Applying neural networks to colour image data compression

K.R.L. Godfrey; Y. Attikiouzel

doi:10.1109/TENCON.1992.272008

Back

Applying neural networks to colour image data compression

Conference paper

Open access

Applying neural networks to colour image data compression

K.R.L. Godfrey and Y. Attikiouzel

TENCON'92 - Technology Enabling Tomorrow, pp.545-549

IEEE

TENCON '92. IEEE Region 10 International Conference, ''Technology Enabling Tomorrow : Computers, Communications and Automation towards the 21st Century.' (Melbourne, Australia, 11/11/1992–13/11/1992)

1992

DOI: https://doi.org/10.1109/TENCON.1992.272008

Files and links (2)

pdf

colour_image_data_compression.pdfDownload View

Published (Version of Record) Open Access

url

Link to Published Version *Subscription may be requiredView

Abstract

A self-organizing neural network is used to achieve color image segmentation and image data compression, with an adaptive codebook for faster training. Neural network architectures are well-suited to high speed processing because they are massively parallel. By adding an external threshold decision, a compression network can build its codebook adaptively and therefore speed the compression process. A 24-bit color image is compressed to 6.39 bit with virtually no visual degradation.

Details

Title: Applying neural networks to colour image data compression
Authors/Creators: K.R.L. Godfrey (Author/Creator)
Y. Attikiouzel (Author/Creator) - The University of Western Australia
Publication Details: TENCON'92 - Technology Enabling Tomorrow, pp.545-549
Conference: TENCON '92. IEEE Region 10 International Conference, ''Technology Enabling Tomorrow : Computers, Communications and Automation towards the 21st Century.' (Melbourne, Australia, 11/11/1992–13/11/1992)
Publisher: IEEE
Identifiers: 991005545515907891
Murdoch Affiliation: Murdoch University
Language: English
Resource Type: Conference paper

Metrics

153 File views/ downloads

51 Record Views