Colour image coding with matching pursuit in the spatio-frequency domain

Ryszard Maciol, Yuan Yuan, Ian T. Nabney

Research output: Contribution to journalArticle

Abstract

We present and evaluate a novel idea for scalable lossy colour image coding with Matching Pursuit (MP) performed in a transform domain. The idea is to exploit correlations in RGB colour space between image subbands after wavelet transformation rather than in the spatial domain. We propose a simple quantisation and coding scheme of colour MP decomposition based on Run Length Encoding (RLE) which can achieve comparable performance to JPEG 2000 even though the latter utilises careful data modelling at the coding stage. Thus, the obtained image representation has the potential to outperform JPEG 2000 with a more sophisticated coding algorithm.
Original languageEnglish
Pages (from-to)306-317
Number of pages12
JournalLecture Notes in Computer Science
Volume6978
DOIs
Publication statusPublished - Sep 2011
EventImage Analysis and Processing - ICIAP 2011 - Ravenna (IT)
Duration: 14 Sep 201116 Sep 2011

Fingerprint

Matching Pursuit
Image Coding
Color Image
Image coding
Frequency Domain
JPEG2000
Coding
Color
Color matching
Run-length Encoding
Data structures
Wavelet Transformation
Image Representation
Data Modeling
Color Space
Decomposition
Quantization
Transform
Decompose
Evaluate

Bibliographical note

The original publication is available at www.springerlink.com

Keywords

  • colour image coding
  • matching pursuit
  • wavelets
  • run length encoding

Cite this

Maciol, Ryszard ; Yuan, Yuan ; Nabney, Ian T. / Colour image coding with matching pursuit in the spatio-frequency domain. In: Lecture Notes in Computer Science. 2011 ; Vol. 6978. pp. 306-317.
@article{c7d3c32b1f214d7ba270cf71d111a9a7,
title = "Colour image coding with matching pursuit in the spatio-frequency domain",
abstract = "We present and evaluate a novel idea for scalable lossy colour image coding with Matching Pursuit (MP) performed in a transform domain. The idea is to exploit correlations in RGB colour space between image subbands after wavelet transformation rather than in the spatial domain. We propose a simple quantisation and coding scheme of colour MP decomposition based on Run Length Encoding (RLE) which can achieve comparable performance to JPEG 2000 even though the latter utilises careful data modelling at the coding stage. Thus, the obtained image representation has the potential to outperform JPEG 2000 with a more sophisticated coding algorithm.",
keywords = "colour image coding, matching pursuit, wavelets, run length encoding",
author = "Ryszard Maciol and Yuan Yuan and Nabney, {Ian T.}",
note = "The original publication is available at www.springerlink.com",
year = "2011",
month = "9",
doi = "10.1007/978-3-642-24085-0",
language = "English",
volume = "6978",
pages = "306--317",
journal = "Lecture Notes in Computer Science",
issn = "0302-9743",
publisher = "Springer",

}

Colour image coding with matching pursuit in the spatio-frequency domain. / Maciol, Ryszard; Yuan, Yuan; Nabney, Ian T.

In: Lecture Notes in Computer Science, Vol. 6978, 09.2011, p. 306-317.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Colour image coding with matching pursuit in the spatio-frequency domain

AU - Maciol, Ryszard

AU - Yuan, Yuan

AU - Nabney, Ian T.

N1 - The original publication is available at www.springerlink.com

PY - 2011/9

Y1 - 2011/9

N2 - We present and evaluate a novel idea for scalable lossy colour image coding with Matching Pursuit (MP) performed in a transform domain. The idea is to exploit correlations in RGB colour space between image subbands after wavelet transformation rather than in the spatial domain. We propose a simple quantisation and coding scheme of colour MP decomposition based on Run Length Encoding (RLE) which can achieve comparable performance to JPEG 2000 even though the latter utilises careful data modelling at the coding stage. Thus, the obtained image representation has the potential to outperform JPEG 2000 with a more sophisticated coding algorithm.

AB - We present and evaluate a novel idea for scalable lossy colour image coding with Matching Pursuit (MP) performed in a transform domain. The idea is to exploit correlations in RGB colour space between image subbands after wavelet transformation rather than in the spatial domain. We propose a simple quantisation and coding scheme of colour MP decomposition based on Run Length Encoding (RLE) which can achieve comparable performance to JPEG 2000 even though the latter utilises careful data modelling at the coding stage. Thus, the obtained image representation has the potential to outperform JPEG 2000 with a more sophisticated coding algorithm.

KW - colour image coding

KW - matching pursuit

KW - wavelets

KW - run length encoding

UR - http://www.scopus.com/inward/record.url?scp=80052971883&partnerID=8YFLogxK

U2 - 10.1007/978-3-642-24085-0

DO - 10.1007/978-3-642-24085-0

M3 - Article

VL - 6978

SP - 306

EP - 317

JO - Lecture Notes in Computer Science

JF - Lecture Notes in Computer Science

SN - 0302-9743

ER -