Abstract—This paper presents a novel lossy compression scheme for medical images by a new architecture Optimization model for the Self-Organized Map (OSOM). Both neural networks for lossy compression scheme are comparatively examined: Kohonen map and OSOM. This new approach based on genetic algorithms to determine the optimal parameters of neural networks. In the compression process of the proposed method, the medical image is decomposed into blocks of 4×4 pixels. The numerical results assess the effectiveness of the theoretical results shown in this paper, and the advantages of the new modeling.
Index Terms—Image medical compression, Vector Quantization, Codebook, Self-Organized Map, Genetic algorithms.
Mohamed Ettaouil is with the Faculty of Science and Technology of Fez, University Sidi Mohammed ben Abdellah, City Fez, MOROCCO, email: mohamedettaouil@yahoo.fr
Youssef Ghranou is with the Faculty of Science and Technology of Fez, University Sidi Mohammed ben Abdellah, City Fez, MOROCCO, email: youssefghanou@yahoo.fr
Karim El Moutaouakil is with the Faculty of Science and Technology of Fez , University Sidi Mohammed ben Abdellah, City Fez, MOROCCO, email: Karimmoutaouakil@yahoo.fr
Mohamed Lazaar is with the Faculty of Science and Technology of Fez, University Sidi Mohammed ben Abdellah, City Fez, MOROCCO, email: mohamedlazaar1@yahoo.fr
Cite: M. Ettaouil, Y. Ghanou, K. El Moutaouakil, M. Lazaar, "Image Medical Compression by A new Architecture Optimization Model for the Kohonen Networks," International Journal of Computer Theory and Engineering vol. 3, no. 2, pp. 204-210, 2011.
Copyright © 2008-2024. International Association of Computer Science and Information Technology. All rights reserved.
