Abstract: This paper presented a new algorithm to estimate the standard deviation of noise for nature images. It uses a gradient filter to estimate the noise on some parts which are selected by a controlled function from the tessellating image. The controlled function can be related to the preestimate of SNR. We optimally determined the controlled function as an exponential function by minimizing the total error. The controlled function can effectively offset the effect which is caused by filtering the image structure. Therefore unlike some existing algorithms which can only accurately estimate noise for images with limited range of noise intensity,the proposed algorithm can perfectly do this for images with the noise intensity range of extremely small to extremely heavy. Moreover, an iterative process which has fast convergence was implemented to obtain more robust solution. Quantitative comparisons with some existing algorithms on an image data set demonstrate that the proposed algorithm has high accuracy, and outperforms those existing algorithms used in this study.

Key words: Standard deviation, Tessellating, Controlled function, Preestimate of SNR