A Complexity-Based Approach in Image Compression using Neural Networks

Authors: Hadi Veisi, Mansour Jamzad

Abstract:

In this paper we present an adaptive method for image compression that is based on complexity level of the image. The basic compressor/de-compressor structure of this method is a multilayer perceptron artificial neural network. In adaptive approach different Back-Propagation artificial neural networks are used as compressor and de-compressor and this is done by dividing the image into blocks, computing the complexity of each block and then selecting one network for each block according to its complexity value. Three complexity measure methods, called Entropy, Activity and Pattern-based are used to determine the level of complexity in image blocks and their ability in complexity estimation are evaluated and compared. In training and evaluation, each image block is assigned to a network based on its complexity value. Best-SNR is another alternative in selecting compressor network for image blocks in evolution phase which chooses one of the trained networks such that results best SNR in compressing the input image block. In our evaluations, best results are obtained when overlapping the blocks is allowed and choosing the networks in compressor is based on the Best-SNR. In this case, the results demonstrate superiority of this method comparing with previous similar works and JPEG standard coding.

Keywords: Adaptive image compression, Image complexity, Multi-layer perceptron neural network, JPEG Standard, PSNR.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1059877

References:

[1] R. C. Gonzales, R. E. Woods, Digital Image Processing, Second Edition, Prentice-Hall, 2002.
[2] Veisi H., Jamzad M., Image Compression Using Neural Networks, Image Processing and Machine Vision Conference (MVIP), Tehran, Iran, 2005.
[3] N.Sonehara, M.Kawato, S.Miyake, K.Nakane, Image compression using a neural network model, International Joint Conference on Neural Networks, Washington DC, 1989.
[4] G.L. Sicuranza, G. Ramponi, S. Marsi, Artificial neural network for image compression, Electronic letters 26, 477-479, 1990.
[5] S. Marsi, G. Ramponi, G. L. Sicuranza, Improved neural structure for image compression, Proceeding of International Conference on Acoustic Speech and Signal Processing, Torento, 1991.
[6] S. Carrato, G. Ramponi, Improved structures based on neural networks for image compression, IEEE Workshop on Neural Networks for Signal Processing, New Jersey, September 1991.
[7] S. Carrato, S. Marsi, Compression of subband-filterd images via neural networks, IEEE Workshop on Neural Networks for Signal Processing. August 1992.
[8] G. Qiu, M. Varley, T. Terrel, Image compression by edge pattern learning using multilayer perceptron, Electronic letters, Vol 29, No 7, April 1993.
[9] R.Sentiono, G. Lu, Image compression using a feedforward neural network, International Conference on Neural Networks, 1994.
[10] J. Jiang, Image compression with neural networks -A survey, Image Communication, ELSEVIER, Vol. 14, No. 9, 1999.
[11] C. Cramer, Neural networks for image and video compression: A review, European Journal of Operational Research, Vol. 108, July 1998.
[12] B. Verma, M. Blumenstein, and S. Kulkarni, A Neural Network Based Technique for Data Compression, Proceedings of the IASTED International Conference on Modelling and Simulation, MSO97, Singapore, 1997.
[13] A.Namphol, S.Chin, M. Arozullah, Image compression with a hierarchical neural network, IEEE Trans. Aerospace Electronic Systems Vol. 32 No.1, January 1996.
[14] J. S. Lin, S.H. Liu, A competitive continuous Hopfield neural network for vector quantization in image compression, Engineering Applications of Artificial Intelligence, Vol. 12, 1999.
[15] G. Pavlidis, A. Tsompanopoulos, A. Atsalakis, N. Papamarkos, C. Chamzas, A Vector Quantization - Entropy Coder Image Compression System, IX Spanish Symposium on Pattern Recognition and Image Processing, 2001.
[16] C. Amerijckx, J. D. Legaty, M. Verleysenz, Image Compression Using Self-Organizing Maps, Systems Analysis Modeling Simulation Vol. 43, No. 11, November 2003.
[17] S. Costa, S. Fiori, Image compression using principal component neural networks, Image and vision computing, Vol. 19, 2001.
[18] M. Egmont-Petersen, D. de Ridder, and H. Handels, Image processing with neural networks - a review, Pattern Recognition, vol. 35, pp. 2279-2301, 2002.
[19] A. Rahman and Chowdhury Mofizur Rahman, "A New Approach for Compressing Color Images using Neural Network", Proceedings of International Conference on Computational Intelligence for Modeling, Control and Automation - CIMCA 2003 , Vienna, Austria, 2003.
[20] Thomas M. Cover and Joy A. Thomas. Elements of Information Theory, John Wiley and Sons Inc., New York, N.Y., 1991.
[21] Sonja Grgic, Marta Mrak, Mislav Grgic, Comparison of JPEG Image Coders Proceedings of the 3rd International Symposium on Video Processing and Multimedia Communications, VIPromCom, pp. 79-85, Zadar, June 2001.