Image understanding using sparse representations

Jayaraman J. Thiagarajan, Karthikeyan Natesan Ramamurthy, Pavan Turaga, Andreas Spanias

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

Download Free Sample Image understanding has been playing an increasingly crucial role in several inverse problems and computer vision. Sparse models form an important component in image understanding, since they emulate the activity of neural receptors in the primary visual cortex of the human brain. Sparse methods have been utilized in several learning problems because of their ability to provide parsimonious, interpretable, and efficient models. Exploiting the sparsity of natural signals has led to advances in several application areas including image compression, denoising, inpainting, compressed sensing, blind source separation, super-resolution, and classification. The primary goal of this book is to present the theory and algorithmic considerations in using sparse models for image understanding and computer vision applications. To this end, algorithms for obtaining sparse representations and their performance guarantees are discussed in the initial chapters. Furthermore, approaches for designing overcomplete, data-adapted dictionaries to model natural images are described. The development of theory behind dictionary learning involves exploring its connection to unsupervised clustering and analyzing its generalization characteristics using principles from statistical learning theory. An exciting application area that has benefited extensively from the theory of sparse representations is compressed sensing of image and video data. Theory and algorithms pertinent to measurement design, recovery, and model-based compressed sensing are presented. The paradigm of sparse models, when suitably integrated with powerful machine learning frameworks, can lead to advances in computer vision applications such as object recognition, clustering, segmentation, and activity recognition. Frameworks that enhance the performance of sparse models in such applications by imposing constraints based on the prior discriminatory information and the underlying geometrical structure, and kernelizing the sparse coding and dictionary learning methods are presented. In addition to presenting theoretical fundamentals in sparse learning, this book provides a platform for interested readers to explore the vastly growing application domains of sparse representations.

Original languageEnglish (US)
Pages (from-to)1-120
Number of pages120
JournalSynthesis Lectures on Image, Video, and Multimedia Processing
Volume15
DOIs
StatePublished - Apr 24 2014

Fingerprint

Image understanding
dictionaries
Compressed sensing
learning
computer vision
Computer vision
Glossaries
learning theory
video data
machine learning
Blind source separation
cortexes
Object recognition
readers
Image compression
Inverse problems
brain
Learning systems
Brain
coding

Keywords

  • Clustering
  • Compressed sensing
  • Dictionary learning
  • Graph embedding
  • Image classification
  • Image reconstruction
  • Image recovery
  • Kernel methods
  • Natural images
  • Sparse representations

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Signal Processing
  • Computer Graphics and Computer-Aided Design
  • Atomic and Molecular Physics, and Optics

Cite this

Image understanding using sparse representations. / Thiagarajan, Jayaraman J.; Ramamurthy, Karthikeyan Natesan; Turaga, Pavan; Spanias, Andreas.

In: Synthesis Lectures on Image, Video, and Multimedia Processing, Vol. 15, 24.04.2014, p. 1-120.

Research output: Contribution to journalArticle

Thiagarajan, Jayaraman J. ; Ramamurthy, Karthikeyan Natesan ; Turaga, Pavan ; Spanias, Andreas. / Image understanding using sparse representations. In: Synthesis Lectures on Image, Video, and Multimedia Processing. 2014 ; Vol. 15. pp. 1-120.
@article{b204b002dc1e4856b46919c1274d3e99,
title = "Image understanding using sparse representations",
abstract = "Download Free Sample Image understanding has been playing an increasingly crucial role in several inverse problems and computer vision. Sparse models form an important component in image understanding, since they emulate the activity of neural receptors in the primary visual cortex of the human brain. Sparse methods have been utilized in several learning problems because of their ability to provide parsimonious, interpretable, and efficient models. Exploiting the sparsity of natural signals has led to advances in several application areas including image compression, denoising, inpainting, compressed sensing, blind source separation, super-resolution, and classification. The primary goal of this book is to present the theory and algorithmic considerations in using sparse models for image understanding and computer vision applications. To this end, algorithms for obtaining sparse representations and their performance guarantees are discussed in the initial chapters. Furthermore, approaches for designing overcomplete, data-adapted dictionaries to model natural images are described. The development of theory behind dictionary learning involves exploring its connection to unsupervised clustering and analyzing its generalization characteristics using principles from statistical learning theory. An exciting application area that has benefited extensively from the theory of sparse representations is compressed sensing of image and video data. Theory and algorithms pertinent to measurement design, recovery, and model-based compressed sensing are presented. The paradigm of sparse models, when suitably integrated with powerful machine learning frameworks, can lead to advances in computer vision applications such as object recognition, clustering, segmentation, and activity recognition. Frameworks that enhance the performance of sparse models in such applications by imposing constraints based on the prior discriminatory information and the underlying geometrical structure, and kernelizing the sparse coding and dictionary learning methods are presented. In addition to presenting theoretical fundamentals in sparse learning, this book provides a platform for interested readers to explore the vastly growing application domains of sparse representations.",
keywords = "Clustering, Compressed sensing, Dictionary learning, Graph embedding, Image classification, Image reconstruction, Image recovery, Kernel methods, Natural images, Sparse representations",
author = "Thiagarajan, {Jayaraman J.} and Ramamurthy, {Karthikeyan Natesan} and Pavan Turaga and Andreas Spanias",
year = "2014",
month = "4",
day = "24",
doi = "10.2200/S00563ED1V01Y201401IVM015",
language = "English (US)",
volume = "15",
pages = "1--120",
journal = "Synthesis Lectures on Image, Video, and Multimedia Processing",
issn = "1559-8136",
publisher = "Morgan and Claypool Publishers",

