Transactions on Mass-Data Analysis of Images and Signals (ISSN:1868-6451)
Volume 1 - Number 1 - September 2009 - Pages 3-14
Intelligent System for Medical X-Rays Compression
A. Khashman, and K. Dimililer
Intelligent Systems Research Group (ISRG), Electrical and Electronic Engineering Department, Near East University, Lefkosa, Mersin 10, Turkey
Medical images require compression, before transmission or storage due to constrained bandwidth and storage capacity. An ideal image compression system must yield high quality compressed image with high compression ratio; this ratio can be achieved using transform-based image compression, however the contents of the image affects the choice of an optimum compression ratio and the optimum compression method. In this paper, two image compression methods are considered; namely Haar Wavelet Transform (HWT) and Discrete Cosine Transform (DCT). A neural network is trained to relate the x-ray image contents to their ideal compression method and its optimum compression ratio. Once trained, the neural network within the intelligent system would be capable of choosing the ideal compression method and its optimum compression ratio upon presenting the x-ray image to the network. Experimental results suggest that our proposed system can be efficiently used to compress x-ray images while maintaining high image quality.