Abstract

This work presents Wavelet-Modified Single Layer Linear Forward Only Counter Propagation Network (MSLLFOCPN) technique to solve image compression. In this technique, it inherits the properties of localizing the global spatial and frequency correlation from wavelets. Function approximation and prediction are obtained from neural networks. As a result counter propagation network was considered for its superior performance and the research enable us to propose a new neural network architecture named single layer linear counter propagation network (SLLC). The combination of wavelet and SLLC network were tested on several benchmark images and the experimental results shows that an enhancement in picture quality, compression ratio and approximation or prediction comparable to existing and traditional neural networks.

References

• Sonja Grgic, Kresimir Kers, Mislav Grgic. ‚ÄúImage compression using wavelets‚Äù, ISIE'99 - Bled, Slovenia, pp. 99-104.
• Poggio T., F. Girosi ‚ÄúNetworks for approximation and learning‚Äù, Proc. IEEE, Vol. 78, no.9, Sept 1990; pp. 1481 - 1497.
• Hornik K,‚Äù Multilayer feedforward networks are universal approximators‚Äù, Neural Networks, Vo1.2, no.5, pp. 359-366, 1989Tavel, P. 2007 Modeling and Simulation Design. AK Peters Ltd.
• Donald woods, ‚ÄúBack and Counter Propagation Abberations‚Äù, Proc. IEEE, Neural Networks, Vol. 1 1988, pp. 473-479.
• Deepak Mishra, N. S. C Bose, A. Tolambiya, A. Dwivedi, P. Kandula, A. Kumar, Prem K. Kalra, ‚ÄúColor Image Compression with Modified Forward-Only Counterpropagation Neural Network: Improvement of the Quality using Different Distance Measures‚Äù , Proceedings of the 9th IEEE International Conference on Information Technology, ICIT‚Äô06, India, (In press).
• A. K. M. Ashikur Rahman and Chowdhury Mofizur Rahman, ‚ÄúA New Approach for Compressing Color Images using Neural Network‚Äô‚Äô, CIMCA 2003 Proceedings/ISBN 1740880684: M. Mohammadian (Ed.) 12-14 February 2003, Vienna ‚Äì Austria.
• Christopher J.C. Burges, Henrique S. Malvar, Patrice Y. Simard, ‚ÄúImproving Wavelet Image Compression with Neural Networks‚Äù, MSR-TR- 2001-47, August 2001, pp. 1-18.
• D. Salomon, ‚ÄúData Compression: The Complete Reference‚Äù, Springer (India) pvt. Ltd., 2005
• Qiu, G.; T.J. Terrell; M.R.Varley; ‚ÄúImproved image compression using backpropagation network‚Äù, workshop on neural network applications and tools , September 13-14, 1993 pp. 73 ‚Äì 81.
• Sameh Ghwanmeh; Riyad Al-Shalabi; G.Kana‚Äôn and Luai Alnemi; ‚ÄúEnhanced neural network model based on a single layer linear counterpropagation for prediction and function approximation‚Äù, Information Technology Journal 5(1): 45-50, 2006.
• N.Sreekumar; Dr.Santhosh Baboo; ‚Äú A novel enhanced neural network model for image compression using wavelet-MSLLFOCPN. Proceedings of First International Conference On Intelligent Design and Analysis of Engineering Products, Systems and Computation, IDAEPSC‚Äô10, India, (in press).