}

TY - JOUR

T1 - Image understanding using sparse representations

AU - Thiagarajan, Jayaraman J.

AU - Ramamurthy, Karthikeyan Natesan

AU - Turaga, Pavan

AU - Spanias, Andreas

PY - 2014/4/24

Y1 - 2014/4/24

N2 - Download Free Sample Image understanding has been playing an increasingly crucial role in several inverse problems and computer vision. Sparse models form an important component in image understanding, since they emulate the activity of neural receptors in the primary visual cortex of the human brain. Sparse methods have been utilized in several learning problems because of their ability to provide parsimonious, interpretable, and efficient models. Exploiting the sparsity of natural signals has led to advances in several application areas including image compression, denoising, inpainting, compressed sensing, blind source separation, super-resolution, and classification. The primary goal of this book is to present the theory and algorithmic considerations in using sparse models for image understanding and computer vision applications. To this end, algorithms for obtaining sparse representations and their performance guarantees are discussed in the initial chapters. Furthermore, approaches for designing overcomplete, data-adapted dictionaries to model natural images are described. The development of theory behind dictionary learning involves exploring its connection to unsupervised clustering and analyzing its generalization characteristics using principles from statistical learning theory. An exciting application area that has benefited extensively from the theory of sparse representations is compressed sensing of image and video data. Theory and algorithms pertinent to measurement design, recovery, and model-based compressed sensing are presented. The paradigm of sparse models, when suitably integrated with powerful machine learning frameworks, can lead to advances in computer vision applications such as object recognition, clustering, segmentation, and activity recognition. Frameworks that enhance the performance of sparse models in such applications by imposing constraints based on the prior discriminatory information and the underlying geometrical structure, and kernelizing the sparse coding and dictionary learning methods are presented. In addition to presenting theoretical fundamentals in sparse learning, this book provides a platform for interested readers to explore the vastly growing application domains of sparse representations.

AB - Download Free Sample Image understanding has been playing an increasingly crucial role in several inverse problems and computer vision. Sparse models form an important component in image understanding, since they emulate the activity of neural receptors in the primary visual cortex of the human brain. Sparse methods have been utilized in several learning problems because of their ability to provide parsimonious, interpretable, and efficient models. Exploiting the sparsity of natural signals has led to advances in several application areas including image compression, denoising, inpainting, compressed sensing, blind source separation, super-resolution, and classification. The primary goal of this book is to present the theory and algorithmic considerations in using sparse models for image understanding and computer vision applications. To this end, algorithms for obtaining sparse representations and their performance guarantees are discussed in the initial chapters. Furthermore, approaches for designing overcomplete, data-adapted dictionaries to model natural images are described. The development of theory behind dictionary learning involves exploring its connection to unsupervised clustering and analyzing its generalization characteristics using principles from statistical learning theory. An exciting application area that has benefited extensively from the theory of sparse representations is compressed sensing of image and video data. Theory and algorithms pertinent to measurement design, recovery, and model-based compressed sensing are presented. The paradigm of sparse models, when suitably integrated with powerful machine learning frameworks, can lead to advances in computer vision applications such as object recognition, clustering, segmentation, and activity recognition. Frameworks that enhance the performance of sparse models in such applications by imposing constraints based on the prior discriminatory information and the underlying geometrical structure, and kernelizing the sparse coding and dictionary learning methods are presented. In addition to presenting theoretical fundamentals in sparse learning, this book provides a platform for interested readers to explore the vastly growing application domains of sparse representations.

KW - Clustering

KW - Compressed sensing

KW - Dictionary learning

KW - Graph embedding

KW - Image classification

KW - Image reconstruction

KW - Image recovery

KW - Kernel methods

KW - Natural images

KW - Sparse representations

UR - http://www.scopus.com/inward/record.url?scp=84899797296&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84899797296&partnerID=8YFLogxK

U2 - 10.2200/S00563ED1V01Y201401IVM015

DO - 10.2200/S00563ED1V01Y201401IVM015

M3 - Article

VL - 15

SP - 1

EP - 120

JO - Synthesis Lectures on Image, Video, and Multimedia Processing

JF - Synthesis Lectures on Image, Video, and Multimedia Processing

SN - 1559-8136

ER -