Abstract
Compression of digital images has been a very important subject of research for several decades, and a vast number of techniques have been proposed. In particular, the possibility of image compression using Neural Networks (NNs) has been considered by many researchers in recent years, and several Feed-forward Neural Networks (FNNs) have been proposed with reported promising experimental results. Constructive One-Hidden-Layer Feedforward Neural Network (OHL-FNN) is one such architecture. We have previously proposed a new constructive OHL-FNN using Hermite polynomials for regression and recognition problems, and good experimental results were demonstrated. In this paper, we first modify and then apply our proposed OHL-FNN to compress still images and investigate its performance in terms of both training and generalization capabilities. Extensive experimental results for still images (Lena, Lake, and Girl) are presented. It is revealed that the performance of the constructive OHL-FNN using Hermite polynomials is quite good.
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
Netravali, A.N., Haskell, B.G.: Digital Pictures, Representation, Compression, and Standards. In: Lucky, R.W. (ed.) Applications of Communications Theory, 2nd edn., Plenum Publishing Corporation, New York (1995)
Dony, R.D., Haykin, S.: Neural Network Approaches to Image Compression. Proceedings of the IEEE 83, 288–303 (1995)
Cramer, C.: Neural Networks for Image and Video Compression: a Review. European Journal of Operational Research 108, 266–282 (1998)
Jiang, J.: Image Compression with Neural Networks — a Survey. Signal Processing: Image Communication 14, 737–760 (1999)
Basso, A., Kunt, M.: Autoassociative Neural Networks for Image Compression. European Trans. on Telecommunications and Related Technologies 3, 593–598 (1992)
Amerijckx, C., Verleysen, M., Thissen, P., Legat, J.-D.: Image Compression by Self-Organized Kohonen map. IEEE Trans. on Neural Networks 9, 503–507 (1998)
Venetianter, P.L., Roska, T.: Image Compression by Cellular Neural Networks. IEEE Trans. on Circuits and Systems I: Fundamental Theory and Applications 45, 205–215 (1998)
Sygnowski, W., Macukow, B.: Counter-propagation Neural Network for Image Compression. Optical Engineering 35, 2214–2217 (1996)
Cottrell, G.W., Munro, P., Zipser, D.: Learning Internal Representations from Gray-level Images: An Example of Extensional Programming. In: Proc. 9th Annual Conf. Cognitive Science Society, pp. 461–473 (1987)
Namphol, A., Chin, S.H., Arozuliah, M.: Image Compression with a Hierarchical Neural Network. IEEE Trans. on Aerospace and Electronic Sys. 32, 326–337 (1996)
Chang, Y., Kumar, D., Mahalingam, N.: Data Compression for Image Recognition. In: Proc. IEEE TENCON - Speech and Image Technologies for Computing and Telecommunications, pp. 399–402 (1997)
Panda, G., Singh, P.: A Novel Scheme of Data Compression and Reconstruction Using Multilayer Artificial Neural Network. Journal of the IETE 41, 329–334 (1995)
Benbenisti, Y., Kornreich, D., Mitchell, H.B., Schaefer, P.A.: New Simple Threelayer Neural Network for Image Compression. Opt. Eng. 36, 1814–1817 (1997)
Setiono, R., Lu, G.: Image Compression Using a Feedforward Neural Network. In: Proc. IEEE Int. Conf. Neural Networks, pp. 4761–4765 (1994)
Ash, T.: Dynamic Node Creation in Backpropagation Networks. Connection Sci. 1, 365–375 (1989)
Kwok, T.Y., Yeung, D.Y.: Objective Functions for Training New Hidden Units in Constructive Neural Networks. IEEE Trans. on Neural Networks 8, 1131–1148 (1997)
Ma, L., Khorasani, K.: New Pruning Techniques for Constructive Neural Networks with Application to Image Compression. Proc. of SPIE 4052, 298–308 (2000)
Ma, L., Khorasani, K.: Adaptive Structure Feed-forward Neural Networks Using Polynomial Activation Functions. Proc. of SPIE 4055, 120–129 (2000)
Ma, L., Khorasani, K.: Constructive Hermite Polynomial Feedforward Neural Networks with Application to Facial Expression Recognition. Proc. of SPIE (2001)
Rasiah, A.I., Togneri, R., Attikiouzel, Y.: Modeling 1-D Signals Using Hermite Basis Functions. IEE Proc.-Vis. Image Signal Process. 144, 345–354 (1997)
Hwang, J.N., Lay, S.R., Maechler, M., Martin, D., Schimert, J.: Regression Modeling in Back-propagation and Projection Pursuit Learning. IEE E Trans. Neural Networks 5, 342–353 (1994)
Fahlman, S.E., Lebiere, C.: The Cascade-correlation Learning Architecture. Tech. Rep., CMU-CS-90-100, Carnegie Mellon University (1991)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ma, L., Khorasani, K. (2005). Adaptive Constructive Neural Networks Using Hermite Polynomials for Image Compression. In: Wang, J., Liao, XF., Yi, Z. (eds) Advances in Neural Networks – ISNN 2005. ISNN 2005. Lecture Notes in Computer Science, vol 3497. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11427445_115
Download citation
DOI: https://doi.org/10.1007/11427445_115
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-25913-8
Online ISBN: 978-3-540-32067-8
eBook Packages: Computer ScienceComputer Science (R0)