Nowadays, neural networks are largely used in signal processing and images. In particular, Kohonen networks or Self Organizing Maps are unsupervised learning models. This method performs a vector quantization (VQ) on the values obtained after processing. The vector quantization has a potential to give more data compression maintaining the same quality. In this paper we propose new scheme to image compression using Kohonen networks. The main innovation is to use the optimal Kohonen topological map to determine the optimal codebook, which can reduce the storage space, simplify data transfer and accelerate the process of data compression, unlike in classical Kohonen approach. To test our approach, we use the medical images. The results demonstrated the effectiveness of the proposed approach.

1. O. T. -C. Chen, B. J. Sheu, W. -C. Fang, 1994, "Image compression using self-organization networks", IEEE Trans. Circuits Syst. Video Technol. , vol. 4, pp. 480-489.
2. J. Elhachmi, Z. Guennoun. 2011, "Evolutionary Neural Networks Algorithm For The Dynamic Frequency Assignment Problem", International Journal of Computer Science & Information Technology (IJCSIT), Vol 3, No 3.
3. A. Eman, M. Asif, 2010, "Performance Analysis Of Multimedia Compression Algorithms", International journal of computer science & information Technology (IJCSIT) Vol. 2, No. 5.
4. E. Erwin, K. Obermayer, K. Schulten, 1992,"Self-organizing maps: Ordering, convergence properties and energy functions". Biol. Cyb. 67(1), pp. 47-55.
5. M. Ettaouil, Y. Ghanou, 2009, "Neural architectures optimization and Genetic algorithms", Wseas Transactions On Computer, Issue 3, Volume 8, pp. 526-537.
6. M. Ettaouil, Y. Ghanou, K. Elmoutaouakil, M. Lazaar, 2011, "A New Architecture Optimization Model for the Kohonen Networks and Clustering", Journal of Advanced Research in Computer Science (JARCS), Volume 3, Issue 1, pp. 14 - 32.
7. M. Goldberg, P. R. Boucher, S. Shlien, 1986, "Image Compression using adaptive vector quantization", IEEE Transactions on Communication, Vol. 34, No. 2, pp. 180-187.
8. R. M. Gray, "Vector quantization", IEEE Acoustics, speech and Signal Processing Magazine, 1984, pp. 4-29.
9. J. Jiang, 1999, "Image compression with neural networks – A survey", Signal processing :image communication n°14, pp 737-760.
10. T. Kohonen, 1995, "Self-Organizing Maps". Berlin/Heidelberg, Germany: Springer, vol. 30.
11. T. Kohonen, Self-organizing maps", Springer, 1997.
12. Y. Linde, A. Buzo, R. M. Gray, 1980,"An algorithm for vector quantizer design", IEEE Transactions on Communication, Vol. 28, No. 1, pp. 84 - 95.
13. N. Nasrabadi, Y. Feng, 1988,"Vector quantization of images based upon the Kohonen self-organizing feature maps", in IEEE Int. Conf. Neural Networks, San Diego, CA, vol. 1, pp. 101-108.
14. J. Pradeep, E. Srinivasan, S. Himavathi, 2011, "Diagonal Based Feature Extraction For Handwritten Alphabets Recognition System Using Neural Network", International Journal of Computer Science & Information Technology (IJCSIT), Vol 3, No 1.
15. Robert , Haykin, 1995, "Neural network approaches to images compression", in . Proceedings of the IEEE, vol 82, n° 2.
16. K. Sayood, "Introduction to Data Compression", Elsever, 2006.
17. J. Skowronski, I. Dologlou, 1997, "Image compression using permutative vector quantization", Signal Processing: Image Communications, Vol. 11, pp. 39-47.
18. C. Stanley and al. , " Competitive learning algorithms for vector quantization", in Neural networks, vol 3, 1990, pp. 277-290.
19. J. Ziv, A. Lempel, 1977, "A Universal Algorithm for Sequential Data Compression", IEEE Trans. on Inform. Theory, Vol. 23, May 1977, pp. 337-343.

Kohonen Networks Vector Quantization Image Compression Codebook