Image Compression with Artificial Neural Networks
In this paper, we make an experimental study of some techniques of image compression based on artificial neural networks, particularly algorithm based on back-propagation gradient error . We also present a new hybrid method based on the use of a multilayer perceptron which combines hierarchical and adaptative schemes. The idea is to compute in a parallel way, the back propagation algorithm on an adaptative neural network that uses sub-neural networks with a hierarchical structure to classify the image blocks in entry according to their activity. The results come from the Yann Le Cun database , and show that the proposed hybrid method gives good results in some cases.
Keywordsneural networks image compression and coding back-propagation
Unable to display preview. Download preview PDF.
- 1.Benamrane, N., Benhamed Daho, Z., Shen, J.: Compression des images medicales par reseaux de neurones. USTO, Traitement Du Signal 6, 631–638 (1998)Google Scholar
- 3.Carrato, S.: Neural networks for image compression. In: Neural Networks: Adv. and Appli., 2nd edn., vol. 2, pp. 177–198. Gelende Pub. North-Holland, Amsterdam (1992)Google Scholar
- 4.de Bodt, E., Cottrell, M., Verleysen, M.: Using the Kohonen algorithm for quick initialisation of simple competitive learning algorithm. In: European Symposium on Artificial Neural Networks (2001)Google Scholar
- 5.Jiang, J.: Images compression with neural networks, A Survey. Signal Processing: Image Communication (1998)Google Scholar
- 7.Le-Cun, Y.: A competitive learning method for asymmetric threshold network. In: COGNITIVA 1985, Paris, June 4-7 (1985)Google Scholar
- 8.Mallat, S.G.: A Wavelet Tour of Signal Processing, pp. 145–150. Academic Press (1999)Google Scholar
- 11.Rabbani, M., Jones, P.W.: Digital Image Compression Techniques. Tutorial Texts. SPIE Optical Engineering Press (1991)Google Scholar
- 12.Ramel, M.J.Y., Agen, F., Michot, J.: Fractal compression, Jacquin methods, triangular subdivisions and Delaunay. EPUT, Depts.-Info (2004)Google Scholar