Modified fastica algorithm for separation of mixed images

摘要

We proposed a novel fast algorithm for Independent Component Analysis using a Non-Linear function which can be used for Blind Source Separation and finding performance parameters of fused images. Practical simulation shows that proposed non-linear function is able to give improved quality separated image. Increase in signal-to-noise ratio and reduction in RMSE and Amari error proves the enhancement in quality of separated image. We are also able to calculate execution time of the algorithm.