Image compression with a dynamic autoassociative neural network

Andres Rios, Mansur R. Kabuka

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

2 Scopus citations

Abstract

Image compression using neural networks has been attempted with some promise. Among the architectures, feedforward backpropagation networks (FFBPN) have been used in several attempts. We propose an architecture and an improved training method to attempt to solve the shortcomings of traditional data compression based on feedforward networks - the dynamic autoassociation neural network (DANN). The results of several tasks presented to DANN based compression are compared with the performance of FFBPN based system. These results indicate that DANN is superior to FFBPN for data compression.

Original languageEnglish
Title of host publicationIntelligent Engineering Systems Through Artificial Neural Networks
EditorsC.H. Dagli, L.I. Burke, Y.C. Shin
Place of PublicationFairfield, NJ, United States
PublisherASME
Pages503-510
Number of pages8
Volume2
StatePublished - Dec 1 1992
EventProceedings of the 1992 Artificial Neural Networks in Engineering, ANNIE'92 - St.Louis, MO, USA
Duration: Nov 15 1992Nov 18 1992

Other

OtherProceedings of the 1992 Artificial Neural Networks in Engineering, ANNIE'92
CitySt.Louis, MO, USA
Period11/15/9211/18/92

ASJC Scopus subject areas

  • Software

Fingerprint Dive into the research topics of 'Image compression with a dynamic autoassociative neural network'. Together they form a unique fingerprint.

  • Cite this

    Rios, A., & Kabuka, M. R. (1992). Image compression with a dynamic autoassociative neural network. In C. H. Dagli, L. I. Burke, & Y. C. Shin (Eds.), Intelligent Engineering Systems Through Artificial Neural Networks (Vol. 2, pp. 503-510). ASME.