The use of edge information for noise removal from digital images is of vital importance for preserving image details after filtering process. In this work, the edges in the speckled image are detected by employing a type-2 fuzzy edge detector and then the mean filter is used for removing speckle noise. Although the mean filter is effective for speckle noise removal, it also introduces undesirable blurrings, especially at the edges in the image. This can be a significant problem when the edge information is utilized for understanding and interpreting the image. The fuzzy edge detector can be highly efficient for detection of the edges correctly in the images with a minimum influence by the speckle noise. In the proposed filter, the mean filter window size is adjusted according to the edge information after detecting edges in the image. The window size in the vicinity of the edges is made smaller in comparison with the window size in the other areas to protect the edges. Experimental results demonstrate that the proposed method performs very well.