article

A neural networks approach to image data compression

Authors:

Hamdy S. Soliman,

Mohammed OmariAuthors Info & Claims

Applied Soft Computing, Volume 6, Issue 3

Pages 258 - 271

https://doi.org/10.1016/j.asoc.2004.12.006

Published: 01 March 2006 Publication History

Abstract

We present a novel neural model for image compression called the direct classification (DC) model. The DC is a hybrid between a subset of the self-organizing Kohonen (SOK) model and the adaptive resonance theory (ART) model. The DC is a fast and efficient neural classification engine. The DC training utilizes the accuracy of the winner-takes-all feature of the SOK model and the elasticity/speed of the ART1 model. The DC engine has experimentally achieved much better results than the state-of-the-art peer image compression techniques (e.g., JPEG2000 and DjVu wavelet technology) especially in the domains of colored documents and still satellite images. We include a comprehensive analysis of the most important parameters of our DC system and their effects on system performance.

References

[1]

Soliman, H.S. and Omari, M., Image Compression using Neural Nets, Hybrid ART/Kohonen Neural Model for Document Image Compression, ANNIE 2002. November 2002. University of Missouri-Rolla, MO.

[2]

Kohonen, T., Self-Organizing Maps, Optimization Approaches, Artificial Neural Networks. 1991. Elsevier/North-Holland.

[3]

Kohonen, T., A program package for the correct application of learning vector quantization algorithms. In: IEEE International Joint Conference on Neural Networks,

[4]

Hankerson, D., Harris, G.A. and Johnson Jr., P.D., Introduction to Information Theory and Data Compression. 1998. CRC Press.

[5]

Erwin, E. and Obermayer, K., Self-organizing maps: ordering, convergence properties and energy functions. Biol. Cybern. v67. 35-45.

Digital Library

[6]

Nasrabadi, N.M. and Katsaggelos, A.K., . In: Applications of Artificial Neural Network in Image Processing III,

[7]

Nasrabadi, N.M. and Katsaggelos, A.K., . In: Applications of Artificial Neural Networks in Image Processing V,

[8]

Zurada, J.M., Introduction to Artificial Neural System. 1995. PWS Publishing Company.

[9]

Ramakrishnan, S., Rose, K. and Gersho, A., Constrained-Storage Vector Quantization with a Universal Codebook. 1998. IEEE.

[10]

Soliman, H.S. and Omari, M., Universal Codebook versus Local Codebook: Applications of Image Compression Using AVQ Theory, ANNIE 2002. November 2002. University of Missouri-Rolla, MO.

[11]

Hecht-Nielson, R., Counterpropagation networks. Appl. Opt. v26. 4979-4984.

[12]

Answers to frequently asked questions about DjVu, http://www.djvuzone.org/support/faq.html.

[13]

Image compression from DCT to wavelets: a review, http://www.abmedia.dk/video/coding.htm.

[14]

Vishwanathan, N. and Wunsch, D.C., ART/SOFM: a hybrid approach to the TSP. In: INNS-IEEE International Joint Conference on Neural Networks (IJCNN'01), vol. 4,

[15]

The Art of Scientific Computing. 1986-1992. Cambridge University Press.

[16]

Examples of the application of direct classification approach in image compression, www.cs.nmt.edu/~hss/dc.htm.

Cited By

Bartecki K(2024)Classical vs. neural network-based PCA approaches for lossy image compressionApplied Soft Computing10.1016/j.asoc.2024.111721161:COnline publication date: 1-Aug-2024
https://dl.acm.org/doi/10.1016/j.asoc.2024.111721
Khashman ADimililer K(2018)Image compression using neural networks and haar waveletWSEAS Transactions on Signal Processing10.5555/1466835.14668444:5(330-339)Online publication date: 15-Dec-2018
https://dl.acm.org/doi/10.5555/1466835.1466844
Lee E(2018)An incremental adaptive neural network model for online noisy data regression and its application to compartment fire studiesApplied Soft Computing10.1016/j.asoc.2010.01.00211:1(827-836)Online publication date: 27-Dec-2018
https://dl.acm.org/doi/10.1016/j.asoc.2010.01.002

A neural networks approach to image data compression
1. Computing methodologies
  1. Computer graphics
  2. Machine learning
    1. Machine learning approaches
2. Information systems
  1. Data management systems
    1. Data structures
      1. Data layout

Recommendations

Image Compression using Artificial Neural Networks
ICMLC '10: Proceedings of the 2010 Second International Conference on Machine Learning and Computing

This paper explores the application of artificial neural networks to image compression. An image compressing algorithm based on Back Propagation (BP) network is developed after image pre-processing. By implementing the proposed scheme the influence of ...
Conditional Entropy Coding of VQ Indexes for Image Compression
DCC '97: Proceedings of the Conference on Data Compression

Vector quantization (VQ) is a source coding methodology with provable rate-distortion optimality. However, despite more than two decades of intensive research, VQ theoretical promise is yet to be fully realized in image compression practice. Restricted ...
Haar image compression using a neural network
ACC'08: Proceedings of the WSEAS International Conference on Applied Computing Conference

Wavelet Transform is one of the most popular methods applied in image compression. Wavelet-based image compression provides substantial improvements in picture quality at higher compression ratios. Haar wavelet transform based compression is one of the ...

Comments

Information & Contributors

Information

Published In

cover image Applied Soft Computing

Applied Soft Computing Volume 6, Issue 3

March, 2006

112 pages

ISSN:1568-4946

Issue’s Table of Contents

Copyright © Elsevier B.V. © 2005.

Publisher

Elsevier Science Publishers B. V.

Netherlands

Publication History

Published: 01 March 2006

Author Tags

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

2
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 25 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

Bartecki K(2024)Classical vs. neural network-based PCA approaches for lossy image compressionApplied Soft Computing10.1016/j.asoc.2024.111721161:COnline publication date: 1-Aug-2024
https://dl.acm.org/doi/10.1016/j.asoc.2024.111721
Khashman ADimililer K(2018)Image compression using neural networks and haar waveletWSEAS Transactions on Signal Processing10.5555/1466835.14668444:5(330-339)Online publication date: 15-Dec-2018
https://dl.acm.org/doi/10.5555/1466835.1466844
Lee E(2018)An incremental adaptive neural network model for online noisy data regression and its application to compartment fire studiesApplied Soft Computing10.1016/j.asoc.2010.01.00211:1(827-836)Online publication date: 27-Dec-2018
https://dl.acm.org/doi/10.1016/j.asoc.2010.01.002

View Options

View options

Figures

Tables

Media

View Issue’s Table of Contents