de imágenes y presentaremos todos los pasos de un primer sistema de clasificación básico. Para ello, primero veremos algunos conceptos básicos sobre el procesamiento de una imagen que nos servirán para introducir un primer método para detectar y describir características locales (SIFT) en una imagen. Luego veremos cómo podemos agrupar estas características locales para representar toda la imagen y explicaremos un primer clasificador simple, k-NN. Finalmente comentaremos los aspectos básicos de la evaluación del rendimiento de un sistema de clasificación de imágenes.
Read more
Bag of Words (BoW)
Esta semana introduciremos Bag of Words como método de representación básico que utilizaremos mayoritariamente a lo largo de todo el curso. Explicaremos todos los detalles necesarios para construir la representación BoW de una imagen, incluyendo la construcción del vocabulario utilizando K-Means y cómo agregar la información de las características locales en la representación final en forma de histograma. En la segunda parte de la semana explicaremos Support Vector Machines (SVM) como método de clasificación, tanto los conceptos fundamentales como su formulación matemática y los detalles para entrenar y utilizar un clasificador basado en SVM. Finalmente, completaremos la explicación de la evaluación del rendimiento que introducimos en la primera semana.
Extracción de características
En esta semana completaremos la explicación de métodos de extracción de características que iniciamos en la primera semana ofreciendo alternativas a la utilización de SIFT. En concreto veremos SURF como un nuevo método de detección y extracción más eficiente computacionalmente que SIFT. Para aumentar la capacidad descriptiva de las características analizaremos otras estrategias para la detección de características locales e introduciremos descriptores que nos permitan tener en cuenta la información del color en la imagen. Veremos también como podemos también mejorar la eficiencia computacional reduciendo la dimensión de los descriptores de carácterísticas locales.
Estrategias de fusión
En esta semana veremos cómo podemos combinar diferentes descriptores que aportan diferente tipo de información en el esquema de representación BoW. Explicaremos los diferentes niveles a los que se puede hacer esta combinación: a nivel de descriptores locales (early fusion), a nivel de construcción del vocabulario (intemediate fusion) o a nivel de clasificador (late fusion)
Incorporación de información espacial
En esta semana abordaremos cómo podemos incorporar información espacial de los objetos de la imagen en la representación BoW. Para ello introduciremos el concepto de pirámide espacial y cómo se utiliza para modificar la representación básica del BoW de forma que tengamos en cuenta la localización en la imagen de cada característica local. Veremos también cómo podemos comparar imágenes que utilizan la pirámide espacial. Finalmente explicaremos una forma de aprender la configuración óptima de una pirámide espacial.
Técnicas avanzadas
En esta última semana veremos algunas técnicas avanzadas que pueden ser extensiones o alternativas al BoW cuando nos enfrentamos a problemas de clasificación complejos por el tipo o el número de imágenes. En primer lugar veremos los GMM como un método alternativo para construir el vocabulario que nos servirá también para explicar Fisher Vector como otra posibilidad de agregar todas las características locales en una representación de toda la imagen. En el mismo sentido explicaremos también VLAD. Finalizaremos el curso con una breve introducción a las redes neuronales convolucionales (CNNs) que se están constituyendo como un esquema alternativo para la clasificación de imágenes, especialmente en problemas con muchas clases e imágenes.

Good to know

Know what's good
, what to watch for
, and possible dealbreakers
Esta dirigido a alumnos universitarios en grados relacionados con la informática, ingeniería o matemáticas, así como a otras personas con conocimientos de programación interesadas en aprender técnicas de visión por computador para extraer información de imágenes

Save this course

Save Clasificación de imágenes: ¿cómo reconocer el contenido de una imagen? to your list so you can find it easily later:
Save

Reviews summary

Outdated course with poor instruction

This course on image classification receives negative feedback. Students remark that materials are outdated and do not align with contemporary practices. They also note that instructors lack clarity, communication skills, and subject matter expertise. Exams are criticized for focusing on minor details and being poorly aligned with course content. Additionally, the lack of practical application, disconnected theoretical and practical components, and inactive forums have led students to express dissatisfaction.
Lack of forum activity hinders student support.
""Los foros no tienen movimiento desde hace 2 años. Yo he realizado preguntas y no se me ha contestado.""
Instructors lack clarity and have difficulty communicating.
""Sólo uno de los profesores, Jordi, explica con claridad. El resto titubean mucho, incluso hablan mal, y no se les entiende""
Theoretical and practical components are not integrated.
""Apenas hay parte práctica en la explicación y el código incluido sirve para poco y no está integrado con las explicaciones.""
Exams focus on minor details and misinterpret the course teachings.
""Los exámenes son prácticamente todas preguntas de múltiple respuesta, que se centran en cosas que apenas se han explicado o a las que no se les ha dado importancia en las lecciones.""
Materials fail to reflect current practices.
""La materia está más o menos bien, aunque se explica claramente que no es lo que se utiliza en la actualidad.""

