Study of Information Extraction Algorithm of Poisson Noise Images Based on Fractional Order Differentiation

According to the characteristic of fractional order differentiation on signal processing, an information extraction algorithm based on fractional-order differentiation was presented. In the first place, by this means information extraction was carried out for Poisson noise images, and then a comprehensive analysis and comparison was carried on with the other results of information extraction using the classical integral order operator. Experimental results shows that the new method can not only extract texture information of smooth area, but also extract high-frequency edge information, and to a great extent, enjoys a better anti-noise performance for the Poisson noise.