Fractal image compression using neural networks

In this paper, we propose neural network technologies to fractal image compression and decompression by implementing numerous comparisons and transformations that are required by the traditional methods. In this way, the computation time of encoding can be reduced for compressing an image, and the compression/decompression process can execute in parallel. Simulated results show that the neural network approach can obtain a high compression-ratio and a clear decompressed image. Thus, our neural network approach performs very well, which encourages us to proceed this research continuously.