Bilateral filter is proven to be the best filter for edge detection techniques in literature, as it preserves the edges of the image while de-noising but this paper presents the effectiveness of Gaussian blur filter over bilateral filter. With the experiments performed on the natural scenes with different noises, we came on a conclusion that Gaussian blur filter perform better with respect to the bilateral filter. This paper also decides the range of noises which the user can tolerate while dealing with the image. The experiment is conducted on three natural scenes with the help of graph based image segmentation technique and result is validated using correlation.