Spline Recurrent Neural Networks for Quad-Tree Video Coding
In this paper a novel connectionist approach for video compression is presented. The basic idea is to extend to the temporal dimension the architecture used for the compression of still images. A multilayer perceptron (MLP) with infinite impulse response (IIR) synapses, embedded in a new quad-tree framework for video segmentation, is employed to take into account the video temporal dynamics. In order to reduce the computational burden and to improve the generalization performance, a flexible spline-based activation function, suitable for signal processing applications, has been used. Preliminary experimental results show that the proposed approach represents a viable alternative with respect to existing standards for high-quality video compression.
Keywordsvideo compression flexible activation function spline neural networks recurrent neural networks
Unable to display preview. Download preview PDF.
- S. Hay kin, ”Neural Networks (A comprehensive Foundation)”, 2nd Edition, Prentice-Hall, 1999.Google Scholar
- J. Woods, T. Naveen, ”A Filter Based Bit Allocation Scheme”, IEEE Trans. on Image Processing, Vol. 1, pp. 436–440, July 1992.Google Scholar
- R.D. Dony, S. Haykin, ”Neural Networks to Image Compression”, Proceedings of IEEE, Vol. 83, No. 2, pp. 228–303, February 1992.Google Scholar
- Cottrel G. W., Munro P., Zipser D., ”Image Compression by back propagation: an example of extensional programming”, in SHARKEY, N. E. (Ed.): ”Advances in cognitive science”, Ablex, Norwood, Nj., 1988.Google Scholar
- Parodi G., Passaggio F., ”Size-Adaptive Neural Network For Image Compression”, Int. Conf. on Image Processing, ICIP’ 94, Austin, TX, USA, 1994.Google Scholar
- Piazza F., Smerilli S., Uncini A., Griffo M., Zunino R., ”Fast Spline Neural Networks for Image Compression”, WIRN-96, Proc. Of the 8th Italian Workshop on Neural Nets, Vietri sul Mare, Salerno, Italy, 23–25 May 1996.Google Scholar
- R. Parisi, E. D. Di Claudio, G. Orlandi and B. D. Rao, ”Fast adaptive digital equalization by recurrent neural networks”, IEEE Trans. on Signal Processing, Special number on Neural Network applications, Vol. 45, No. 11, November 1997.Google Scholar