Abstract
Backpropagation is one possible algorithm used to achieve image compression with a multi-layer neural net [l]. Associated with a quadratic cost function in a linear case, it is nothing but an indirect way to compress images with the Karhunen-Loève method [2]. So, in this case, this algorithm brings no improvement. However, the knowledge of the optimal solution helps us to study in detail, how the backpropagation algorithm solves the compression problem. We show that the convergence of the learning process can be accelerated by setting some constraints on the weights. The error function is then minimized for an unique value around which it is strictly convex.
In order to improve the visual appearance of restored images, we use the same algorithm associated to other cost functions (p-Hölder norms). Unlike the quadratic case, the theoretical optimal solution for the p-Hölder norms (p≠2) is not known, and backpropagation is shown to provide a relevant tool to compute the optimal solution.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
G. Cottrell, P. Munro, D. Zipser. Image compression by backpropagation: An example of extensional programming. In N.E. Sharkey (Ed). Advances in Cognitive science (Vol. 3). Norwood, NJ: Ablex.
H. Bourlard, Y. Kamp. Autoassociation by multilayer perceptrons and singular values decomposition. Manuscript 217. Philips research laboratory. Brussels. November 87.
Baldi, P., Hornik, K.: Neutral Network and principal component analysis. Learning from examples without local minima, preprint (1988).
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1990 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Mougeot, M., Azencott, R., Angeniol, B. (1990). A Study of Image Compression with Backpropagation. In: Soulié, F.F., Hérault, J. (eds) Neurocomputing. NATO ASI Series, vol 68. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-76153-9_39
Download citation
DOI: https://doi.org/10.1007/978-3-642-76153-9_39
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-76155-3
Online ISBN: 978-3-642-76153-9
eBook Packages: Springer Book Archive