TU Darmstadt / ULB / TUbiblio

Image Compression with Self-Organizing Networks

Freisleben, Bernd and Mengel, Maximilian (1993):
Image Compression with Self-Organizing Networks.
Springer, Berlin, Heidelberg, In: New Trends in Neural Computation. Proceedings, In: Lecture Notes in Computer Science (LNCS); 686, [Conference or Workshop Item]

Abstract

In this paper we evaluate and compare the performance of self-organizing neural networks applied to the task of image compression. The networks investigated are two-layered architectures with linear neurons, and variants of Hebbian learning rules are used to reduce the dimensionality of the inputs while preserving a maximum of information in the output units. Although in theory all networks considered are effectively equivalent to performing the Karhunen-Loeve transform, which is the optimal image compression method in the sense that it allows linear reconstruction of the input information with minimal squared error, the results obtained in practice reveal significant differences between the networks. An experimental study has been conducted to demonstrate these differences and thus some light is shed on the suitability of self-organizing neural networks for image compression, particularly in comparison to more conventional methods.

Item Type: Conference or Workshop Item
Erschienen: 1993
Creators: Freisleben, Bernd and Mengel, Maximilian
Title: Image Compression with Self-Organizing Networks
Language: German
Abstract:

In this paper we evaluate and compare the performance of self-organizing neural networks applied to the task of image compression. The networks investigated are two-layered architectures with linear neurons, and variants of Hebbian learning rules are used to reduce the dimensionality of the inputs while preserving a maximum of information in the output units. Although in theory all networks considered are effectively equivalent to performing the Karhunen-Loeve transform, which is the optimal image compression method in the sense that it allows linear reconstruction of the input information with minimal squared error, the results obtained in practice reveal significant differences between the networks. An experimental study has been conducted to demonstrate these differences and thus some light is shed on the suitability of self-organizing neural networks for image compression, particularly in comparison to more conventional methods.

Series Name: Lecture Notes in Computer Science (LNCS); 686
Publisher: Springer, Berlin, Heidelberg
Uncontrolled Keywords: Hebbian learning for image compression, Principal component analysis, Self-organizing networks
Divisions: UNSPECIFIED
20 Department of Computer Science
20 Department of Computer Science > Interactive Graphics Systems
Event Title: New Trends in Neural Computation. Proceedings
Date Deposited: 16 Apr 2018 09:09
Export:
Suche nach Titel in: TUfind oder in Google

Optionen (nur für Redakteure)

View Item View Item