A high performance adaptive image compression system using a generative neural network: DynAmic Neural Network II (DANN II)

Andres Rios, Mansur R. Kabuka

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The system is guaranteed theoretically to compress to any feasible rate, with as low a distortion rate as required. It also exhibits user selectable compression and error rates, ability to compress general data types, and adaptation to the data source. The compression system is based on a novel family of connectionist algorithms and generative algorithms used in conjunction with new artificial neural network models that permit the determination of a quasi-optimal architecture for compressing a given data source.

Original languageEnglish (US)
Title of host publicationProceedings - DCC 1993
Subtitle of host publicationData Compression Conference
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages204-213
Number of pages10
ISBN (Electronic)0818633921
DOIs
StatePublished - Jan 1 1993
Event1993 Data Compression Conference, DCC 1993 - Snowbird, United States
Duration: Mar 30 1993Apr 2 1993

Publication series

NameData Compression Conference Proceedings
ISSN (Print)1068-0314

Conference

Conference1993 Data Compression Conference, DCC 1993
CountryUnited States
CitySnowbird
Period3/30/934/2/93

Fingerprint

Image compression
Neural networks

ASJC Scopus subject areas

  • Computer Networks and Communications

Cite this

Rios, A., & Kabuka, M. R. (1993). A high performance adaptive image compression system using a generative neural network: DynAmic Neural Network II (DANN II). In Proceedings - DCC 1993: Data Compression Conference (pp. 204-213). [253129] (Data Compression Conference Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/DCC.1993.253129

A high performance adaptive image compression system using a generative neural network : DynAmic Neural Network II (DANN II). / Rios, Andres; Kabuka, Mansur R.

Proceedings - DCC 1993: Data Compression Conference. Institute of Electrical and Electronics Engineers Inc., 1993. p. 204-213 253129 (Data Compression Conference Proceedings).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Rios, A & Kabuka, MR 1993, A high performance adaptive image compression system using a generative neural network: DynAmic Neural Network II (DANN II). in Proceedings - DCC 1993: Data Compression Conference., 253129, Data Compression Conference Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 204-213, 1993 Data Compression Conference, DCC 1993, Snowbird, United States, 3/30/93. https://doi.org/10.1109/DCC.1993.253129
Rios A, Kabuka MR. A high performance adaptive image compression system using a generative neural network: DynAmic Neural Network II (DANN II). In Proceedings - DCC 1993: Data Compression Conference. Institute of Electrical and Electronics Engineers Inc. 1993. p. 204-213. 253129. (Data Compression Conference Proceedings). https://doi.org/10.1109/DCC.1993.253129
Rios, Andres ; Kabuka, Mansur R. / A high performance adaptive image compression system using a generative neural network : DynAmic Neural Network II (DANN II). Proceedings - DCC 1993: Data Compression Conference. Institute of Electrical and Electronics Engineers Inc., 1993. pp. 204-213 (Data Compression Conference Proceedings).
@inproceedings{baf16d7f930240529de198827a1799e9,
title = "A high performance adaptive image compression system using a generative neural network: DynAmic Neural Network II (DANN II)",
abstract = "The system is guaranteed theoretically to compress to any feasible rate, with as low a distortion rate as required. It also exhibits user selectable compression and error rates, ability to compress general data types, and adaptation to the data source. The compression system is based on a novel family of connectionist algorithms and generative algorithms used in conjunction with new artificial neural network models that permit the determination of a quasi-optimal architecture for compressing a given data source.",
author = "Andres Rios and Kabuka, {Mansur R.}",
year = "1993",
month = "1",
day = "1",
doi = "10.1109/DCC.1993.253129",
language = "English (US)",
series = "Data Compression Conference Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "204--213",
booktitle = "Proceedings - DCC 1993",

}

TY - GEN

T1 - A high performance adaptive image compression system using a generative neural network

T2 - DynAmic Neural Network II (DANN II)

AU - Rios, Andres

AU - Kabuka, Mansur R.

PY - 1993/1/1

Y1 - 1993/1/1

N2 - The system is guaranteed theoretically to compress to any feasible rate, with as low a distortion rate as required. It also exhibits user selectable compression and error rates, ability to compress general data types, and adaptation to the data source. The compression system is based on a novel family of connectionist algorithms and generative algorithms used in conjunction with new artificial neural network models that permit the determination of a quasi-optimal architecture for compressing a given data source.

AB - The system is guaranteed theoretically to compress to any feasible rate, with as low a distortion rate as required. It also exhibits user selectable compression and error rates, ability to compress general data types, and adaptation to the data source. The compression system is based on a novel family of connectionist algorithms and generative algorithms used in conjunction with new artificial neural network models that permit the determination of a quasi-optimal architecture for compressing a given data source.

UR - http://www.scopus.com/inward/record.url?scp=85063511440&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063511440&partnerID=8YFLogxK

U2 - 10.1109/DCC.1993.253129

DO - 10.1109/DCC.1993.253129

M3 - Conference contribution

AN - SCOPUS:85063511440

T3 - Data Compression Conference Proceedings

SP - 204

EP - 213

BT - Proceedings - DCC 1993

PB - Institute of Electrical and Electronics Engineers Inc.

ER -