Predictive vector quantization using neural networks

M. R. Hashemi; T. H. Yeap; S. Panchanathan

doi:10.1117/12.269776

Predictive vector quantization using neural networks

M. R. Hashemi, T. H. Yeap, S. Panchanathan

Research output: Contribution to journal › Conference article › peer-review

Abstract

In this paper we propose a new scalable predictive vector quantization (PVQ) technique for image and video compression. This technique has been implemented using neural networks. A Kohonen self organized feature map is used to implement the vector quantizer, while a multilayer perceptron implements the predictor. Simulation results demonstrate that the proposed technique provides a 5-10% improvement in coding performance over the existing neural networks based PVQ techniques.

Original language	English (US)
Pages (from-to)	14-20
Number of pages	7
Journal	Proceedings of SPIE - The International Society for Optical Engineering
Volume	3030
DOIs	https://doi.org/10.1117/12.269776
State	Published - Apr 1 1997
Externally published	Yes
Event	Applications of Artificial Neural Networks in Image Processing II 1997 - San Jose, United States Duration: Feb 8 1997 → Feb 14 1997

Keywords

Image compression
Multimedia
Neural networks
Predictive vector quantization

ASJC Scopus subject areas

Electronic, Optical and Magnetic Materials
Condensed Matter Physics
Computer Science Applications
Applied Mathematics
Electrical and Electronic Engineering

Access to Document

10.1117/12.269776

Cite this

@article{6f9a7a6e90f54d53b7bd4f65dd6cfbe2,

title = "Predictive vector quantization using neural networks",

abstract = "In this paper we propose a new scalable predictive vector quantization (PVQ) technique for image and video compression. This technique has been implemented using neural networks. A Kohonen self organized feature map is used to implement the vector quantizer, while a multilayer perceptron implements the predictor. Simulation results demonstrate that the proposed technique provides a 5-10% improvement in coding performance over the existing neural networks based PVQ techniques.",

keywords = "Image compression, Multimedia, Neural networks, Predictive vector quantization",

author = "Hashemi, {M. R.} and Yeap, {T. H.} and S. Panchanathan",

note = "Funding Information: The authors would like to thank the Ministry of Culture and Higher Education of the Islamic Republic of Iran for the Funding Information: The authors would like to thank the Ministry of Culture and Higher Education of the Islamic Republic of Iran for the financial assistance for student support. Publisher Copyright: {\textcopyright} 1997 SPIE. All rights reserved.; Applications of Artificial Neural Networks in Image Processing II 1997 ; Conference date: 08-02-1997 Through 14-02-1997",

year = "1997",

month = apr,

day = "1",

doi = "10.1117/12.269776",

language = "English (US)",

volume = "3030",

pages = "14--20",

journal = "Proceedings of SPIE - The International Society for Optical Engineering",

issn = "0277-786X",

publisher = "SPIE",

}

TY - JOUR

T1 - Predictive vector quantization using neural networks

AU - Hashemi, M. R.

AU - Yeap, T. H.

AU - Panchanathan, S.

N1 - Funding Information: The authors would like to thank the Ministry of Culture and Higher Education of the Islamic Republic of Iran for the Funding Information: The authors would like to thank the Ministry of Culture and Higher Education of the Islamic Republic of Iran for the financial assistance for student support. Publisher Copyright: © 1997 SPIE. All rights reserved.

PY - 1997/4/1

Y1 - 1997/4/1

N2 - In this paper we propose a new scalable predictive vector quantization (PVQ) technique for image and video compression. This technique has been implemented using neural networks. A Kohonen self organized feature map is used to implement the vector quantizer, while a multilayer perceptron implements the predictor. Simulation results demonstrate that the proposed technique provides a 5-10% improvement in coding performance over the existing neural networks based PVQ techniques.

AB - In this paper we propose a new scalable predictive vector quantization (PVQ) technique for image and video compression. This technique has been implemented using neural networks. A Kohonen self organized feature map is used to implement the vector quantizer, while a multilayer perceptron implements the predictor. Simulation results demonstrate that the proposed technique provides a 5-10% improvement in coding performance over the existing neural networks based PVQ techniques.

KW - Image compression

KW - Multimedia

KW - Neural networks

KW - Predictive vector quantization

UR - http://www.scopus.com/inward/record.url?scp=85076429062&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85076429062&partnerID=8YFLogxK

U2 - 10.1117/12.269776

DO - 10.1117/12.269776

M3 - Conference article

AN - SCOPUS:85076429062

SN - 0277-786X

VL - 3030

SP - 14

EP - 20

JO - Proceedings of SPIE - The International Society for Optical Engineering

JF - Proceedings of SPIE - The International Society for Optical Engineering

T2 - Applications of Artificial Neural Networks in Image Processing II 1997

Y2 - 8 February 1997 through 14 February 1997

ER -

Predictive vector quantization using neural networks

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this