Grayscale and colour image Codec based on matching pursuit in the spatio-frequency domain

Ryszard Maciol, Yuan Yuan, Ian Nabney

Research output: Book/ReportOther report

Abstract

This report presents and evaluates a novel idea for scalable lossy colour image coding with Matching Pursuit (MP) performed in a transform domain. The benefits of the idea of MP performed in the transform domain are analysed in detail. The main contribution of this work is extending MP with wavelets to colour coding and proposing a coding method. We exploit correlations between image subbands after wavelet transformation in RGB colour space. Then, a new and simple quantisation and coding scheme of colour MP decomposition based on Run Length Encoding (RLE), inspired by the idea of coding indexes in relational databases, is applied. As a final coding step arithmetic coding is used assuming uniform distributions of MP atom parameters. The target application is compression at low and medium bit-rates. Coding performance is compared to JPEG 2000 showing the potential to outperform the latter with more sophisticated than uniform data models for arithmetic coder. The results are presented for grayscale and colour coding of 12 standard test images.
Original languageEnglish
PublisherAston University
Number of pages19
Publication statusUnpublished - 11 Apr 2011

Fingerprint

Color
Color matching
Image coding
Data structures
Decomposition
Atoms

Keywords

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

Cite this

Maciol, R., Yuan, Y., & Nabney, I. (2011). Grayscale and colour image Codec based on matching pursuit in the spatio-frequency domain. Aston University.
Maciol, Ryszard ; Yuan, Yuan ; Nabney, Ian. / Grayscale and colour image Codec based on matching pursuit in the spatio-frequency domain. Aston University, 2011. 19 p.
@book{e6ced01b94c04f80b6c25aaf70c0e8c5,
title = "Grayscale and colour image Codec based on matching pursuit in the spatio-frequency domain",
abstract = "This report presents and evaluates a novel idea for scalable lossy colour image coding with Matching Pursuit (MP) performed in a transform domain. The benefits of the idea of MP performed in the transform domain are analysed in detail. The main contribution of this work is extending MP with wavelets to colour coding and proposing a coding method. We exploit correlations between image subbands after wavelet transformation in RGB colour space. Then, a new and simple quantisation and coding scheme of colour MP decomposition based on Run Length Encoding (RLE), inspired by the idea of coding indexes in relational databases, is applied. As a final coding step arithmetic coding is used assuming uniform distributions of MP atom parameters. The target application is compression at low and medium bit-rates. Coding performance is compared to JPEG 2000 showing the potential to outperform the latter with more sophisticated than uniform data models for arithmetic coder. The results are presented for grayscale and colour coding of 12 standard test images.",
keywords = "colour image coding, matching pursuit, wavelets, run length encoding",
author = "Ryszard Maciol and Yuan Yuan and Ian Nabney",
year = "2011",
month = "4",
day = "11",
language = "English",
publisher = "Aston University",

}

Grayscale and colour image Codec based on matching pursuit in the spatio-frequency domain. / Maciol, Ryszard; Yuan, Yuan; Nabney, Ian.

Aston University, 2011. 19 p.

Research output: Book/ReportOther report

TY - BOOK

T1 - Grayscale and colour image Codec based on matching pursuit in the spatio-frequency domain

AU - Maciol, Ryszard

AU - Yuan, Yuan

AU - Nabney, Ian

PY - 2011/4/11

Y1 - 2011/4/11

N2 - This report presents and evaluates a novel idea for scalable lossy colour image coding with Matching Pursuit (MP) performed in a transform domain. The benefits of the idea of MP performed in the transform domain are analysed in detail. The main contribution of this work is extending MP with wavelets to colour coding and proposing a coding method. We exploit correlations between image subbands after wavelet transformation in RGB colour space. Then, a new and simple quantisation and coding scheme of colour MP decomposition based on Run Length Encoding (RLE), inspired by the idea of coding indexes in relational databases, is applied. As a final coding step arithmetic coding is used assuming uniform distributions of MP atom parameters. The target application is compression at low and medium bit-rates. Coding performance is compared to JPEG 2000 showing the potential to outperform the latter with more sophisticated than uniform data models for arithmetic coder. The results are presented for grayscale and colour coding of 12 standard test images.

AB - This report presents and evaluates a novel idea for scalable lossy colour image coding with Matching Pursuit (MP) performed in a transform domain. The benefits of the idea of MP performed in the transform domain are analysed in detail. The main contribution of this work is extending MP with wavelets to colour coding and proposing a coding method. We exploit correlations between image subbands after wavelet transformation in RGB colour space. Then, a new and simple quantisation and coding scheme of colour MP decomposition based on Run Length Encoding (RLE), inspired by the idea of coding indexes in relational databases, is applied. As a final coding step arithmetic coding is used assuming uniform distributions of MP atom parameters. The target application is compression at low and medium bit-rates. Coding performance is compared to JPEG 2000 showing the potential to outperform the latter with more sophisticated than uniform data models for arithmetic coder. The results are presented for grayscale and colour coding of 12 standard test images.

KW - colour image coding

KW - matching pursuit

KW - wavelets

KW - run length encoding

M3 - Other report

BT - Grayscale and colour image Codec based on matching pursuit in the spatio-frequency domain

PB - Aston University

ER -