Activities

Be better prepared before your course. Deepen your understanding during and after it. Supplement your coursework and achieve mastery of the topics covered in Clasificación de imágenes: ¿cómo reconocer el contenido de una imagen? with these activities:
Explora bibliotecas de visión artificial
Familiarízate con las bibliotecas de visión artificial para comprender mejor cómo se implementan los algoritmos en la práctica.
Browse courses on OpenCV
Show steps
  • Investiga bibliotecas populares de visión artificial como OpenCV o scikit-image.
  • Explora la documentación y los tutoriales de la biblioteca.
  • Implementa algunos ejemplos de código para tareas básicas de procesamiento de imágenes.
Contribuye a un proyecto de código abierto de visión artificial
Amplía tus habilidades prácticas y contribuye a la comunidad de visión artificial participando en un proyecto de código abierto.
Show steps
  • Explora proyectos de código abierto relacionados con la clasificación de imágenes.
  • Identifica áreas donde puedes contribuir, como corrección de errores o nuevas funciones.
  • Lee la documentación del proyecto y sigue las pautas de contribución.
  • Presenta una solicitud de extracción y colabora con los mantenedores del proyecto.
Show all two activities

Career center

Learners who complete Clasificación de imágenes: ¿cómo reconocer el contenido de una imagen? will develop knowledge and skills that may be useful to these careers:
Data Scientist
A Data Scientist uses data to solve business problems. Data Scientists must be able to collect, clean, and analyze data. They must also be able to build and train machine learning models. This course will help you build the skills necessary to become a Data Scientist. You will learn how to represent and classify images, which is a fundamental task in data science. You will also learn about different machine learning algorithms and how to evaluate their performance.
Computer Vision Engineer
A Computer Vision Engineer develops and applies computer vision techniques to solve real-world problems. Computer Vision Engineers must be able to understand the principles of computer vision, develop and implement computer vision algorithms, and evaluate the performance of computer vision systems. This course will help you build the skills necessary to become a Computer Vision Engineer. You will learn how to represent and classify images, which is a fundamental task in computer vision. You will also learn about different computer vision algorithms and how to evaluate their performance.
Machine Learning Engineer
A Machine Learning Engineer designs, builds, and deploys machine learning models to solve real-world problems. Machine Learning Engineers must be able to understand the business problem, collect and prepare data, build and train models, and evaluate and deploy models into production. This course will help you build the skills necessary to become a Machine Learning Engineer. You will learn how to represent and classify images, which is a fundamental task in machine learning. You will also learn about different machine learning algorithms and how to evaluate their performance.
Software Engineer
A Software Engineer designs, develops, and maintains software systems. Software Engineers must be able to understand the requirements of a software system, design and implement the system, and test and debug the system. This course will help you build the skills necessary to become a Software Engineer. You will learn how to represent and classify images, which is a fundamental task in software development. You will also learn about different software development tools and techniques.
Product Manager
A Product Manager is responsible for the development and launch of a product. Product Managers must be able to understand the market, identify customer needs, and develop and execute a product strategy. This course will help you build the skills necessary to become a Product Manager. You will learn how to represent and classify images, which is a fundamental task in product development. You will also learn about different product development processes and techniques.
Business Analyst
A Business Analyst helps organizations understand their business needs and develop solutions to meet those needs. Business Analysts must be able to analyze data, identify problems, and develop and implement solutions. This course will help you build the skills necessary to become a Business Analyst. You will learn how to represent and classify images, which is a fundamental task in business analysis. You will also learn about different business analysis tools and techniques.
User Experience Designer
A User Experience Designer designs and evaluates the user experience of products and services. User Experience Designers must be able to understand the needs of users, develop and implement user experience designs, and evaluate the effectiveness of those designs. This course will help you build the skills necessary to become a User Experience Designer. You will learn how to represent and classify images, which is a fundamental task in user experience design. You will also learn about different user experience design tools and techniques.
Marketing Manager
A Marketing Manager is responsible for developing and executing marketing campaigns. Marketing Managers must be able to understand the market, identify customer needs, and develop and execute marketing strategies. This course will help you build the skills necessary to become a Marketing Manager. You will learn how to represent and classify images, which is a fundamental task in marketing. You will also learn about different marketing tools and techniques.
Sales Manager
A Sales Manager is responsible for leading and managing a sales team. Sales Managers must be able to understand the market, identify customer needs, and develop and execute sales strategies. This course may help you build the skills necessary to become a Sales Manager. You will learn how to represent and classify images, which is a fundamental task in sales. You will also learn about different sales tools and techniques.
Operations Manager
An Operations Manager is responsible for planning, organizing, and managing the operations of an organization. Operations Managers must be able to understand the organization's goals, develop and implement operational plans, and evaluate the effectiveness of those plans. This course may help you build the skills necessary to become an Operations Manager. You will learn how to represent and classify images, which is a fundamental task in operations management. You will also learn about different operations management tools and techniques.
Project Manager
A Project Manager is responsible for planning, organizing, and managing projects. Project Managers must be able to understand the project's goals, develop and implement project plans, and evaluate the effectiveness of those plans. This course may help you build the skills necessary to become a Project Manager. You will learn how to represent and classify images, which is a fundamental task in project management. You will also learn about different project management tools and techniques.
Management Consultant
A Management Consultant provides advice to organizations on how to improve their performance. Management Consultants must be able to analyze organizational data, identify problems, and develop and implement solutions. This course may help you build the skills necessary to become a Management Consultant. You will learn how to represent and classify images, which is a fundamental task in management consulting. You will also learn about different management consulting tools and techniques.
Financial Analyst
A Financial Analyst provides financial advice to individuals and organizations. Financial Analysts must be able to analyze financial data, identify trends, and make recommendations. This course may help you build the skills necessary to become a Financial Analyst. You will learn how to represent and classify images, which is a fundamental task in financial analysis. You will also learn about different financial analysis tools and techniques.
Human Resources Manager
A Human Resources Manager is responsible for managing the human resources of an organization. Human Resources Managers must be able to develop and implement HR policies, manage employee relations, and recruit and hire new employees. This course may help you build the skills necessary to become a Human Resources Manager. You will learn how to represent and classify images, which is a fundamental task in human resources management. You will also learn about different human resources management tools and techniques.
Public relations manager
A Public Relations Manager is responsible for managing the public relations of an organization. Public Relations Managers must be able to develop and implement public relations campaigns, manage media relations, and build relationships with the public. This course may help you build the skills necessary to become a Public Relations Manager. You will learn how to represent and classify images, which is a fundamental task in public relations. You will also learn about different public relations tools and techniques.

