Image compression using topological maps and MLP - Université de Bretagne Occidentale Access content directly
Conference Papers Year : 1993

Image compression using topological maps and MLP

Abstract

Image compression is an essential task for image storage and transmission. We propose a compression technique in which an MLP predictor takes advantage of the topological properties of the Kohonen algorithm. The Kohonen algorithm creates a code-book which is used for Vector Quantization of the source image. Then,an MLP is trained to predict references to code-book, allowing further compression. Even with difficult images, the result is a reduction of 15% to 20% of the bit rate compared with classical Vector Quantization techniques, for the same quality of decoded images.
Fichier principal
Vignette du fichier
1993_03_icnn_compression.pdf (946.53 Ko) Télécharger le fichier
Origin Files produced by the author(s)
Licence
Copyright

Dates and versions

hal-03221764 , version 1 (17-03-2023)

Licence

Copyright

Identifiers

Cite

Gilles Burel, Jean-Yves Catros. Image compression using topological maps and MLP. IEEE International Conference on Neural Networks, Mar 1993, San Francisco, United States. pp.727-731, ⟨10.1109/ICNN.1993.298645⟩. ⟨hal-03221764⟩

Collections

UNIV-BREST
37 View
10 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More