Rate-distortion modeling for multiscale binary shape coding based on Markov random fields

Anthony Vetro, Yao Wang, Huifang Sun

Research output: Contribution to journalArticle

Abstract

The purpose of this paper it to explore the relationship between the rate-distortion characteristics of multiscale binary shape and Markov random field (MRF) parameters. For coding, it is important that the input parameters that will be used to define this relationship be able to distinguish between the same shape at different scales, as well as different shapes at the same scale. In this work, we consider an MRF model, referred to as the Chien model, which accounts for high-order spatial interactions among pixels. We propose to use the statistical moments of the Chien model as input to a neural network to accurately predict the rate and distortion of the binary shape when coded at various scales.

Original languageEnglish (US)
Pages (from-to)356-364
Number of pages9
JournalIEEE Transactions on Image Processing
Volume12
Issue number3
DOIs
StatePublished - Mar 2003

Fingerprint

Rate-distortion
Random Field
Coding
Binary
Modeling
Pixels
Neural networks
Pixel
Model
Neural Networks
Higher Order
Moment
Predict
Interaction
Relationships

Keywords

  • Markov random fields
  • MPEG-4
  • Multiscale
  • Rate distortion
  • Shape coding

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition
  • Software
  • Electrical and Electronic Engineering
  • Theoretical Computer Science

Cite this

Rate-distortion modeling for multiscale binary shape coding based on Markov random fields. / Vetro, Anthony; Wang, Yao; Sun, Huifang.

In: IEEE Transactions on Image Processing, Vol. 12, No. 3, 03.2003, p. 356-364.

Research output: Contribution to journalArticle

@article{5aa7cc69edb94b7eb0f51a22dd69521a,
title = "Rate-distortion modeling for multiscale binary shape coding based on Markov random fields",
abstract = "The purpose of this paper it to explore the relationship between the rate-distortion characteristics of multiscale binary shape and Markov random field (MRF) parameters. For coding, it is important that the input parameters that will be used to define this relationship be able to distinguish between the same shape at different scales, as well as different shapes at the same scale. In this work, we consider an MRF model, referred to as the Chien model, which accounts for high-order spatial interactions among pixels. We propose to use the statistical moments of the Chien model as input to a neural network to accurately predict the rate and distortion of the binary shape when coded at various scales.",
keywords = "Markov random fields, MPEG-4, Multiscale, Rate distortion, Shape coding",
author = "Anthony Vetro and Yao Wang and Huifang Sun",
year = "2003",
month = "3",
doi = "10.1109/TIP.2003.809016",
language = "English (US)",
volume = "12",
pages = "356--364",
journal = "IEEE Transactions on Image Processing",
issn = "1057-7149",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "3",

}

TY - JOUR

T1 - Rate-distortion modeling for multiscale binary shape coding based on Markov random fields

AU - Vetro, Anthony

AU - Wang, Yao

AU - Sun, Huifang

PY - 2003/3

Y1 - 2003/3

N2 - The purpose of this paper it to explore the relationship between the rate-distortion characteristics of multiscale binary shape and Markov random field (MRF) parameters. For coding, it is important that the input parameters that will be used to define this relationship be able to distinguish between the same shape at different scales, as well as different shapes at the same scale. In this work, we consider an MRF model, referred to as the Chien model, which accounts for high-order spatial interactions among pixels. We propose to use the statistical moments of the Chien model as input to a neural network to accurately predict the rate and distortion of the binary shape when coded at various scales.

AB - The purpose of this paper it to explore the relationship between the rate-distortion characteristics of multiscale binary shape and Markov random field (MRF) parameters. For coding, it is important that the input parameters that will be used to define this relationship be able to distinguish between the same shape at different scales, as well as different shapes at the same scale. In this work, we consider an MRF model, referred to as the Chien model, which accounts for high-order spatial interactions among pixels. We propose to use the statistical moments of the Chien model as input to a neural network to accurately predict the rate and distortion of the binary shape when coded at various scales.

KW - Markov random fields

KW - MPEG-4

KW - Multiscale

KW - Rate distortion

KW - Shape coding

UR - http://www.scopus.com/inward/record.url?scp=0038192253&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0038192253&partnerID=8YFLogxK

U2 - 10.1109/TIP.2003.809016

DO - 10.1109/TIP.2003.809016

M3 - Article

C2 - 18237914

AN - SCOPUS:0038192253

VL - 12

SP - 356

EP - 364

JO - IEEE Transactions on Image Processing

JF - IEEE Transactions on Image Processing

SN - 1057-7149

IS - 3

ER -