Reading list

We've selected 12 books that we think will supplement your learning. Use these to develop background knowledge, enrich your coursework, and gain a deeper understanding of the topics covered in Clasificación de imágenes: ¿cómo reconocer el contenido de una imagen?.
Provides a comprehensive introduction to probabilistic graphical models, covering topics such as Bayesian networks, Markov random fields, and Kalman filters. It valuable resource for students and practitioners who want to learn about the theoretical foundations of probabilistic graphical models.
Provides a comprehensive overview of deep learning, covering topics such as convolutional neural networks, recurrent neural networks, and generative adversarial networks. It valuable resource for students and practitioners who want to learn about the latest advances in deep learning.
Provides a comprehensive overview of computer vision, covering topics such as image formation, feature detection, object recognition, and image segmentation. It valuable resource for students and practitioners in the field of computer vision.
Provides a probabilistic perspective on machine learning, covering topics such as Bayesian inference, graphical models, and reinforcement learning. It valuable resource for students and practitioners who want to learn about the theoretical foundations of machine learning.
Provides a comprehensive introduction to pattern recognition, covering topics such as supervised and unsupervised learning, dimensionality reduction, and model selection. It valuable resource for students and practitioners in the field of pattern recognition.
Provides a comprehensive introduction to statistical learning, covering topics such as linear regression, logistic regression, and tree-based methods. It valuable resource for students and practitioners who want to learn about the practical aspects of statistical learning.
Provides an algorithmic perspective on machine learning, covering topics such as supervised and unsupervised learning, dimensionality reduction, and model selection. It valuable resource for students and practitioners who want to learn about the algorithmic foundations of machine learning.
Provides a comprehensive introduction to pattern recognition and machine learning, covering topics such as supervised and unsupervised learning, dimensionality reduction, and model selection. It valuable resource for students and practitioners in the field of machine learning.
Provides a comprehensive introduction to machine learning for predictive data analytics, covering topics such as supervised and unsupervised learning, dimensionality reduction, and model selection. It valuable resource for students and practitioners who want to learn about the practical aspects of machine learning for predictive data analytics.
Provides a concise introduction to machine learning, covering topics such as supervised and unsupervised learning, dimensionality reduction, and model selection. It valuable resource for students and practitioners who want to learn about the basic concepts of machine learning.

Share

Help others find this course page by sharing it with your friends and followers:

Similar courses

Here are nine courses similar to Clasificación de imágenes: ¿cómo reconocer el contenido de una imagen?.
Detección de objetos
Most relevant
Visión artificial contemporánea
Most relevant
Introducción a la visión por computador: desarrollo de...
Most relevant
Transformer Models and BERT Model - Español
Most relevant
Transformer Models and BERT Model - Deutsch
Most relevant
Modelos predictivos con aprendizaje automático
Most relevant
Constructores de Paz
Most relevant
Introducción al Análisis de Datos
Most relevant
Preparación de alimentos saludables
Most relevant
Our mission

OpenCourser helps millions of learners each year. People visit us to learn workspace skills, ace their exams, and nurture their curiosity.

Our extensive catalog contains over 50,000 courses and twice as many books. Browse by search, by topic, or even by career interests. We'll match you to the right resources quickly.

Find this site helpful? Tell a friend about us.

Affiliate disclosure

We're supported by our community of learners. When you purchase or subscribe to courses and programs or purchase books, we may earn a commission from our partners.

Your purchases help us maintain our catalog and keep our servers humming without ads.

Thank you for supporting OpenCourser.

© 2016 - 2024 OpenCourser