Fractal Image Compression and Decompression by Neural Network Approaches

Abstract

In image compression technologies, fractal image compression and decompression have advantages of high compression-ratio and low loss-ratio. But, it requires a great deal of computation, which limits its applications. And, still now, there is no parallel processing technique that had been designed and implemented. In this paper, we applied neural networks to implement the numerous computations of fractal image compression and decompression in parallel. The simulation results show that the quality of generated pictures by neural networks is similar to traditional methods, which verifies the high value of our research - the neural network technologies are useful and efficient for fractal image compression and decompression.