• Duración:
    5 semanas
  • Dedicación:
    5–6 horas por semana
  • Precio:

    GRATIS
    Agregar un Certificado Verificado por $99 USD

  • Instituciones
  • Tema:
  • Nivel:
    Advanced
  • Idioma:
    English
  • Transcripción de video:
    English
  • Tipo de curso:
    Al ritmo del instructor

Programas asociados:

Prerrequisitos

Advanced knowledge on linear algebra and optimization; basic familiarity with signal and image processing.

Sobre este curso

Omitir Sobre este curso

This course is a follow-up to the first introductory course of sparse representations. Whereas the first course puts emphasis on the theory and algorithms in this field, this course shows how these apply to actual signal and image processing needs.

Models play a central role in practically every task in signal and image processing. Sparse representation theory puts forward an emerging, highly effective, and universal such model. Its core idea is the description of the data as a linear combination of few building blocks - atoms - taken from a pre-defined dictionary of such fundamental elements.

In this course, you will learn how to use sparse representations in series of image processing tasks. We will cover applications such as denoising, deblurring, inpainting, image separation, compression, super-resolution, and more. A key feature in migrating from the theoretical model to its practical deployment is the adaptation of the dictionary to the signal. This topic, known as "dictionary learning" will be presented, along with ways to use the trained dictionaries in the above mentioned applications.

Lo que aprenderás

Omitir Lo que aprenderás
  • The importance of models in data processing, and the universality of sparse representation modeling.
  • Dictionary learning algorithms and their role in applications.
  • How to deploy sparse representations to signal and image processing tasks.

Plan de estudios

Omitir Plan de estudios

This program is composed from two separate parts:
1. Part 1: Sparse Representations in Signal and Image Processing: Fundamentals.
2. Part 2: Sparse Representations in Image Processing: From Theory to Practice.
While we recommend taking both courses, each of them can be taken independently of the other. The duration of each course is five weeks, and each part includes: (i) knowledge-check questions and discussions, (ii) series of quizzes, and (iii) Matlab programming projects. Each course will be graded separately, using the average grades of the questions/discussions [K] quizzes [Q], and projects [P], by Final-Grade = 0.1K + 0.5Q + 0.4P.
The following includes more details of the topics we will cover in the second course:

  • Overview of the field and this course.

  • Sparseland theoretic and algorithmic background.

  • Introduction to image priors and their evolution in image processing.

  • In-depth view of the Sparseland model including a geometry perspective and processing of Sparseland' signals.

  • Image deblurring and Iterative Shrinkage Thresholding Algorithm (ISTA).

  • Sparesland from an estimation point of view, including a crash-course of estimation theory.

  • The quest for a dictionary: choosing versus learning a dictionary, including basic dictionary learning algorithms: MOD and KSVD.

  • Challenges in dictionary learning and advanced methods, including the double-sparsity, unitary and signature dictionaries.

  • The image denoising problem and ways to solve it, including global and patch-based Sparseland methods.

  • Crash course on SURE estimator for parameter tuning.

  • The tasks of image separation and inpainting, including Morphological Component Analysis (MCA) and global versus patch-based treatment.

  • The single image super-resolution problem and ways to solve it using Sparseland.

  • Course summary and future research directions of the field.

Conoce a tus instructores

Michael Elad
Professor of Computer Science, Technion
Israel Institute of Technology
Alona Golts
Lecturer
IsraelX

Obtén un Certificado Verificado para destacar los conocimientos y las habilidades que adquieras
$99 USD

Ver un modelo de certificado de edX en PDF
  • Oficial y verificado

    Obtén un certificado con la firma del instructor y el logotipo de la institución para demostrar tus logros y aumentar las posibilidades de conseguir trabajo

  • Fácil de compartir

    Agrega el certificado a tu currículum o publícalo directamente en LinkedIn

  • Incentivo comprobado

    El certificado te da un motivo más para completar el curso

  • Apoya nuestra labor

    edX, una organización sin fines de lucro, se sustenta con los certificados verificados para financiar la educación gratuita para todo el mundo

¿Quién puede hacer este curso?

Lamentablemente, las personas de uno o más de los siguientes países o regiones no podrán registrarse para este curso: Irán, Cuba y la región de Crimea en Ucrania. Si bien edX consiguió licencias de la Oficina de Control de Activos Extranjeros de los EE. UU. (U.S. Office of Foreign Assets Control, OFAC) para ofrecer nuestros cursos a personas en estos países y regiones, las licencias que hemos recibido no son lo suficientemente amplias como para permitirnos dictar este curso en todas las ubicaciones. edX lamenta profundamente que las sanciones estadounidenses impidan que ofrezcamos todos nuestros cursos a cualquier persona, sin importar dónde viva.