Einstein International Journal Organization(EIJO)

Abstract
It is well known that the classic image compression techniques such as JPEG and MPEG have serious limitations at high compression rate, the decompressed image gets really fuzzy or indistinguishable. To overcome this problem, artificial neural networks ANNs techniques are used. This paper presents a neural network based technique that may be applied to data compression. This paper breaks down large images into smaller windows and eliminates redundant information. Finally, the technique uses a neural network trained by direct solution methods. Conventional techniques such as Huffman coding and the Shannon Fano method, LZ Method, Run Length Method, LZ-77 are discussed as well as more recent methods for the compression of data presents a neural network based technique that may be applied to data compression. The proposed technique and images. Intelligent methods for data compression are reviewed including the use of Back propagation and Kohonen neural networks. The proposed method includes steps to break down large images into smaller windows for Lossless image compression/ decompression processes. Results obtained with proposed technique leads to better compression ratio at the same time preserving the image quality.
Keywords: Neural Network, Data Compression, Image Compression, ANN.

[1]. Jiang, J. A Neural Network Design for Image Compression and Indexing. International Conference on Artificial Intelligent Expert Systems and Neural Networks, Hawaii, USA, 1996, 296-299.
[2]. Joutsensalo, J. Non Linear Data Compression and Representation by Combining Self Organising Map and Subspace Rule, Vol-2 IEEE International Conference on Neural Networks, 1994, 637-642.
[3]. Blumenstein, M The Recognition of Printed and Handwritten Postal Address using Artificial Neural Networks. Dissertation, Griffith University, Australia, 1996.
[4]. Nelson M, The Data Compression Book M & T Publishing Inc. 1991.
[5]. Gelene R., and Sungar, M. Random Network Learning and Image Compression using Artificial Neural Networks, Vol-6 IEEE 1994, 3996-4001.
[6]. Sicuranza, G.L, Ramponi G, and Marsi S. Artificial Neural Network for image compression, Electronic letters, 1990, 477-479.
[7]. Ash, T. (1989) Dynamic Node Creation in Backpropagation Networks, 1989, 365-375.
[8]. Kenue S. K. Modified Back-Propagation Neural Network with Applications to Image Compression, SPIE Vol.1709, Applications of Artificial Neural Networks, 1992, 394-401.
[9]. Carbonara, M., Fowler J., and Ahalt, S, Compression of Digital Video Data using Artificial Neural Network Differential Vector Quantization, SPIE Vol. 1709, Applications of Artificial Neural Networks, 1992, 422-433.
[10]. Min, K., and Min, H. Neural Network Based Image Compression using AMT DAP 610, SPIE Vol. 1709, Application of Artificial Neural Networks, 1992,386-393.
[11]. Panchanathan, S., Yeap, T., and Pilache, B. A Neural Network for Image Compression, SPIE Vol. 1709, Application of Artificial Neural Networks, 1992 376-385.